CN108573203A

CN108573203A - Identity identifying method and device and storage medium

Info

Publication number: CN108573203A
Application number: CN201710218218.8A
Authority: CN
Inventors: 范浩强; 陈可卿
Original assignee: Beijing Megvii Technology Co Ltd; Beijing Maigewei Technology Co Ltd
Current assignee: Beijing Megvii Technology Co Ltd; Beijing Maigewei Technology Co Ltd
Priority date: 2017-03-17
Filing date: 2017-04-05
Publication date: 2018-09-25
Anticipated expiration: 2037-04-05
Also published as: CN108573203B; CN112651348A; CN108629260B; CN108629260A; CN112651348B

Abstract

The embodiment provides a kind of identity identifying methods and device and storage medium.This method includes：Obtain the identification information of personnel to be certified；Judge whether identification information is authentication information, to obtain authentification of message result；In vivo detection is carried out to personnel to be certified, to obtain In vivo detection result；And determine whether the identity of personnel to be certified is legal according at least to authentification of message result and In vivo detection result.The above method and device judge to determine whether the identity of personnel to be certified is legal with In vivo detection in conjunction with authentication information, therefore compared with the conventional mode for being based purely on password or certificate progress authentication, the authentication result of identity identifying method and device according to the ... of the embodiment of the present invention is more acurrate, the safety that subscription authentication can be improved, so as to the equity of effective guarantee user.

Description

Identity identifying method and device and storage medium

Technical field

The present invention relates to image processing field, relate more specifically to a kind of identity identifying method and device and storage medium.

Background technology

The socialization that sci-tech product uses becomes the beautiful scenery together of modernized society's life, the clothing, food, lodging and transportion -- basic necessities of life of people Invariably closely related with science and technology, sci-tech product is gradually applied to different social sectors, and it is daily to become modern humans It lives indispensable important component.However, people also experience while enjoying the welfare that science product is brought Negative issue caused by it, for example, information security issue.

Current many fields all refer to information security issue, especially in e-commerce, mobile payment, the technologies such as open a bank account Field, information security issue are especially prominent.Specifically, currently, most in above-mentioned field carry out user using pin mode Interaction authentication (being referred to as authentication) is also had and is carried out user's interaction authentication by the way of brush certificate.Above two Mode has certain drawbacks, the former needs user to keep password firmly in mind, and it is relatively complicated to input password every time, once password is illegal Molecule is stolen, and the loss of privacy or property will be more caused to user, and for which, certificate is easy to be forged or falsely use, Its safety is relatively low.Therefore, it is necessary to a kind of convenient and safe identity identifying method or system be proposed, to be applied to electronics quotient Business, mobile payment, the technical fields such as open a bank account.

Invention content

The present invention is proposed in view of the above problem.The present invention provides a kind of identity identifying method and device and storages Medium.

According to an aspect of the present invention, a kind of identity identifying method is provided.This method includes：Obtain of personnel to be certified People's identification information；Judge whether identification information is authentication information, to obtain authentification of message result；To personnel to be certified into Row In vivo detection, to obtain In vivo detection result；And it is determined according at least to authentification of message result and In vivo detection result and waits recognizing Whether the identity of witness person is legal.

Illustratively, identification information is passport NO., name, certificate face, collection in worksite face, passport NO. Transformed value, the transformed value of name, the transformed value of certificate face and collection in worksite face transformed value in it is one or more.

Illustratively, before the identification information for obtaining personnel to be certified, identity identifying method further includes：Output is used In the instruction information for the personal information for indicating personnel's offer predefined type to be certified；Wherein, identification information is by be certified The personal information or obtained based on personal information that personnel provide.

Illustratively, identification information is the transformed value of the transformed value of passport NO., the transformed value of name, certificate face With it is one or more in the transformed value of collection in worksite face, the identification information for obtaining personnel to be certified includes：Acquisition waits for The initial information of certification personnel, wherein initial information is one in passport NO., name, certificate face and collection in worksite face Kind is a variety of；And initial information is converted based on pre-defined algorithm, the transformed value to obtain initial information is marked as individual Know information.

Illustratively, the identification information for obtaining personnel to be certified includes：The certificate image of personnel to be certified is obtained, In, authentification of message result is certificate authentication result；In vivo detection is carried out to personnel to be certified, to obtain In vivo detection result packet It includes：Obtain the facial image of personnel to be certified；And In vivo detection is carried out using facial image, to obtain In vivo detection result.

Illustratively, the identity that personnel to be certified are determined according at least to authentification of message result and In vivo detection result whether Before legal, identity identifying method further includes：Further decision is executed using certificate image and/or facial image to operate, to obtain Further decision result；The whether legal packet of the identity of personnel to be certified is determined according at least to authentification of message result and In vivo detection result It includes：Determine whether the identity of personnel to be certified is legal according to certificate authentication result, In vivo detection result and further decision result.

Illustratively, further decision operation includes certificate true and false judgement operation and/or face consistency judges operation, and Further decision result includes certificate true and false judging result and/or face consistency judging result, and the certificate true and false judges that operation includes： Judge whether the certificate in certificate image is real docu-ment, to obtain certificate true and false judging result；Face consistency judges operation Including：The certificate face of personnel to be certified is obtained according to certificate image；And by the certificate face of personnel to be certified and face figure Face as in is compared, to obtain face consistency judging result.

Illustratively, the certificate face for personnel to be certified being obtained according to certificate image includes：People is detected from certificate image Face, to obtain the certificate face of personnel to be certified.

Illustratively, the certificate face for personnel to be certified being obtained according to certificate image includes：Word is carried out to certificate image Identification, to obtain the text information in certificate image；Based on the text information in certificate image from certification certificate information data Matched certificate information is searched in library；And determine that the certificate face in certificate information search, matched is people to be certified The certificate face of member.

Illustratively, judge whether the certificate in certificate image is real docu-ment, to obtain certificate true and false judging result packet It includes：Extract the characteristics of image of certificate image；And characteristics of image is inputted into trained certificate grader, to obtain the certificate true and false Judging result；Wherein, certificate true and false judging result is the confidence level that the certificate in certificate image is real docu-ment.

Illustratively, judge whether the certificate in certificate image is real docu-ment, to obtain certificate true and false judging result packet It includes：Identification includes the image block of certificate identifier information from certificate image；And in the image block comprising certificate identifier information Certificate identifier information be identified, to obtain certificate true and false judging result；Wherein, certificate true and false judging result is certificate image In certificate be real docu-ment confidence level.

Illustratively, personnel to be certified are being determined according to certificate authentication result, In vivo detection result and further decision result Identity it is whether legal during, each result in certificate authentication result, In vivo detection result and further decision result tool There is respective weight coefficient.

Illustratively, the certificate image for obtaining personnel to be certified includes：It obtains and is waited for for described under the conditions of current shooting The pre- shooting image that the certificate of certification personnel acquires in real time；The image attributes of the pre- shooting image of assessment in real time；When pre- shooting image The assessed value of image attributes when being less than preset assessed value threshold value, pre- shooting is generated according to the image attributes of pre- shooting image and is carried Show information, for prompting personnel to be certified to adjust the shooting condition of its certificate；And the image attributes of image ought be shot in advance and is commented When valuation is equal to or more than preset assessed value threshold value, pre- shooting image is preserved with as certificate image.

Illustratively, judge whether identification information is authentication information, includes to obtain authentification of message result：Verification Part image carries out Text region, to obtain the text information in certificate image；And existed based on the text information in certificate image It is scanned in certification certificate information database, to obtain certificate authentication result；Wherein, certificate authentication result is certificate image In certificate information be certification certificate information confidence level.

Illustratively, Text region is carried out to certificate image, includes with the text information obtained in certificate image：To certificate Word in image is positioned, to obtain the image block for including word；And to the word in the block of the image comprising word into Row identification, to obtain the text information in certificate image.

Illustratively, before the word in the block of the image comprising word is identified, identity identifying method further includes： Image block comprising word is corrected to horizontality.

Illustratively, it is identified to the word in the block of the image comprising word, to obtain the word in certificate image After information, Text region is carried out to certificate image, further includes with the text information obtained in certificate image：Export certificate image In text information, so that user checks；Receive word update information input by user；By waiting for indicated by word update information Word is corrected to be compared with the corresponding word in the text information in certificate image；And if indicated by word update information Text word to be repaired and the corresponding word in the text information in certificate image between difference be less than preset discrepancy threshold, then The text information in certificate image is updated using word update information.

Illustratively, In vivo detection is carried out to personnel to be certified, includes to obtain In vivo detection result：Generate live body action Instruction, live body action command are used to indicate personnel to be certified and execute corresponding live body action；Obtain the people to be certified acquired in real time The facial image of member；Detect the face in facial image；And whether the face for judging in facial image executes live body action and refers to Indicated live body action is enabled, to obtain In vivo detection result.

Illustratively, In vivo detection is carried out to personnel to be certified, includes to obtain In vivo detection result：Generate live body action Instruction, live body action command are used to indicate personnel to be certified and execute corresponding live body action；Obtain the people to be certified acquired in real time The facial image of member；From captured in the facial image acquired personnel to be certified execute the skin area image before live body action and Execute the skin area image after live body action；And personnel to be certified are executed into the skin area image before live body action and are held Skin area image after the action of row live body inputs skin elasticity grader, to obtain In vivo detection result.

Illustratively, identity identifying method includes：It obtains true personnel and executes facial image and execution before live body action Facial image after live body action, and false personnel execute the facial image before live body action and execute the people after live body action Face image；It executes the facial image before live body acts from true personnel and executes in the facial image after live body action and extract really Personnel execute the facial image before live body action and execute the skin area image after live body action as positive sample image；From void The false personnel of extraction execute work in the facial image after facial image and execution live body action before dummy person's execution live body action The skin area image after facial image and execution live body action before body action is as negative sample image；And utilize positive sample Image and negative sample image train sorter model, to obtain skin elasticity grader.

Illustratively, the skin area figure before capturing personnel's execution live body action to be certified in the facial image acquired Picture and the skin area image executed after live body action include：Personnel to be certified are selected to execute work from the facial image acquired The facial image after facial image and execution live body action before body action；Using Face datection model to being held in personnel to be certified The face in the facial image after facial image and execution live body action before the action of row live body is positioned；Utilize face key Point location model is to executing the facial image before live body action in personnel to be certified and executing in the facial image after live body action The key point of face positioned；And the face location obtained according to positioning and key point position in personnel to be certified to holding The face in the facial image after facial image and execution live body action before the action of row live body carries out region division, to be waited for Certification personnel execute the skin area image before live body action and execute the skin area image after live body action.

Illustratively, identity identifying method further includes：Obtain sample facial image, the position of the face in sample facial image It is to have marked to set with the position of the key point of face；And neural metwork training is carried out using sample facial image, to obtain Obtain Face datection model and face key point location model.

Illustratively, In vivo detection is carried out to personnel to be certified, includes to obtain In vivo detection result：Acquisition is taken the photograph by binocular The facial image that the face of the personnel to be certified in the case where structure light is irradiated is acquired as scalp acupuncture；And it is determined according to facial image Whether the face of personnel to be certified belongs to live body, to obtain In vivo detection result.

Illustratively, In vivo detection is carried out to personnel to be certified, includes to obtain In vivo detection result：Step S110：It obtains Take one or more light images that the face for the personnel to be certified under the irradiation of detection light is acquired；Step S120： The reflective character showed in one or more light images based on the face of personnel to be certified determines personnel's to be certified Whether face belongs to live body, to obtain illumination live body verification result；And step S130：At least it is based on illumination live body verification result Determine whether certification personnel are verified by live body, to obtain In vivo detection result.

Illustratively, during irradiating the face of personnel to be certified, the pattern of detection light at least changes once.

Illustratively, during irradiating the face of personnel to be certified, the pattern of detection light is when each two is continuous It changes between quarter.

Illustratively, during irradiating the face of personnel to be certified, the pattern of detection light is changing at random or pre- First set.

Illustratively, In vivo detection is carried out to personnel to be certified, includes to obtain In vivo detection result：Step S140：It is defeated Go out action command, wherein action command is used to indicate certification personnel and executes corresponding action；Step S150：It obtains to be directed to and waits recognizing Multiple motion images that the face of witness person is acquired；Step S160：Personnel to be certified are detected based on multiple motion images to be held Capable action；And step S170：Determine whether the face of personnel to be certified belongs to according to motion detection result and action command Live body, to obtain action live body verification result；Step S130 includes：Based on illumination live body verification result and action live experience card knot Fruit determines whether personnel to be certified are verified by live body, to obtain In vivo detection result.

Illustratively, step S170 includes：If more based on being acquired in the period no more than the first preset time A motion images detect the action kept strokes indicated by executed by personnel to be certified and action command, it is determined that wait for The face of certification personnel belongs to live body, if based on the multiple motion images acquired in the first preset time be not detected by The action kept strokes indicated by personnel to be certified execute and action command, it is determined that the face of personnel to be certified does not belong to In live body.

Illustratively, identity identifying method further includes：It is counted during executing step S140 to step S170 every time Once, verification number is acted with acquisition；After step S170, identity identifying method further includes：If action live experience card knot Fruit indicates that the face of personnel to be certified is not belonging to live body, then exports the first error message, and judges whether action verification number reaches Step S130 is gone to if action verification number reaches the first frequency threshold value to the first frequency threshold value, if action verification time Number is not up to the first frequency threshold values, then return to step S140 or is returned in the case where step S110 is executed before step S140 Return step S110, wherein the first error message is used to prompt the live body authentication failed for personnel to be certified.

Illustratively, before step S110, identity identifying method further includes：Step S108：Judge personnel's to be certified Whether Image Acquisition condition meets preset requirement, if Image Acquisition condition meets preset requirement, goes to step S110, In, Image Acquisition condition includes personnel to be certified the location of in the image acquisition region of image collecting device and/or waits for The relative angle of certification personnel and image collecting device.

Illustratively, before step S108 or with step S108 simultaneously, identity identifying method further includes：Step S106：Export the first prompt message, wherein the first prompt message is for prompting personnel to be certified by face's face image collector It sets and close to image collecting device.

Illustratively, step S106 includes：By one or more defeated in speech form, image format and written form Go out the first prompt message.

Illustratively, step S108 includes：Obtain the realtime graphic acquired for the face of personnel to be certified；Output in real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is for showing；And according to face area Domain judges whether Image Acquisition condition meets preset requirement, if human face region is located in predeterminable area and human face region is in reality When image in proportion be more than the first preset ratio, it is determined that Image Acquisition condition meets preset requirement, if human face region It is not in predeterminable area or human face region proportion in realtime graphic is not more than the first preset ratio, it is determined that figure As acquisition condition is unsatisfactory for preset requirement.

Illustratively, identity identifying method further includes：If human face region in realtime graphic proportion no more than the One preset ratio, then output first acquires prompt message in real time, to prompt personnel to be certified and image collecting device close.

Illustratively, step S108 includes：Obtain the realtime graphic acquired for the face of personnel to be certified；Output in real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is for showing；And according in face Whether region decision Image Acquisition condition meets preset requirement, if human face region is located in predeterminable area and human face region exists Proportion is more than the second preset ratio in predeterminable area, it is determined that Image Acquisition condition meets preset requirement, if face area Domain is not in predeterminable area or human face region proportion in predeterminable area is not more than the second preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, identity identifying method further includes：If human face region in predeterminable area proportion no more than the Two preset ratios, then output second acquires prompt message in real time, to prompt personnel to be certified and image collecting device close.

Illustratively, identity identifying method further includes：Relative position between real-time judge human face region and predeterminable area Relationship；And third is exported based on the relative position relation between human face region and predeterminable area in real time and acquires prompt message, with Prompt changes the relative position relation between personnel to be certified and image collecting device so that human face region is leaned on predeterminable area Closely.

Illustratively, step S108 includes：Obtain the posture information of image collecting device；And judged according to posture information Whether image collecting device is in vertical placement status, if it is, determining that Image Acquisition condition meets preset requirement, otherwise really Determine Image Acquisition condition and is unsatisfactory for preset requirement.

Illustratively, identity identifying method further includes：It is counted during executing step S110 to step S120 every time Once, number is verified to obtain illumination；After step S120, identity identifying method further includes：If illumination live body verification knot Fruit indicates that the face of personnel to be certified is not belonging to live body, then exports the second error message, and judges whether illumination verification number reaches Step S130 is gone to if illumination verification number reaches the second frequency threshold value to the second frequency threshold value, if illumination verification time Number is not up to the second frequency threshold value, then return to step S108 or return to step S110, wherein the second error message is for prompting needle To the live body authentication failed of personnel to be certified.

Illustratively, before step S110 or during executing step S110 and step S120, authentication side Method further includes：Export the second prompt message, wherein the second prompt message is for prompting personnel to be certified in the second preset time It remains stationary as.

Illustratively, the second prompt message is count down information corresponding with the second preset time.

Illustratively, detection light is by dynamically changing color and/or the position of the light emitted to the face of personnel to be certified To obtain.

Illustratively, detection light is obtained in the following manner by display screen emissions, detection light：Screen is shown by change The content of upper display carrys out the pattern that dynamic changes the light of display screen emissions, to emit detection light to the face of personnel to be certified.

According to a further aspect of the invention, a kind of identification authentication system is provided.The device includes：Data obtaining module is used for Obtain the identification information of personnel to be certified；Authentication information judgment module, for judging whether identification information is Authentication information, to obtain authentification of message result；In vivo detection module, for carrying out In vivo detection to personnel to be certified, to obtain In vivo detection result；And identity determining module, it waits recognizing for determining according at least to authentification of message result and In vivo detection result Whether the identity of witness person is legal.

Illustratively, identification information is passport NO., name, certificate face, the transformed value of passport NO., name It is one or more in the transformed value of transformed value, the transformed value of certificate face and collection in worksite face.

Illustratively, identification authentication system further includes：Message output module is indicated, for being waited in data obtaining module acquisition Before the identification information of certification personnel, output is used to indicate the instruction that personnel to be certified provide the personal information of predefined type Information；Wherein, identification information is the personal information provided by personnel to be certified or is obtained based on personal information.

Illustratively, identification information is the transformed value of the transformed value of passport NO., the transformed value of name, certificate face With it is one or more in the transformed value of collection in worksite face, data obtaining module includes：Initial information acquisition submodule, is used for Obtain the initial information of personnel to be certified, wherein initial information is passport NO., name, certificate face and collection in worksite face In it is one or more；And transformation submodule, initial information is converted for being based on pre-defined algorithm, to obtain initial letter The transformed value of breath is as identification information.

Illustratively, data obtaining module includes：Certificate image acquisition submodule, the certificate for obtaining personnel to be certified Image, wherein authentification of message result is certificate authentication result；In vivo detection module includes：Facial image acquisition submodule, is used for Obtain the facial image of personnel to be certified；And detection sub-module, for carrying out In vivo detection using facial image, to obtain work Body testing result.

Illustratively, identification authentication system further includes：Further decision module is used in identity determining module according at least to letter Before breath authentication result and In vivo detection result determine whether the identity of personnel to be certified is legal, certificate image and/or people are utilized Face image executes further decision operation, to obtain further decision result；Identity determining module includes：Identity determination sub-module is used In determining whether the identity of personnel to be certified is legal according to certificate authentication result, In vivo detection result and further decision result.

Illustratively, further decision module includes certificate true and false judging submodule and/or face consistency judging submodule, Certificate true and false judging submodule judges operation for executing the certificate true and false, and face consistency judging submodule is for executing face one Cause property judges operation, and further decision result includes certificate true and false judging result and/or face consistency judging result,

Certificate true and false judging submodule includes：Certificate true and false judging unit, for whether judging the certificate in certificate image For real docu-ment, to obtain certificate true and false judging result；Face consistency sentences submodule：Certificate face acquiring unit is used In the certificate face for obtaining personnel to be certified according to certificate image；And face comparison unit, it is used for the card of personnel to be certified Part face is compared with the face in facial image, to obtain face consistency judging result.

Illustratively, certificate face acquiring unit includes：Certificate Face datection subelement, for being detected from certificate image Face, to obtain the certificate face of personnel to be certified.

Illustratively, certificate face acquiring unit includes：Text region submodule, for carrying out word knowledge to certificate image Not, to obtain the text information in certificate image；Search for subelement, for based on the text information in certificate image from certification Matched certificate information is searched in certificate information database；And certificate face determination subelement, for determine search, Certificate face in the certificate information matched is the certificate face of personnel to be certified.

Illustratively, certificate true and false judging unit includes：Feature extraction subelement, the image for extracting certificate image are special Sign；And input subelement judges knot for characteristics of image to be inputted trained certificate grader to obtain the certificate true and false Fruit；Wherein, certificate true and false judging result is the confidence level that the certificate in certificate image is real docu-ment.

Illustratively, certificate true and false judging unit includes：Image recognition subelement, for identifying packet from certificate image The image block of the information containing certificate identifier；And identification information identifies subelement, for the image block to including certificate identifier information In certificate identifier information be identified, to obtain certificate true and false judging result；Wherein, certificate true and false judging result is certificate figure Certificate as in is the confidence level of real docu-ment.

Illustratively, in identity determination sub-module according to certificate authentication result, In vivo detection result and further decision result During determining whether the identity of personnel to be certified is legal, certificate authentication result, In vivo detection result and further decision result In each result have respective weight coefficient.

Illustratively, certificate image acquisition submodule includes：Collecting unit is directed to for obtaining under the conditions of current shooting The pre- shooting image that the certificate of personnel to be certified acquires in real time；Assessment unit, the image category for assessing pre- shooting image in real time Property；Prompt unit, for when shooting the assessed value of image attributes of image in advance less than preset assessed value threshold value, being clapped according to pre- The image attributes for taking the photograph image generates pre- shooting prompt message, for prompting personnel to be certified to adjust the shooting condition of its certificate；With And storage unit, for when shooting the assessed value of image attributes of image in advance equal to or more than preset assessed value threshold value, protecting Pre- shooting image is deposited with as certificate image.

Illustratively, authentication information judgment module includes：Text region submodule, for carrying out word to certificate image Identification, to obtain the text information in certificate image；And search submodule, for being existed based on the text information in certificate image It is scanned in certification certificate information database, to obtain certificate authentication result；Wherein, certificate authentication result is certificate image In certificate information be certification certificate information confidence level.

Illustratively, Text region submodule includes：Text location unit, for determining the word in certificate image Position, to obtain the image block for including word；And word recognition unit, for being carried out to the word in the block of the image comprising word Identification, to obtain the text information in certificate image.

Illustratively, identification authentication system further includes：Word correction module is used in word recognition unit to including word Image word in the block be identified before, the image block comprising word is corrected to horizontality.

Illustratively, Text region submodule further includes：Word output unit, for exporting the letter of the word in certificate image Breath, so that user checks；Update information receiving unit, for receiving word update information input by user；Word comparison unit, For text word to be repaired and the corresponding word in the text information in certificate image indicated by word update information to be carried out pair Than；And word updating unit, if for the text word to be repaired indicated by word update information and the word in certificate image The difference between correspondence word in information is less than preset discrepancy threshold, then utilizes in word update information update certificate image Text information.

Illustratively, In vivo detection module includes：Instruction generates submodule, and for generating live body action command, live body is dynamic Make instruction and is used to indicate the corresponding live body action of personnel's execution to be certified；Realtime graphic acquisition submodule, what acquisition acquired in real time The facial image of personnel to be certified；Face datection submodule, for detecting the face in facial image；And live body action executes Judging submodule, for judging whether the face in facial image executes the live body action indicated by live body action command, to obtain Obtain In vivo detection result.

Illustratively, In vivo detection module includes：Instruction generates submodule, and for generating live body action command, live body is dynamic Make instruction and is used to indicate the corresponding live body action of personnel's execution to be certified；Realtime graphic acquisition submodule is adopted in real time for obtaining The facial image of the personnel to be certified of collection；Skin area captures submodule, waits recognizing for capturing from the facial image acquired Witness person executes the skin area image before live body action and executes the skin area image after live body action；And input submodule Block, for personnel to be certified to be executed to the skin area image before live body action and execute the skin area image after live body action Skin elasticity grader is inputted, to obtain In vivo detection result.

Illustratively, identification authentication system includes：True and false image collection module, it is dynamic for obtaining true personnel's execution live body The facial image after facial image and execution live body action before work, and false personnel execute the facial image before live body action With the facial image after execution live body action；Positive sample extracting sub-module, for executing the people before live body action from true personnel True personnel, which are extracted, in facial image after face image and execution live body action executes facial image and execution before live body action Skin area image after live body action is as positive sample image；Negative sample extracting sub-module, for executing work from false personnel False personnel, which are extracted, in the facial image after facial image and execution live body action before body action executes the people before live body acts Skin area image after face image and execution live body action is as negative sample image；And training submodule, for using just Sample image and negative sample image train sorter model, to obtain skin elasticity grader.

Illustratively, skin area capture submodule includes：Image selection unit, for from the facial image acquired The facial image after facial image and execution live body action before selecting personnel to be certified to execute live body action；Face detection list Member, after using Face datection model to executing the facial image before live body action in personnel to be certified and executing live body action Facial image in face positioned；Key point positioning unit, for using face key point location model to waiting recognizing Witness person executes the facial image before live body action and the key point of the face in the facial image after execution live body action carries out Positioning；And skin area obtaining unit, the face location and key point position for being obtained according to positioning are in people to be certified The face that member executes the facial image before live body action and executes in the facial image after live body action carries out region division, to obtain Personnel to be certified are obtained to execute the skin area image before live body action and execute the skin area image after live body acts.

Illustratively, identification authentication system further includes：Sample image acquisition module, for obtaining sample facial image, sample The position of face in this facial image and the position of the key point of face are to have marked；And training module, for profit Neural metwork training is carried out with sample facial image, to obtain Face datection model and face key point location model.

Illustratively, In vivo detection module includes：Structure light image acquisition submodule, for obtaining by binocular camera shooting scalp acupuncture The facial image that the face of personnel to be certified in the case where structure light is irradiated is acquired；And live body determination sub-module, it is used for root Determine whether the face of personnel to be certified belongs to live body according to facial image, to obtain In vivo detection result.

Illustratively, In vivo detection module includes：Light image acquisition submodule, for obtaining for the photograph in detection light One or more light images that the face of personnel to be certified under penetrating is acquired；Illumination live body verifies submodule, for being based on The reflective character that the face of personnel to be certified is showed in one or more light images determines the face of personnel to be certified Whether live body is belonged to, to obtain illumination live body verification result；And live body is verified determination sub-module, for being at least based on light Determine whether certification personnel are verified by live body according to live body verification result, to obtain In vivo detection result.

Illustratively, In vivo detection module includes：Output sub-module is instructed, is instructed for output action, wherein action refers to Order is used to indicate certification personnel and executes corresponding action；Motion images acquisition submodule, for obtaining for personnel's to be certified Multiple motion images that face is acquired；Motion detection submodule, for detecting personnel institute to be certified based on multiple motion images The action of execution；And action live experience card submodule, for determining people to be certified according to motion detection result and action command Whether the face of member belongs to live body, to obtain action live body verification result；Live body is verified determination sub-module：By true Order member, for determining whether personnel to be certified are tested by live body based on illumination live body verification result and action live body verification result Card, to obtain In vivo detection result.

Illustratively, action live experience card submodule includes：Live body determination unit, if for based on no more than first The multiple motion images acquired in the period of preset time detect indicated by executed by personnel to be certified and action command The action kept strokes, it is determined that the face of personnel to be certified belongs to live body, if based on being adopted in the first preset time The action kept strokes indicated by executed by personnel to be certified and action command is not detected in multiple motion images of collection, Then determine that the face of personnel to be certified is not belonging to live body.

Illustratively, identification authentication system further includes：First counting module, for instructing output sub-module in each run It is counted during verifying submodule to run action live body once, verification number is acted with acquisition；Live body verification device also wraps It includes：First authentication error execution module, if indicating that the face of personnel to be certified is not belonging to live for action live body verification result Body then exports the first error message, and judges whether action verification number reaches the first frequency threshold value, if action verification number Reach the first frequency threshold value, then start live body and be verified determination sub-module, if action verification number is not up to first number Threshold value then restarts instruction output sub-module or is run before instructing output sub-module in light image acquisition submodule In the case of restart light image acquisition submodule, wherein the first error message is used to prompt to be directed to personnel to be certified Live body authentication failed.

Illustratively, identification authentication system further includes：Condition judgment module, the Image Acquisition for judging personnel to be certified Whether condition meets preset requirement, if Image Acquisition condition meets preset requirement, starts light image acquisition submodule, In, Image Acquisition condition includes personnel to be certified the location of in the image acquisition region of image collecting device and/or waits for The relative angle of certification personnel and image collecting device.

Illustratively, identification authentication system further includes：First prompt message output module, for sentencing in condition judgment module Judge personnel to be certified before whether the Image Acquisition condition of disconnected personnel to be certified meets preset requirement or with condition judgment module Image Acquisition condition whether meet preset requirement simultaneously, export the first prompt message, wherein the first prompt message is for carrying Show personnel to be certified by face's face image collecting device and close to image collecting device.

Illustratively, the first prompt message output module includes：First prompt message output sub-module, for passing through voice The first prompt message of one or more outputs in form, image format and written form.

Illustratively, condition judgment module includes：First realtime graphic acquisition submodule is directed to people to be certified for obtaining The realtime graphic of the face acquisition of member；First real-time output sub-module, for being exported in real time for calibrating Image Acquisition condition Human face region in predeterminable area and realtime graphic is for showing；And first judging submodule, for scheming according in real time The human face region detected as in judges whether Image Acquisition condition meets preset requirement, if human face region is located at predeterminable area Interior and human face region proportion in realtime graphic is more than the first preset ratio, it is determined that Image Acquisition condition meets default It is required that if human face region is not in predeterminable area or human face region proportion in realtime graphic is not more than first Preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, identification authentication system further includes：First acquisition prompt output module, if for human face region in reality When image in proportion be not more than the first preset ratio, then in real time output first acquisition prompt message, to prompt people to be certified Member is close with image collecting device.

Illustratively, condition judgment module includes：Second realtime graphic acquisition submodule is directed to people to be certified for obtaining The realtime graphic of the face acquisition of member；Second real-time output sub-module, for being exported in real time for calibrating Image Acquisition condition Human face region in predeterminable area and realtime graphic is for showing；And second judgment submodule, for according in face area Domain judges whether Image Acquisition condition meets preset requirement, if human face region is located in predeterminable area and human face region is pre- If proportion is more than the second preset ratio in region, it is determined that Image Acquisition condition meets preset requirement, if human face region It is not in predeterminable area or human face region proportion in predeterminable area is not more than the second preset ratio, it is determined that figure As acquisition condition is unsatisfactory for preset requirement.

Illustratively, identification authentication system further includes：Second acquisition prompt output module, is used for real-time judge human face region Relative position relation between predeterminable area；And third acquires prompt output module, for being based on human face region and presetting Relative position relation between region exports third acquisition prompt message in real time, changes personnel to be certified and Image Acquisition with prompt Relative position relation between device is so that human face region is close with predeterminable area.

Illustratively, condition judgment module includes：Posture information acquisition module, the posture for obtaining image collecting device Information；And third judging submodule, for judging whether image collecting device is in vertical placement status according to posture information, If it is, determining that Image Acquisition condition meets preset requirement, otherwise determine that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, identity identifying method further includes：Second counting module, for running light image acquisition module to fortune It is counted during row illumination live body authentication module once, number is verified to obtain illumination；Identification authentication system further includes：Second Authentication error execution module, it is defeated if indicating that the face of personnel to be certified is not belonging to live body for illumination live body verification result Go out the second error message, and judge whether illumination verification number reaches the second frequency threshold value, if illumination verification number reaches the Two frequency threshold values then start live body and are verified determination sub-module, if illumination verification number is not up to the second frequency threshold value, Restart conditionss judgment module or restarting light image acquisition submodule, wherein the second error message is for prompting needle To the live body authentication failed of personnel to be certified.

Illustratively, identification authentication system further includes：Second prompt message output module, for obtaining son in light image Module obtains before the one or more light images acquired for the face of the personnel to be certified under the irradiation of detection light Or one acquired for the face of the personnel to be certified under the irradiation of detection light is obtained in light image acquisition submodule Or multiple light images and illumination live body verify face of the submodule based on personnel to be certified in one or more light images During the reflective character showed determines whether the face of personnel to be certified belongs to live body, the second prompt message is exported, Wherein, the second prompt message is for prompting personnel to be certified to be remained stationary as in the second preset time.

According to a further aspect of the invention, a kind of identification authentication system, including processor and memory are provided, wherein storage Computer program instructions are stored in device, for executing following steps when computer program instructions are run by processor：Acquisition waits for The identification information of certification personnel；Judge whether identification information is authentication information, to obtain authentification of message result；It is right Personnel to be certified carry out In vivo detection, to obtain In vivo detection result；And according at least to authentification of message result and In vivo detection As a result determine whether the identity of personnel to be certified is legal.

Illustratively, when computer program instructions are run by processor the acquisition personnel to be certified of used execution It is additionally operable to execute following steps before people's identification information, when computer program instructions are run by processor：Output, which is used to indicate, to be waited for Certification personnel provide the instruction information of the personal information of predefined type；Wherein, identification information is is provided by personnel to be certified Personal information or based on personal information obtain.

Illustratively, identification information is the transformed value of the transformed value of passport NO., the transformed value of name, certificate face With one or more in the transformed value of collection in worksite face, used execution when computer program instructions are run by processor The step of identification information for obtaining personnel to be certified includes：Obtain the initial information of personnel to be certified, wherein initial information It is one or more in passport NO., name, certificate face and collection in worksite face；And based on pre-defined algorithm to initially believing Breath is converted, to obtain the transformed value of initial information as identification information.

Illustratively, the individual of the acquisition personnel to be certified of used execution when computer program instructions are run by processor The step of identification information includes：Obtain the certificate image of personnel to be certified, wherein authentification of message result is certificate authentication result； When computer program instructions are run by processor used execution to personnel to be certified carry out In vivo detection, with obtain live body inspection Survey result the step of include：Obtain the facial image of personnel to be certified；And In vivo detection is carried out using facial image, to obtain In vivo detection result.

Illustratively, when computer program instructions are run by processor used execution according at least to authentification of message knot Before fruit and In vivo detection result determine the whether legal step of the identity of personnel to be certified, computer program instructions are by processor It is additionally operable to execute following steps when operation：Further decision is executed using certificate image and/or facial image to operate, to be added Judging result；Used execution examines according at least to authentification of message result and live body when computer program instructions are run by processor Survey result determines the identity of personnel to be certified, and whether legal step includes：According to certificate authentication result, In vivo detection result and Further decision result determines whether the identity of personnel to be certified is legal.

Illustratively, be additionally operable to execute when computer program instructions are run by processor waits for according to certificate image acquisition The step of certificate face of certification personnel includes：Face is detected from certificate image, to obtain the certificate face of personnel to be certified.

Illustratively, being obtained according to certificate image for used execution waits recognizing when computer program instructions are run by processor The step of certificate face of witness person includes：Text region is carried out to certificate image, to obtain the text information in certificate image； Based on the text information in certificate image matched certificate information is searched for from certification certificate information database；And determination is searched Rope to, certificate face that the certificate face in matched certificate information is personnel to be certified.

Illustratively, the certificate of used execution judged in certificate image when computer program instructions are run by processor Whether it is real docu-ment, includes the step of certificate true and false judging result to obtain：Extract the characteristics of image of certificate image；And it will Characteristics of image inputs trained certificate grader, to obtain certificate true and false judging result；Wherein, certificate true and false judging result is Certificate in certificate image is the confidence level of real docu-ment.

Illustratively, the certificate of used execution judged in certificate image when computer program instructions are run by processor Whether it is real docu-ment, includes the step of certificate true and false judging result to obtain：Identification includes certificate identifier from certificate image The image block of information；And the certificate identifier information in the block of the image comprising certificate identifier information is identified, to be demonstrate,proved Part true and false judging result；Wherein, certificate true and false judging result is the confidence level that the certificate in certificate image is real docu-ment.

Illustratively, when computer program instructions are run by processor used execution according to certificate authentication result, In vivo detection result and further decision result determine in the implementation procedure of the whether legal step of identity of personnel to be certified, certificate Each result in authentication result, In vivo detection result and further decision result has respective weight coefficient.

Illustratively, the certificate of the acquisition personnel to be certified of used execution when computer program instructions are run by processor The step of image includes：Obtain the pre- shooting image that the certificate for personnel to be certified under the conditions of current shooting acquires in real time； The image attributes of the pre- shooting image of assessment in real time；When the assessed value for the image attributes for shooting image in advance is less than preset assessed value threshold When value, pre- shooting prompt message is generated according to the image attributes of pre- shooting image, for prompting personnel to be certified to adjust its certificate Shooting condition；And it when shooting the assessed value of image attributes of image in advance equal to or more than preset assessed value threshold value, protects Pre- shooting image is deposited with as certificate image.

Illustratively, whether used execution judges identification information when computer program instructions are run by processor For authentication information, include the step of authentification of message result to obtain：Text region is carried out to certificate image, to obtain certificate figure Text information as in；And scanned in certification certificate information database based on the text information in certificate image, To obtain certificate authentication result；Wherein, it is certification certificate information that certificate authentication result, which is the certificate information in certificate image, Confidence level.

Illustratively, used execution carries out word knowledge to certificate image when computer program instructions are run by processor Not, include the step of the text information in certificate image to obtain：Word in certificate image is positioned, to be included The image block of word；And the word in the block of the image comprising word is identified, to obtain the letter of the word in certificate image Breath.

Illustratively, when computer program instructions are run by processor used execution to the image block comprising word In word the step of being identified before computer program instructions be additionally operable to execute following steps when being run by processor：It will packet Image block containing word is corrected to horizontality.

Illustratively, when computer program instructions are run by processor used execution to the image block comprising word In word be identified, the step of to obtain the text information in certificate image after, computer program instructions are by processor When operation used execution to certificate image carry out Text region, also wrapped the step of the text information in certificate image with obtaining It includes：The text information in certificate image is exported, so that user checks；Receive word update information input by user；Word is repaiied Text word to be repaired indicated by positive information is compared with the corresponding word in the text information in certificate image；And if text Text word to be repaired indicated by word update information is less than with the difference between the corresponding word in the text information in certificate image Preset discrepancy threshold then utilizes the text information in word update information update certificate image.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Live body action command is generated, live body action command is used to indicate to be certified Personnel execute corresponding live body action；Obtain the facial image of the personnel to be certified acquired in real time；Detect the people in facial image Face；And judge that the live body whether face in facial image executes indicated by live body action command acts, to obtain live body inspection Survey result.

Illustratively, be additionally operable to execute when computer program instructions are run by processor carries out live body to personnel to be certified It detects, includes the step of In vivo detection result to obtain：Live body action command is generated, live body action command is used to indicate to be certified Personnel execute corresponding live body action；Obtain the facial image of the personnel to be certified acquired in real time；From the facial image acquired It is middle to capture the skin area image before personnel's execution live body to be certified acts and execute the skin area image after live body action；With And the skin area image that personnel to be certified execute the skin area image before live body action and execute after live body action is inputted Skin elasticity grader, to obtain In vivo detection result.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Obtain true personnel It executes the facial image before live body acts and executes the facial image after live body action, and before false personnel's execution live body action Facial image and execute live body action after facial image；Facial image and execution before live body action are executed from true personnel After extracting the facial image before true personnel's execution live body action in facial image after live body action and executing live body action Skin area image is as positive sample image；After false personnel execute the facial image before live body action and execute live body action Facial image in extract false personnel and execute the facial image before live body action and execute the skin area figure after live body action As being used as negative sample image；And sorter model is trained using positive sample image and negative sample image, to obtain skin elasticity Grader.

Illustratively, used execution from the facial image acquired when computer program instructions are run by processor Capture the step that personnel to be certified execute the skin area image before live body action and execute the skin area image after live body action Suddenly include：From being selected in the facial image acquired, personnel to be certified execute the facial image before live body action and execution live body is dynamic Facial image after work；Using Face datection model to executing the facial image before live body action in personnel to be certified and executing work The face in facial image after body action is positioned；Using face key point location model to executing work in personnel to be certified The key point of the face in the facial image after facial image and execution live body action before body action is positioned；And according to The face location obtained and key point position are positioned to executing the facial image before live body action in personnel to be certified and executing work The face in facial image after body action carries out region division, to obtain the skin region before personnel to be certified execute live body action Skin area image after area image and execution live body action.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Obtain sample face The position of image, the position of the face in sample facial image and the key point of face is to have marked；And utilize sample Facial image carries out neural metwork training, to obtain Face datection model and face key point location model.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：It obtains by binocular camera for be certified under structure light irradiation The facial image that the face of personnel is acquired；And determine whether the face of personnel to be certified belongs to live body according to facial image, To obtain In vivo detection result.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Step S110：It obtains for the people to be certified under the irradiation of detection light One or more light images that the face of member is acquired；Step S120：Face based on personnel to be certified is in one or more The reflective character showed in light image determines whether the face of personnel to be certified belongs to live body, is tested with obtaining illumination live body Demonstrate,prove result；And step S130：At least determine whether certification personnel are verified by live body based on illumination live body verification result, to obtain Obtain In vivo detection result.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Step S140：Output action instructs, wherein action command is used to indicate Certification personnel execute corresponding action；Step S150：Obtain the multiple motion images acquired for the face of personnel to be certified； Step S160：The action performed by personnel to be certified is detected based on multiple motion images；And step S170：According to motion detection As a result determine whether the face of personnel to be certified belongs to live body with action command, to obtain action live body verification result；Computer The step S130 of used execution when program instruction is run by processor includes：Based on illumination live body verification result and action live body Verification result determines whether personnel to be certified are verified by live body, to obtain In vivo detection result.

Illustratively, the step S170 of used execution when computer program instructions are run by processor includes：If base In the multiple motion images acquired in the period no more than the first preset time detect it is being executed by personnel to be certified, with The action kept strokes indicated by action command, it is determined that the face of personnel to be certified belongs to live body, if based on first The multiple motion images acquired in preset time are not detected dynamic indicated by executed by personnel to be certified and action command Make consistent action, it is determined that the face of personnel to be certified is not belonging to live body.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Executing step every time It is counted during rapid S140 to step S170 once, verification number is acted with acquisition；After step S170, computer program Instruction is additionally operable to execute following steps when being run by processor：If action live body verification result indicates the face of personnel to be certified It is not belonging to live body, then exports the first error message, and judges whether action verification number reaches the first frequency threshold value, if action Verification number reaches the first frequency threshold value, then goes to step S130, if action verification number is not up to the first frequency threshold value, The return to step S140 or return to step S110 in the case where step S110 is executed before step S140, wherein first is wrong False information is used to prompt the live body authentication failed for personnel to be certified.

Illustratively, it when computer program instructions are run by processor before the step S110 of used execution, calculates Machine program instruction is additionally operable to execute following steps when being run by processor：Step S108：Judge the Image Acquisition of personnel to be certified Whether condition meets preset requirement, if Image Acquisition condition meets preset requirement, goes to step S110, wherein image is adopted Collection condition include personnel to be certified the location of in the image acquisition region of image collecting device and/or personnel to be certified with The relative angle of image collecting device.

Illustratively, when computer program instructions are run by processor before the step S108 of used execution or with meter The step S108 of calculation machine program instruction used execution when being run by processor simultaneously, by processor transported by computer program instructions It is additionally operable to execute following steps when row：Step S106：Export the first prompt message, wherein the first prompt message is waited for for prompting Certification personnel are by face's face image collecting device and close to image collecting device.

Illustratively, used step S106 includes when computer program instructions are run by processor：Pass through voice shape The first prompt message of one or more outputs in formula, image format and written form.

Illustratively, the step S108 of used execution when computer program instructions are run by processor includes：Obtain needle To the realtime graphic of the face acquisition of personnel to be certified；Predeterminable area and reality of the output for calibrating Image Acquisition condition in real time When image in human face region for showing；And Image Acquisition item is judged according to the human face region detected in realtime graphic Whether part meets preset requirement, if human face region is located in predeterminable area and human face region proportion in realtime graphic More than the first preset ratio, it is determined that Image Acquisition condition meets preset requirement, if human face region is not at predeterminable area Interior or human face region proportion in realtime graphic is not more than the first preset ratio, it is determined that Image Acquisition condition is unsatisfactory for Preset requirement.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：If human face region Proportion is not more than the first preset ratio in realtime graphic, then the first acquisition of output in real time prompt message, to prompt to wait to recognize Witness person is close with image collecting device.

Illustratively, the step S108 of used execution when computer program instructions are run by processor includes：Obtain needle To the realtime graphic of the face acquisition of personnel to be certified；Predeterminable area and reality of the output for calibrating Image Acquisition condition in real time When image in human face region for showing；And judge whether Image Acquisition condition meets default want according in human face region It asks, if human face region is located in predeterminable area and human face region proportion in predeterminable area is more than the second default ratio Example, it is determined that Image Acquisition condition meets preset requirement, if human face region is not in predeterminable area or human face region Proportion is not more than the second preset ratio in predeterminable area, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：If human face region Proportion is not more than the second preset ratio in predeterminable area, then the second acquisition of output in real time prompt message, to prompt to wait to recognize Witness person is close with image collecting device.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Real-time judge face Relative position relation between region and predeterminable area；And based on the relative position relation between human face region and predeterminable area Output third acquires prompt message in real time, changes the relative position relation between personnel to be certified and image collecting device with prompt So that human face region is close with predeterminable area.

Illustratively, the step S108 of used execution when computer program instructions are run by processor includes：Obtain figure As the posture information of harvester；And judge whether image collecting device is in vertical placement status according to posture information, such as Fruit is, it is determined that Image Acquisition condition meets preset requirement, otherwise determines that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Executing step every time It is counted during rapid S110 to step S120 once, number is verified to obtain illumination；In computer program instructions by processor After the step S120 of used execution when operation, it is additionally operable to execute following step when computer program instructions are run by processor Suddenly：If illumination live body verification result indicates that the face of personnel to be certified is not belonging to live body, the second error message is exported, and sentence Whether disconnected illumination verification number reaches the second frequency threshold value, if illumination verification number reaches the second frequency threshold value, goes to step Rapid S130, if illumination verification number is not up to the second frequency threshold value, return to step S108 or return to step S110, wherein Second error message is used to prompt the live body authentication failed for personnel to be certified.

Illustratively, it before the step S110 of used execution or is being counted when computer program instructions are run by processor When being run by processor during the step S110 and step S120 of used execution, computer program refers to calculation machine program instruction Order is additionally operable to execute following steps when being run by processor：Export the second prompt message, wherein the second prompt message is for prompting Personnel to be certified remain stationary as in the second preset time.

According to a further aspect of the invention, a kind of storage medium is provided, stores program instruction on a storage medium, program refers to It enables and is used to execute following steps at runtime：Obtain the identification information of personnel to be certified；Whether judge identification information For authentication information, to obtain authentification of message result；In vivo detection is carried out to personnel to be certified, to obtain In vivo detection result； And determine whether the identity of personnel to be certified is legal according at least to authentification of message result and In vivo detection result.

Illustratively, program instruction at runtime the used acquisition personnel to be certified executed identification information it Before, program instruction is additionally operable to execute following steps at runtime：Output is used to indicate the people that personnel to be certified provide predefined type The instruction information of member's information；Wherein, identification information is the personal information provided by personnel to be certified or is based on personal information It obtains.

Illustratively, identification information is the transformed value of the transformed value of passport NO., the transformed value of name, certificate face With one or more in the transformed value of collection in worksite face, the program instruction used acquisition people to be certified executed at runtime Member identification information the step of include：Obtain the initial information of personnel to be certified, wherein initial information be passport NO., It is one or more in name, certificate face and collection in worksite face；And initial information is converted based on pre-defined algorithm, To obtain the transformed value of initial information as identification information.

Illustratively, the step of the program instruction identification information of the used acquisition personnel to be certified executed at runtime Suddenly include：Obtain the certificate image of personnel to be certified, wherein authentification of message result is certificate authentication result；Program instruction is being transported When row used execution to personnel to be certified carry out In vivo detection, include the step of In vivo detection result to obtain：Acquisition waits for The facial image of certification personnel；And In vivo detection is carried out using facial image, to obtain In vivo detection result.

Illustratively, program instruction at runtime it is used execute according at least to authentification of message result and In vivo detection As a result before determining the whether legal step of the identity of personnel to be certified, program instruction is additionally operable to execute following step at runtime Suddenly：Further decision is executed using certificate image and/or facial image to operate, to obtain further decision result；Program instruction is being transported Used execution determines whether the identity of personnel to be certified closes according at least to authentification of message result and In vivo detection result when row The step of method includes：The identity of personnel to be certified is determined according to certificate authentication result, In vivo detection result and further decision result It is whether legal.

Illustratively, the program instruction used certificate that personnel to be certified are obtained according to certificate image executed at runtime The step of face includes：Face is detected from certificate image, to obtain the certificate face of personnel to be certified.

Illustratively, the program instruction used certificate that personnel to be certified are obtained according to certificate image executed at runtime The step of face includes：Text region is carried out to certificate image, to obtain the text information in certificate image；Based on certificate image In text information search for matched certificate information from certification certificate information database；And determine search, matching Certificate information in certificate face be personnel to be certified certificate face.

Illustratively, whether the used certificate judged in certificate image executed is really to demonstrate,prove to program instruction at runtime Part includes the step of certificate true and false judging result to obtain：Extract the characteristics of image of certificate image；And characteristics of image is inputted Trained certificate grader, to obtain certificate true and false judging result；Wherein, certificate true and false judging result is in certificate image Certificate is the confidence level of real docu-ment.

Illustratively, whether the used certificate judged in certificate image executed is really to demonstrate,prove to program instruction at runtime Part includes the step of certificate true and false judging result to obtain：Identification includes the image block of certificate identifier information from certificate image； And the certificate identifier information in the block of the image comprising certificate identifier information is identified, judge knot to obtain the certificate true and false Fruit；Wherein, certificate true and false judging result is the confidence level that the certificate in certificate image is real docu-ment.

Illustratively, program instruction at runtime it is used execute according to certificate authentication result, In vivo detection result In the implementation procedure of the whether legal step of identity for determining personnel to be certified with further decision result, certificate authentication result, work Each result in body testing result and further decision result has respective weight coefficient.

Illustratively, program instruction at runtime the certificate image of the used acquisition personnel to be certified executed the step of wrap It includes：Obtain the pre- shooting image that the certificate for personnel to be certified under the conditions of current shooting acquires in real time；Assessment in real time is pre- to clap Take the photograph the image attributes of image；When shooting the assessed value of image attributes of image in advance less than preset assessed value threshold value, according to pre- The image attributes for shooting image generates pre- shooting prompt message, for prompting personnel to be certified to adjust the shooting condition of its certificate； And when shooting the assessed value of image attributes of image in advance equal to or more than preset assessed value threshold value, pre- shooting image is preserved With as certificate image.

Illustratively, program instruction at runtime it is used execute judge whether identification information is the letter of certification It ceases, includes the step of authentification of message result to obtain：Text region is carried out to certificate image, to obtain the word in certificate image Information；And scanned in certification certificate information database based on the text information in certificate image, to obtain certificate Authentication result；Wherein, certificate authentication result is the confidence level that the certificate information in certificate image is certification certificate information.

Illustratively, program instruction at runtime it is used execute Text region is carried out to certificate image, to be demonstrate,proved The step of text information in part image includes：Word in certificate image is positioned, to obtain the image for including word Block；And the word in the block of the image comprising word is identified, to obtain the text information in certificate image.

Illustratively, program instruction at runtime it is used execute the word in the block of the image comprising word is carried out Before the step of identification, program instruction is additionally operable to execute following steps at runtime：Image block comprising word is corrected to water Level state.

Illustratively, program instruction at runtime it is used execute the word in the block of the image comprising word is carried out Identification, the step of to obtain the text information in certificate image after, program instruction at runtime it is used execute to certificate Image carries out Text region, further includes the step of the text information in certificate image to obtain：Export the word in certificate image Information, so that user checks；Receive word update information input by user；By the text word to be repaired indicated by word update information It is compared with the corresponding word in the text information in certificate image；And it is if to be modified indicated by word update information Difference between word and the corresponding word in the text information in certificate image is less than preset discrepancy threshold, then utilizes word Update information updates the text information in certificate image.

Illustratively, program instruction at runtime it is used execute In vivo detection is carried out to personnel to be certified, to obtain The step of In vivo detection result includes：Live body action command is generated, live body action command is used to indicate personnel's execution pair to be certified The live body action answered；Obtain the facial image of the personnel to be certified acquired in real time；Detect the face in facial image；And judge Whether the face in facial image executes the action of the live body indicated by live body action command, to obtain In vivo detection result.

Illustratively, program instruction at runtime it is used execute In vivo detection is carried out to personnel to be certified, to obtain The step of In vivo detection result includes：Live body action command is generated, live body action command is used to indicate personnel's execution pair to be certified The live body action answered；Obtain the facial image of the personnel to be certified acquired in real time；It is captured from the facial image acquired and waits recognizing Witness person executes the skin area image before live body action and executes the skin area image after live body action；And it will be to be certified Personnel execute the skin area image before live body action and execute the skin area image input skin elasticity point after live body action Class device, to obtain In vivo detection result.

Illustratively, program instruction is additionally operable to execute following steps at runtime：It obtains true personnel and executes live body action Preceding facial image and execute the facial image after live body action, and false personnel execute the facial image before live body action and Execute the facial image after live body action；After true personnel execute the facial image before live body action and execute live body action True personnel are extracted in facial image to execute the facial image before live body action and execute the skin area image after live body action As positive sample image；The facial image before live body action is executed from false personnel and is executed in the facial image after live body action The false personnel of extraction execute the facial image before live body action and execute the skin area image after live body action as negative sample Image；And sorter model is trained using positive sample image and negative sample image, to obtain skin elasticity grader.

Illustratively, program instruction at runtime it is used execute people to be certified is captured from the facial image acquired Member executes the skin area image before live body action and includes the step of executing the skin area image after live body action：From being adopted The face figure after facial image and execution live body action before selecting personnel to be certified to execute live body action in the facial image of collection Picture；Using Face datection model to executing the facial image before live body action in personnel to be certified and executing the people after live body action Face in face image is positioned；Using face key point location model to the people before personnel to be certified execute live body action Face image and the key point for executing the face in the facial image after live body action are positioned；And the people obtained according to positioning Face position and key point position are to executing the facial image before live body action in personnel to be certified and executing the people after live body action Face in face image carries out region division, and skin area image and execution before live body action are executed to obtain personnel to be certified Skin area image after live body action.

Illustratively, program instruction is additionally operable to execute following steps at runtime：Obtain sample facial image, sample face The position of face in image and the position of the key point of face are to have marked；And carry out god using sample facial image Through network training, to obtain Face datection model and face key point location model.

Illustratively, program instruction at runtime it is used execute In vivo detection is carried out to personnel to be certified, to obtain The step of In vivo detection result includes：Obtain the face institute for the personnel to be certified being directed to by binocular camera under structure light irradiation The facial image of acquisition；And determine whether the face of personnel to be certified belongs to live body according to facial image, to obtain live body inspection Survey result.

Illustratively, program instruction at runtime it is used execute In vivo detection is carried out to personnel to be certified, to obtain The step of In vivo detection result includes：Step S110：Obtain the face institute for the personnel to be certified under the irradiation of detection light One or more light images of acquisition；Step S120：Face based on personnel to be certified is in one or more light images The reflective character showed determines whether the face of personnel to be certified belongs to live body, to obtain illumination live body verification result；With And step S130：At least determine whether certification personnel are verified by live body based on illumination live body verification result, to obtain live body inspection Survey result.

Illustratively, program instruction at runtime it is used execute In vivo detection is carried out to personnel to be certified, to obtain The step of In vivo detection result includes：Step S140：Output action instructs, wherein action command is used to indicate certification personnel and holds The corresponding action of row；Step S150：Obtain the multiple motion images acquired for the face of personnel to be certified；Step S160： The action performed by personnel to be certified is detected based on multiple motion images；And step S170：According to motion detection result and move Make instruction and determine whether the face of personnel to be certified belongs to live body, to obtain action live body verification result；Program instruction is being run When used execution step S130 include：People to be certified is determined based on illumination live body verification result and action live body verification result Whether member is verified by live body, to obtain In vivo detection result.

Illustratively, the used step S170 executed includes program instruction at runtime：If based on no more than the The multiple motion images acquired in the period of one preset time detect being executed by personnel to be certified, signified with action command The action kept strokes shown, it is determined that the face of personnel to be certified belongs to live body, if based on the institute in the first preset time Multiple motion images of acquisition are not detected being executed by personnel to be certified, dynamic with keeping strokes indicated by action command Make, it is determined that the face of personnel to be certified is not belonging to live body.

Illustratively, program instruction is additionally operable to execute following steps at runtime：Step S140 is being executed every time to step It is counted during S170 once, verification number is acted with acquisition；In program instruction used the step of executing at runtime After S170, program instruction is additionally operable to execute following steps at runtime：If action live body verification result indicates people to be certified The face of member is not belonging to live body, then exports the first error message, and judges whether action verification number reaches the first frequency threshold value, If action verification number reaches the first frequency threshold value, step S130 is gone to, if action verification number is not up to for the first time Threshold value is counted, then the return to step S140 or return to step S110 in the case where step S110 is executed before step S140, In, the first error message is used to prompt the live body authentication failed for personnel to be certified.

Illustratively, before the program instruction at runtime used step S110 executed, program instruction is at runtime It is additionally operable to execute following steps：Step S108：Judge whether the Image Acquisition condition of personnel to be certified meets preset requirement, if Image Acquisition condition meets preset requirement, then goes to step S110, wherein Image Acquisition condition includes personnel to be certified in image The relative angle of location and/or personnel to be certified and image collecting device in the image acquisition region of harvester.

Illustratively, it is being run before the program instruction at runtime used step S108 executed or with program instruction When used execution step S108 simultaneously, program instruction is additionally operable to execute following steps at runtime：Step S106：Output First prompt message, wherein the first prompt message is for prompting personnel to be certified by face's face image collecting device and close Image collecting device.

Illustratively, the used step S106 executed includes program instruction at runtime：Pass through speech form, image shape The first prompt message of one or more outputs in formula and written form.

Illustratively, the used step S108 executed includes program instruction at runtime：It obtains and is directed to personnel to be certified Face acquisition realtime graphic；People in predeterminable area and realtime graphic of the output for calibrating Image Acquisition condition in real time Face region is for showing；And according to the human face region detected in realtime graphic to judge whether Image Acquisition condition meets pre- If it is required that if human face region is located in predeterminable area and human face region proportion in realtime graphic is more than first and presets Ratio, it is determined that Image Acquisition condition meets preset requirement, if human face region is not in predeterminable area or face area Domain proportion in realtime graphic is not more than the first preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, program instruction is additionally operable to execute following steps at runtime：If human face region is in realtime graphic Proportion is not more than the first preset ratio, then the first acquisition of output in real time prompt message, to prompt personnel to be certified and image Harvester is close.

Illustratively, the used step S108 executed includes program instruction at runtime：It obtains and is directed to personnel to be certified Face acquisition realtime graphic；People in predeterminable area and realtime graphic of the output for calibrating Image Acquisition condition in real time Face region is for showing；And judge whether Image Acquisition condition meets preset requirement according in human face region, if face area Domain is located in predeterminable area and human face region proportion in predeterminable area is more than the second preset ratio, it is determined that image is adopted Collection condition meets preset requirement, if human face region is not in predeterminable area or human face region is shared in predeterminable area Ratio is not more than the second preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, program instruction is additionally operable to execute following steps at runtime：If human face region is in predeterminable area Proportion is not more than the second preset ratio, then the second acquisition of output in real time prompt message, to prompt personnel to be certified and image Harvester is close.

Illustratively, program instruction is additionally operable to execute following steps at runtime：Real-time judge human face region and preset areas Relative position relation between domain；And third is exported based on the relative position relation between human face region and predeterminable area in real time Prompt message is acquired, the relative position relation between personnel to be certified and image collecting device is changed so that face area with prompt Domain is close with predeterminable area.

Illustratively, the used step S108 executed includes program instruction at runtime：Obtain image collecting device Posture information；And judge whether image collecting device is in vertical placement status according to posture information, if it is, determining figure As acquisition condition meets preset requirement, otherwise determine that Image Acquisition condition is unsatisfactory for preset requirement.

Illustratively, program instruction is additionally operable to execute following steps at runtime：Step S110 is being executed every time to step It is counted during S120 once, number is verified to obtain illumination；In program instruction used the step of executing at runtime After S120, program instruction is additionally operable to execute following steps at runtime：If illumination live body verification result indicates people to be certified The face of member is not belonging to live body, then exports the second error message, and judges whether illumination verification number reaches the second frequency threshold value, If illumination verification number reaches the second frequency threshold value, step S130 is gone to, if illumination verification number is not up to for the second time Threshold value is counted, then return to step S108 or return to step S110, wherein the second error message is used to prompt for personnel's to be certified Live body authentication failed.

Illustratively, it is being run before the program instruction at runtime used step S110 executed or in program instruction When used execution step S110 and step S120 during, program instruction is additionally operable to execute following steps at runtime： Export the second prompt message, wherein the second prompt message is for prompting personnel to be certified to be remained stationary as in the second preset time.

According to a further aspect of the invention, a kind of identification authentication system, including information collecting device, processor and storage are provided Device, wherein information collecting device is used to acquire the initial information of personnel to be certified；Computer program is stored in memory to refer to It enables, for executing following steps when computer program instructions are run by processor：The identification information of personnel to be certified is obtained, Wherein, identification information is initial information or is obtained based on initial information；Judge whether identification information is the letter of certification Breath is to obtain authentification of message result；In vivo detection is carried out to obtain In vivo detection result to personnel to be certified；And according at least to Authentification of message result and In vivo detection result determine whether the identity of personnel to be certified is legal.

Illustratively, information collecting device includes image collecting device and/or input unit.

Illustratively, information collecting device includes image collecting device, and image collecting device is additionally operable to acquire people to be certified The certificate image and facial image of member；The acquisition of used execution personnel to be certified when computer program instructions are run by processor Identification information the step of include：Obtain the certificate image of personnel to be certified, wherein authentification of message result is certificate certification As a result；When computer program instructions are run by processor used execution to personnel to be certified carry out In vivo detection, with obtain The step of In vivo detection result includes：Obtain the facial image of personnel to be certified；And In vivo detection is carried out using facial image, To obtain In vivo detection result.

Illustratively, identification authentication system further includes image collecting device, and image collecting device is for acquiring people to be certified The certificate image and facial image of member；The acquisition of used execution personnel to be certified when computer program instructions are run by processor Identification information the step of include：Obtain the certificate image of personnel to be certified, wherein authentification of message result is certificate certification As a result；When computer program instructions are run by processor used execution to personnel to be certified carry out In vivo detection, with obtain The step of In vivo detection result includes：Obtain the facial image of personnel to be certified；And In vivo detection is carried out using facial image, To obtain In vivo detection result.

Illustratively, image collecting device is further used for acquiring pre- shooting figure in real time for the certificate of personnel to be certified Picture；The step of certificate image of the acquisition personnel to be certified of used execution when computer program instructions are run by processor, wraps It includes：Obtain the pre- shooting image that the certificate for the personnel to be certified under the conditions of current shooting acquires in real time；Assessment in real time The image attributes of pre- shooting image；When shooting the assessed value of image attributes of image in advance less than preset assessed value threshold value, root Pre- shooting prompt message is generated according to the image attributes of pre- shooting image, for prompting personnel to be certified to adjust the shooting item of its certificate Part；And when shooting the assessed value of image attributes of image in advance equal to or more than preset assessed value threshold value, pre- shooting is preserved Image is with as certificate image.

Illustratively, identification authentication system further includes structure light source and binocular camera, wherein structure light source is used for waiting for The face emitting structural light of certification personnel；Binocular camera is used to adopt for the face of the personnel to be certified under structure light irradiation Collect facial image；When computer program instructions are run by processor used execution to personnel to be certified carry out In vivo detection, Include the step of In vivo detection result to obtain：Obtain the personnel's to be certified being directed to by binocular camera under structure light irradiation The facial image that face is acquired；And determine whether the face of personnel to be certified belongs to live body according to facial image, to obtain In vivo detection result.

Illustratively, information collecting device includes image collecting device, and identification authentication system further includes light source, wherein light Source is used to emit detection light to the face of personnel to be certified；The face that image collecting device is additionally operable to acquire personnel to be certified is being examined Survey one or more light images under the irradiation of light；Used execution treats when computer program instructions are run by processor Certification personnel carry out In vivo detection, include the step of In vivo detection result to obtain：Step S110：It obtains in detection light One or more light images that the face of personnel to be certified under irradiation is acquired；Step S120：Based on personnel's to be certified The reflective character that face is showed in one or more light images determines whether the face of personnel to be certified belongs to live body, To obtain illumination live body verification result；And step S130：Whether certification personnel are at least determined based on illumination live body verification result It is verified by live body, to obtain In vivo detection result.

Illustratively, identification authentication system further includes light source and image collecting device, wherein light source is used for people to be certified The face of member emits detection light；Image collecting device is additionally operable to acquire one of the face of personnel to be certified under the irradiation of detection light A or multiple light images；Used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Step S110：It obtains for the people to be certified under the irradiation of detection light One or more light images that the face of member is acquired；Step S120：Face based on personnel to be certified is in one or more The reflective character showed in light image determines whether the face of personnel to be certified belongs to live body, is tested with obtaining illumination live body Demonstrate,prove result；And step S130：At least determine whether certification personnel are verified by live body based on illumination live body verification result, to obtain Obtain In vivo detection result.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Step S140：Output action instructs, wherein action command is used to indicate Certification personnel execute corresponding action；Step S150：Obtain the multiple motion images acquired for the face of personnel to be certified； Step S160：The action performed by personnel to be certified is detected based on multiple motion images；And step S170：According to motion detection As a result determine whether the face of personnel to be certified belongs to live body with action command, to obtain action live body verification result；Computer The step S130 of used execution when program instruction is run by processor includes：Based on illumination live body verification result and action live body Verification result determines whether personnel to be certified are verified by live body, to obtain In vivo detection result；Image collecting device is additionally operable to Acquire the multiple motion images.

Illustratively, the identification authentication system further comprises display device, wherein computer program instructions are handled The step S108 of used execution includes when device operation：Obtain the realtime graphic acquired for the face of personnel to be certified；In real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is exported for showing；And according to The human face region detected in realtime graphic judges whether Image Acquisition condition meets preset requirement, if human face region is located in advance If in region and human face region proportion in realtime graphic is more than the first preset ratio, it is determined that Image Acquisition condition is full Sufficient preset requirement, if human face region is not in predeterminable area or human face region proportion in realtime graphic is little In the first preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement；Image collecting device is additionally operable to obtain the reality When image；Display device is for showing predeterminable area and human face region.

Illustratively, the live body verification device further comprises display device, wherein computer program instructions are handled The step S108 of used execution includes when device operation：Obtain the realtime graphic acquired for the face of personnel to be certified；In real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is exported for showing；And according to Human face region judges whether Image Acquisition condition meets preset requirement, if human face region is located in predeterminable area and face area Domain proportion in predeterminable area is more than the second preset ratio, it is determined that Image Acquisition condition meets preset requirement, if people Face region is not in predeterminable area or human face region proportion in predeterminable area is not more than the second preset ratio, then Determine that Image Acquisition condition is unsatisfactory for preset requirement；Image collecting device is additionally operable to obtain the realtime graphic；Display device is used In display predeterminable area and human face region.

According to a further aspect of the invention, a kind of identification authentication system is provided, including：Information collecting device is waited for for acquiring The initial information of certification personnel；And transmitting device, for initial information to be sent to server, and receives and service from server The whether legal authentication information of the identity about personnel to be certified that device obtains in the following manner：Obtain of personnel to be certified People's identification information, wherein identification information is initial information or is obtained based on initial information；Whether judge identification information It is authentication information to obtain authentification of message result；In vivo detection is carried out to obtain In vivo detection result to personnel to be certified；With And determine whether the identity of personnel to be certified is legal according at least to authentification of message result and In vivo detection result.

According to a further aspect of the invention, a kind of identification authentication system, including transmitting device, processor and memory are provided, Wherein, transmitting device is used to receive the initial information of personnel to be certified from client, and will be about the identity of personnel to be certified No legal authentication information is sent to client；Computer program instructions are stored in memory, computer program instructions are located For executing following steps when reason device operation：Obtain the identification information of personnel to be certified, wherein identification information is first Beginning information is obtained based on initial information；Judge identification information whether be authentication information to obtain authentification of message result； In vivo detection is carried out to obtain In vivo detection result to personnel to be certified；And according at least to authentification of message result and In vivo detection As a result determine whether the identity of personnel to be certified is legal.

Illustratively, when computer program instructions are run by processor the acquisition personnel to be certified of used execution It is additionally operable to execute following steps before people's identification information, when computer program instructions are run by processor：Output, which is used to indicate, to be waited for Certification personnel provide the instruction information of the personal information of predefined type；Transmitting device is additionally operable to indicate that information is sent to client To be exported by client；Wherein, identification information is the personal information provided by personnel to be certified or is obtained based on personal information .

Illustratively, the certificate of the acquisition personnel to be certified of used execution when computer program instructions are run by processor The step of image includes：Obtain the pre- shooting figure that the certificate for the personnel to be certified under the conditions of current shooting acquires in real time Picture；The image attributes of the pre- shooting image of assessment in real time；When the assessed value for the image attributes for shooting image in advance is less than preset assessment When being worth threshold value, pre- shooting prompt message is generated according to the image attributes of pre- shooting image, for prompting personnel to be certified to adjust it The shooting condition of certificate；And ought shoot in advance image image attributes assessed value be equal to or more than preset assessed value threshold value When, pre- shooting image is preserved with as certificate image；Transmitting device is additionally operable to receive pre- shooting image.

Illustratively, used execution carries out live body to personnel to be certified when computer program instructions are run by processor It detects, includes the step of In vivo detection result to obtain：Step S140：Output action instructs, wherein action command is used to indicate Certification personnel execute corresponding action；Step S150：Obtain the multiple motion images acquired for the face of personnel to be certified； Step S160：The action performed by personnel to be certified is detected based on multiple motion images；And step S170：According to motion detection As a result determine whether the face of personnel to be certified belongs to live body with action command, to obtain action live body verification result；Computer The step S130 of used execution when program instruction is run by processor includes：Based on illumination live body verification result and action live body Verification result determines whether personnel to be certified are verified by live body, to obtain In vivo detection result；Transmitting device is additionally operable to move Make instruction to be sent to client and receive multiple motion images from client.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Executing step every time It is counted during rapid S140 to step S170 once, verification number is acted with acquisition；After step S170, computer program Instruction is additionally operable to execute following steps when being run by processor：If action live body verification result indicates the face of personnel to be certified It is not belonging to live body, then exports the first error message, and judges whether action verification number reaches the first frequency threshold value, if action Verification number reaches the first frequency threshold value, then goes to step S130, if action verification number is not up to the first frequency threshold value, The return to step S140 or return to step S110 in the case where step S110 is executed before step S140, wherein first is wrong False information is used to prompt the live body authentication failed for personnel to be certified；Transmitting device is additionally operable to the first error message being sent to Client by client to be exported.

Illustratively, when computer program instructions are run by processor before the step S108 of used execution or with meter The step S108 of calculation machine program instruction used execution when being run by processor simultaneously, by processor transported by computer program instructions It is additionally operable to execute following steps when row：Step S106：Export the first prompt message, wherein the first prompt message is waited for for prompting Certification personnel are by face's face image collecting device and close to image collecting device；Transmitting device is additionally operable to the first prompt message Client is sent to be exported by client.

Illustratively, the identification authentication system further comprises display device, wherein computer program instructions are handled The step S108 of used execution includes when device operation：Obtain the realtime graphic acquired for the face of personnel to be certified；In real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is exported for showing；And according to The human face region detected in realtime graphic judges whether Image Acquisition condition meets preset requirement, if human face region is located in advance If in region and human face region proportion in realtime graphic is more than the first preset ratio, it is determined that Image Acquisition condition is full Sufficient preset requirement, if human face region is not in predeterminable area or human face region proportion in realtime graphic is little In the first preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement；Transmitting device is additionally operable to receive from client real When image and by predeterminable area and human face region be sent to client with by client export for showing.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：If human face region Proportion is not more than the first preset ratio in realtime graphic, then the first acquisition of output in real time prompt message, to prompt to wait to recognize Witness person is close with image collecting device；Transmitting device is additionally operable to the first acquisition prompt message being sent to client with by client End output.

Illustratively, the live body verification device further comprises display device, wherein computer program instructions are handled The step S108 of used execution includes when device operation：Obtain the realtime graphic acquired for the face of personnel to be certified；In real time The human face region in predeterminable area and realtime graphic for calibrating Image Acquisition condition is exported for showing；And according to Human face region judges whether Image Acquisition condition meets preset requirement, if human face region is located in predeterminable area and face area Domain proportion in predeterminable area is more than the second preset ratio, it is determined that Image Acquisition condition meets preset requirement, if people Face region is not in predeterminable area or human face region proportion in predeterminable area is not more than the second preset ratio, then Determine that Image Acquisition condition is unsatisfactory for preset requirement；Transmitting device is additionally operable to receive realtime graphic from client and by predeterminable area And human face region is sent to client to be exported by client for showing.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：If human face region Proportion is not more than the second preset ratio in predeterminable area, then the second acquisition of output in real time prompt message, to prompt to wait to recognize Witness person is close with image collecting device；Transmitting device is additionally operable to the second acquisition prompt message being sent to client with by client End output.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Real-time judge face Relative position relation between region and predeterminable area；And based on the relative position relation between human face region and predeterminable area Output third acquires prompt message in real time, changes the relative position relation between personnel to be certified and image collecting device with prompt So that human face region is close with predeterminable area；Transmitting device be additionally operable to by third acquisition prompt message be sent to client with by Client exports.

Illustratively, it is additionally operable to execute following steps when computer program instructions are run by processor：Executing step every time It is counted during rapid S110 to step S120 once, number is verified to obtain illumination；In computer program instructions by processor After the step S120 of used execution when operation, it is additionally operable to execute following step when computer program instructions are run by processor Suddenly：If illumination live body verification result indicates that the face of personnel to be certified is not belonging to live body, the second error message is exported, and sentence Whether disconnected illumination verification number reaches the second frequency threshold value, if illumination verification number reaches the second frequency threshold value, goes to step Rapid S130, if illumination verification number is not up to the second frequency threshold value, return to step S108 or return to step S110, wherein Second error message is used to prompt the live body authentication failed for personnel to be certified；Transmitting device is additionally operable to the second error message Client is sent to be exported by client.

Illustratively, it before the step S110 of used execution or is being counted when computer program instructions are run by processor When being run by processor during the step S110 and step S120 of used execution, computer program refers to calculation machine program instruction Order is additionally operable to execute following steps when being run by processor：Export the second prompt message, wherein the second prompt message is for prompting Personnel to be certified remain stationary as in the second preset time；Transmitting device be additionally operable to by the second prompt message be sent to client with It is exported by client.

Identity identifying method and device and storage medium according to the ... of the embodiment of the present invention judge and living in conjunction with authentication information Physical examination surveys to determine whether the identity of personnel to be certified is legal, therefore, password or certificate progress identity is based purely on conventional The mode of certification is compared, and the authentication result of identity identifying method according to the ... of the embodiment of the present invention is more acurrate, can improve user's mirror The safety of power, so as to the equity of effective guarantee user.

Description of the drawings

The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention, Feature and advantage will be apparent.Attached drawing is used for providing further understanding the embodiment of the present invention, and constitutes explanation A part for book is not construed as limiting the invention for explaining the present invention together with the embodiment of the present invention.In the accompanying drawings, Identical reference label typically represents same parts or step.

Fig. 1 shows showing for the exemplary electronic device for realizing identity identifying method according to the ... of the embodiment of the present invention and device Meaning property block diagram；

Fig. 2 shows the schematic flow charts of identity identifying method according to an embodiment of the invention；

Fig. 3 shows the schematic flow chart of identity identifying method in accordance with another embodiment of the present invention；

Fig. 4 shows the schematic flow chart of identity identifying method in accordance with another embodiment of the present invention；

Fig. 5 shows the schematic flow chart of the training step of skin elasticity grader according to an embodiment of the invention；

Fig. 6 shows that the exemplary electron for realizing identity identifying method in accordance with another embodiment of the present invention and device is set Standby schematic block diagram；

Fig. 7 shows the schematic flow chart of In vivo detection step according to an embodiment of the invention；

Fig. 8 shows the schematic flow chart of In vivo detection step in accordance with another embodiment of the present invention；

Fig. 9 shows the implementation process of In vivo detection step according to an embodiment of the invention；

Figure 10 shows the schematic block diagram of identification authentication system according to an embodiment of the invention；And

Figure 11 shows the schematic block diagram of identity authorization system according to an embodiment of the invention.

Specific implementation mode

In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiment of the present invention, rather than this hair Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor It should all fall under the scope of the present invention.

In order to solve problem as described above, a kind of identity identifying method of offer of the embodiment of the present invention and device and storage are situated between Matter.The identity identifying method and device and the identification of storage medium combination identification information and recognition of face carry out authentication, It is whether legal with the identity of determination personnel to be certified, that is, determine whether personnel to be certified there is permission to carry out subsequent consumption and payment Deng operation.Identity identifying method and device according to the ... of the embodiment of the present invention can easily and safely identify the body of personnel to be certified Part, it is a kind of safe interaction authentication mode, the technologies such as can be advantageously applied to e-commerce, mobile payment, open a bank account Field.

First, it describes referring to Fig.1 for realizing identity identifying method according to the ... of the embodiment of the present invention and device and storage The exemplary electronic device 100 of medium.

As shown in Figure 1, electronic equipment 100 include one or more processors 102, it is one or more storage device 104, defeated Enter device 106, output device 108 and image collecting device 110, these components pass through bus system 112 and/or other forms Bindiny mechanism's (not shown) interconnection.It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, and Unrestricted, as needed, the electronic equipment can also have other assemblies and structure.

The processor 102 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution The processing unit of the other forms of ability, and it is desired to execute to control other components in the electronic equipment 100 Function.

The storage device 104 may include one or more computer program products, and the computer program product can To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy The property lost memory is such as may include random access memory (RAM) and/or cache memory (cache).It is described non- Volatile memory is such as may include read-only memory (ROM), hard disk, flash memory.In the computer readable storage medium On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or The various data etc. generated.

The input unit 106 can be the device that user is used for inputting instruction, and may include keyboard, mouse, wheat One or more of gram wind and touch screen etc..

The output device 108 can export various information (such as image and/or sound) to external (such as user), and And may include one or more of display, loud speaker etc..

Described image harvester 110 can acquire certificate image (including video frame) and/or facial image (including video Frame), and acquired image is stored in the storage device 104 so that other components use.Image collecting device 110 It can be camera.It should be appreciated that image collecting device 110 is only example, electronic equipment 100 can not include image collector Set 110.In such a case, it is possible to using other image acquisition device certificate images and/or facial image, and will acquisition Image be sent to electronic equipment 100.

Illustratively, the exemplary electronic device for realizing identity identifying method according to the ... of the embodiment of the present invention and device can To be realized in the equipment of personal computer or remote server etc..

The embodiment of the present invention provides a kind of identity identifying method, including：Obtain the identification information of personnel to be certified；Sentence Whether the identification information of breaking is authentication information, to obtain authentification of message result；It lives to the personnel to be certified Physical examination is surveyed, to obtain In vivo detection result；And it is determined according at least to described information authentication result and the In vivo detection result Whether the identity of the personnel to be certified is legal.

In the following, identity identifying method according to an embodiment of the invention will be described with reference to figure 2.Fig. 2 shows according to this hair The schematic flow chart of the identity identifying method 200 of bright one embodiment.As shown in Fig. 2, identity identifying method 200 includes following Step.

In step S210, the identification information of personnel to be certified is obtained.

This paper institutes are mainly described so that the identification information of personnel to be certified is the certificate in certificate image as an example below The identity identifying method stated, in the case where actually using scene, identification information is not limited to this, and can be, for example, certificate number Code, name, certificate face (facial image detected from certificate image) and collection in worksite face (use Image Acquisition Device for personnel to be certified face acquire facial image) in one or more and/or passport NO. transformed values The transformed value (such as output valve of certain hashing algorithm) of (such as output valve of certain hashing algorithm), name, certificate face Transformed value (such as the output of certain hashing algorithm of transformed value (such as output valve of certain hashing algorithm) and collection in worksite face Value) in it is one or more.The type of identification information can be selected according to specific usage scenario, and the present invention marks individual The type selection for knowing information is not especially limited.

Step S210 may include：Obtain the certificate image of personnel to be certified.It can be by the certificate information in certificate image It is considered as identification information.

Certificate as described herein can include but is not limited to identity card, driver's license, passport, social security card etc..

Certificate image can be the certificate acquired image for personnel to be certified.Illustratively, certificate image can be with It is the original image that the image acquisition devices such as camera arrive, can also be to be pre-processed to obtain later to original image Image.

Certificate image can be by client device (such as mobile terminal, long-distance video automatic teller machine including camera (Video Teller Machine, VTM) etc.) electronic equipment 100 is sent to be carried out by the processor 102 of electronic equipment 100 Processing, the image collecting device 110 (such as camera) that can also include by electronic equipment 100 acquire and are transmitted to processor 102 are handled.

According to embodiments of the present invention, the certificate image for obtaining personnel to be certified may include：It obtains in current shooting condition The pre- shooting image that knit stitch acquires the certificate of personnel to be certified in real time；The image attributes of the pre- shooting image of assessment in real time；When pre- When shooting the assessed value of the image attributes of image less than preset assessed value threshold value, generated according to the image attributes of pre- shooting image Pre- shooting prompt message, for prompting personnel to be certified to adjust the shooting condition of its certificate；And the image of image ought be shot in advance When the assessed value of attribute is equal to or more than preset assessed value threshold value, pre- shooting image is preserved with as certificate image.

Pre- shooting refers to starting the shooting of image collecting device (such as camera of the mobile terminals such as mobile phone, tablet computer) It is (not yet practical complete that pattern and certificate to be captured is placed in the coverage of image collecting device carries out the process that shooting is found a view At photograph taking).

It is alternatively possible to carry out quality evaluation to the pre- shooting image that shooting obtains.For example, in pre- shooting process, it can To calculate the image attributes for carrying out shooting obtained pre- shooting image under the conditions of current shooting in real time.Illustratively, it shoots Condition can include but is not limited to it is following in it is one or more：The placement position of certificate, the placement angle of certificate, Image Acquisition The camera site of device, shooting angle of image collecting device etc..Illustratively, image attributes can include but is not limited to following In it is one or more：Certificate fog-level, certificate profile, certificate key position, certificate circumstance of occlusion, certificate size, certificate Word clarity etc..When the assessed value of image attributes is less than preset assessed value threshold value, it is believed that the pre- shooting image taken It is unqualified.At this point it is possible to generate corresponding pre- shooting prompt message according to image attributes and export the information, to prompt user Angle, the position etc. for adjusting certificate or image collecting device, until taking qualified pre- shooting image.Qualified pre- shooting The assessed value of image, that is, image attributes is equal to or more than the pre- shooting image of preset assessed value threshold value.When in pre photograph mode When taking qualified pre- shooting image, which can be preserved as the certificate figure acquired in step S210 Picture, judge for the subsequent certificate of certification and etc..Optionally, when the certain image attributes for shooting image in advance are unqualified, It can be adjusted to shooting image in advance, so that shooting image is qualified in advance, and then obtain required certificate image.For example, when pre- Shoot certificate size in image it is unqualified when, the operations such as can be cut, be scaled to shooting image in advance, make pre- shooting image In certificate size it is qualified.

In step S220, judge whether identification information is authentication information, to obtain authentification of message result.

In the case where identification information is the certificate information in certificate image, authentication information can be authentication proof Part information, authentification of message result can be certificate authentication results.That is, the card in identification information is certificate image In the case of part information, step S220 may include：Judge whether the certificate information in certificate image is certification certificate information, To obtain certificate authentication result.

For example, can be identified from certificate image with some relevant certificate informations of the certificate of personnel to be certified, such as The information such as identification card number, name on identity card, then, it can be determined that whether these certificate informations are certification certificate information, It is, judging whether the certificate of personnel to be certified is certification certificate.

The certificate information of certification about certification certificate can store in the database, herein be known as the database Certification certificate information database.It can be based on the certificate information identified from certificate image in certification certificate information database In scan for, i.e., will be from the certificate information that is identified in certificate image and the authentication proof in certification certificate information database Part information is compared, to judge whether the certificate in certificate image is certification certificate.

In one example, certification certificate information database can be stored in local, such as be stored in for realizing body In the storage device (storage device 104 as shown in Figure 1) of the equipment such as the server or client of identity authentication method and device.

In another example, certification certificate information database can be stored in (such as the public security of certain public service systems System) server in.The equipment such as server or client for realizing identity identifying method and device can pass through networking The server communication of docking mode and public service system searches for certificate information from the server of public service system.For example, Usually there is the certificate information (record information) of the competent person of certification on the net in public security, can be based on being obtained in step S210 The certificate image taken scans for searching in public security net, if the certificate information that can be found and be identified from the certificate image Matched certificate information (record information) can then determine the certificate in certificate image for certification certificate, as lawful document.

In another example, identification information is identification card number.Its identification card number can be inputted body by personnel to be certified Part authentication device.Identification authentication system can be examined based on the identification card number received in certification personal information database Rope, certification personal information database can store the identification card number of a large amount of certification personnel for this.If there is matched identity Card number illustrates that personnel to be certified are that certification personnel, identification information have been authentication information.Similarly, above-mentioned certification Personal information library can be optionally stored in the server of local or public service system.

It will be understood by those skilled in the art that being name, certificate face, collection in worksite face, card in identification information The transformed value of piece number code, the transformed value of name, the transformed value of certificate face or collection in worksite face transformed value embodiment in, The realization of the realization method of identity identifying method and the identity identifying method in the embodiment that identification information is identification card number Mode is similar, repeats no more.

In step S230, In vivo detection is carried out to personnel to be certified, to obtain In vivo detection result.

Step S230 may include：Obtain the facial image of personnel to be certified；And carry out live body inspection using facial image It surveys, to obtain In vivo detection result.

Facial image can be the face acquired image for personnel to be certified.Illustratively, facial image can be with It is the original image that the image acquisition devices such as camera arrive, can also be to be pre-processed to obtain later to original image Image.

Facial image can be sent to by client device (such as mobile terminal including camera) electronic equipment 100 with It is handled by the processor 102 of electronic equipment 100, it can also be by 110 (example of image collecting device that electronic equipment 100 includes Such as camera) it acquires and is transmitted to processor 102 and is handled.Step S230 may be used any existing or possible in the future real Existing biopsy method realizes that the present invention limits not to this.Illustratively, when the face in facial image is true people When face, it is believed that personnel to be certified are live bodies, and In vivo detection result can be 1, when the face in facial image is false face, It is live body to think personnel to be certified not, and In vivo detection result can be 0.

In step S240, according at least to authentification of message result and In vivo detection result determine personnel to be certified identity whether It is legal.

In one example, authentification of message result can be one of 1 and 0, wherein 1 indicates the personal mark of personnel to be certified It is authentication information to know information, and 0 indicates that the identification information of personnel to be certified is not authentication information.Similarly, live body is examined It can be one of 1 and 0 to survey result, wherein 1 indicates that personnel to be certified are live body (being verified by live body), and 0 indicates people to be certified Member is not live body (not verified by live body).Illustratively, if any in authentification of message result and In vivo detection result Person is 0, it may be considered that the identity of personnel to be certified is illegal, i.e., personnel's failed authentication to be certified, in such a case, it is possible to Forbid its to carry out subsequent business operation, such as it is forbidden operations such as to carry out online trading or open a bank account.

In another example, authentification of message result can be any numerical value in [0,1] range, indicate personnel to be certified Identification information be authentication information confidence level.In such a case, it is possible to authentification of message result and In vivo detection As a result such as average weighted operation is carried out, and weighs whether personnel to be certified are competent persons according to operation result.Similar Embodiment will be described in more detail below, and not repeat herein.

It should be understood that the execution sequence of each step of identity identifying method 200 shown in Fig. 2 is only exemplary rather than limitation, example Such as, step S230 can before step S210, between step S210 and step S220 or with step S210 or S220 simultaneously It executes.

Identity identifying method according to the ... of the embodiment of the present invention judges in conjunction with authentication information and In vivo detection waits recognizing to determine Whether the identity of witness person is legal, therefore, compared with the conventional mode for being based purely on password or certificate progress authentication, root Authentication result according to the identity identifying method of the embodiment of the present invention is more acurrate, can improve the safety of subscription authentication, so as to With the equity of effective guarantee user.The above method can be advantageously applied to the various fields for being related to authentication, such as electronics The fields such as commercial affairs, mobile payment or banking.

Illustratively, identity identifying method according to the ... of the embodiment of the present invention can be in setting with memory and processor It is realized in standby, device or system.

Identity identifying method according to the ... of the embodiment of the present invention can be deployed at Image Acquisition end, for example, can be deployed in It is mobile at the Image Acquisition end of the financial systems such as bank management system or to be deployed in smart mobile phone, tablet computer etc. At terminal.Alternatively, identity identifying method according to the ... of the embodiment of the present invention is deployed in server end (or cloud in which can also be distributed End) and client at.For example, can client collect identification information (such as acquisition certificate image or receive it is to be certified Passport NO., the name etc. of personnel's input) and/or acquisition facial image, client by the identification information being collected into and/or Collected facial image sends server end (or high in the clouds) to, and authentication is carried out by server end (or high in the clouds).

According to embodiments of the present invention, before step S210, identity identifying method 200 can also include：Output is for referring to Show that personnel to be certified provide the instruction information of the personal information of predefined type；Wherein, identification information is by personnel to be certified The personal information of offer is obtained based on personal information.

Due to database (such as above-mentioned certificate of certification information database or the certification people for storing authentication information Member's information database etc.) type of authentication information that is stored is fixed, so in order to smoothly implement authentication, needs User (personnel i.e. to be certified) is wanted to provide type the person identifier letter consistent with the type of authentication information that database is stored Breath.For this purpose, instruction information can be exported to indicate that personnel to be certified input the personal information of predefined type.It illustratively, can be with Instruction information is exported by forms such as word, image or voices.

For example, " name can be shown on a display screen：" and " identification card number：" such indicate that information, instruction are to be certified Personnel input corresponding personal information in the subsequent blank space of information type (i.e. name and identification card number).Personnel's input to be certified Personal information can be used directly as identification information, can also by it is carried out become bring obtain person identifier letter Breath.

In another example voice prompt as " ask the appearance of and show identity card " can be sent out by loud speaker, personnel to be certified provide After the identity card of oneself, identity card can be directed to and carry out Image Acquisition, obtain ID Card Image.In this example, personal mark Knowledge information is ID Card Image.

Output is used to indicate the instruction information that personnel to be certified provide the personal information of predefined type, is conducive to obtain valuable Value, the identification information that can be compared with authentication information, to be conducive to smoothly implement authentication.In addition, Indicate that the output of information can promote the interactive experience between user and identification authentication system.

It can be seen from the foregoing, identification information can be such as passport NO., name, certificate face and collection in worksite The raw information of face etc. can also be to be converted the transformed value obtained later to these raw informations.According to of the invention real Example is applied, in the transformed value and collection in worksite that identification information is the transformed value of passport NO., the transformed value of name, certificate face In the case of one or more in the transformed value of face, step S210 may include：The initial information of personnel to be certified is obtained, Wherein, initial information is one or more in passport NO., name, certificate face and collection in worksite face；And based on pre- Determine algorithm to convert initial information, to obtain the transformed value of initial information as identification information.

When by the storage of the personal information of certification personnel in the database, can using pre-defined algorithm, (such as certain is dissipated Row algorithm) personal information of certification personnel is converted, to obtain the authentication information of certification personnel.Mapping mode is Arbitrarily, it can be set as needed.Conversion process can be understood as a kind of cataloged procedure.

The initial information of personnel to be certified acquired in identification authentication system is typically the information without passing through transformation, such as Passport NO., name, certificate face, collection in worksite face etc..The subsequently comparison with authentication information for convenience, may be used Initial information is converted with algorithm consistent algorithm when generating authentication information, to obtain identification information.

According to embodiments of the present invention, in the case where identification information is the certificate information in certificate image, in step Before S240, identity identifying method 200 can also include：Further decision is executed using certificate image and/or facial image to operate, To obtain further decision result；Step S240 may include：According to certificate authentication result, In vivo detection result and further decision knot Fruit determines whether the identity of personnel to be certified is legal.

Further decision operation may include the people in one or more certificates and/or facial image in certificate image Face carries out the operation that authenticity or consistency judge.For example, further decision operation may include the certificate true and false judge operation and/or Face consistency judges operation.Judge except operation and In vivo detection operation in certification certificate, some other be directed to is added Face in certificate and/or facial image in certificate image carries out the operation that authenticity or consistency judge, this be conducive into One step improves the reliability of identity authentication result, so as to improve the safety for the application for being related to authentication.

The embodiment of the further decision operation of citing description below.

According to one embodiment, further decision operation may include that the certificate true and false judges operation.The certificate true and false judges operation May include：Judge whether the certificate in certificate image is real docu-ment, to obtain certificate true and false judging result.According to another Embodiment, further decision operation may include that face consistency judges operation.Face consistency judges that operation may include：According to Certificate image obtains the certificate face of personnel to be certified；And by the face in the certificate face of personnel to be certified and facial image It is compared, to obtain face consistency judging result.Above-mentioned two embodiment is described in conjunction with Fig. 3 and Fig. 4 separately below.

Fig. 3 shows the schematic flow chart of identity identifying method 300 in accordance with another embodiment of the present invention.Fig. 3 is described Be personnel to be certified identification information be certificate image in certificate information embodiment.Authentication shown in Fig. 3 Step S310, S330 of method 300 to S350 above with respect to identity identifying method 200 shown in Fig. 2 step S210 extremely It had been introduced in the description of S230, details are not described herein.According to the present embodiment, before step S360, identity identifying method 300 Can also include step S320.In step s 320, it executes the above-mentioned certificate true and false and judges operation.In step S360, according to certificate Authentication result (i.e. authentification of message result), In vivo detection result and certificate true and false judging result determine that the identity of personnel to be certified is It is no legal.

After executing the certificate true and false and judging operation, certificate true and false judging result can be obtained.Illustratively, the certificate true and false Judging result can be one of 1 and 0, wherein the certificate in 1 expression certificate image is real docu-ment, and 0 indicates in certificate image Certificate is false certificate.Certainly, certificate true and false judging result can also be any numerical value in [0,1] range, indicate certificate Certificate in image is the confidence level of real docu-ment.False certificate can be, for example, for the screen on mobile phone or apparatus such as computer The certificate or the certificate etc. obtained is forged using computer graphics techniques that curtain reproduction obtains.

Illustratively, if any of certificate authentication result, In vivo detection result and certificate true and false judging result It is 0, then can determines that the identity of personnel to be certified is illegal, otherwise can determines that the identity of personnel to be certified is legal.

Two kinds of illustrative embodiments of step S320 are described below.

In one example, step S320 may include：Extract the characteristics of image of certificate image；And it is characteristics of image is defeated Enter trained certificate grader, to obtain certificate true and false judging result；Wherein, certificate true and false judging result is in certificate image Certificate be real docu-ment confidence level.

Due to the interference effect of the wave between the photosensitive element and display of image collecting device, pass through reproduction computer or hand It will appear apparent periodical color fringe on image obtained from certificate photograph on machine screen, referred to as " moire fringes ".Mole Line is the important clue for distinguishing real docu-ment and reproduction certificate.Since moire fringes are presented periodically, in frequency domain mole The characteristic of line can be particularly evident.In addition, the color of moire fringes is also different from the color of real docu-ment.Therefore, can be based on mole Line differentiates whether the certificate in certificate image is reproduction certificate.

Illustratively, characteristics of image can include but is not limited in spectrum signature, textural characteristics and color characteristic at least One.

The certificate true and false judges that certificate grader involved in operation can be instructed in advance using great amount of samples certificate image It perfects.Illustratively, " grader " as described herein can be any existing or in the cards in the future based on engineering Grader of habit, such as support vector machines (Support Vector Machine, SVM) etc..

By taking identity card as an example, the training process of certificate grader may include：Acquisition and mark include real identity card ID Card Image and the ID Card Image for including reproduction identity card；Calculate separately the ID Card Image and packet for including real identity card The spectrum information of the ID Card Image of the identity card containing reproduction, using as respective characteristics of image；With the body comprising real identity card The characteristics of image of part card image is as positive sample, using the characteristics of image of the ID Card Image comprising reproduction identity card as negative sample Training sorter model, to obtain identity card grader.Then, in actual authentication procedures, for acquired body Part card image, can calculate its spectrum information as its characteristics of image, the characteristics of image of extraction is then inputted trained body Part card grader, to judge whether the identity card in acquired ID Card Image is reproduction identity card.

The certificate true and false judging result of certificate grader output can be that the certificate in certificate image is setting for real docu-ment Reliability.Confidence level can be any one numerical value in [0,1] range.

In another example, step S320 may include：Identification includes the figure of certificate identifier information from certificate image As block；And the certificate identifier information in the block of the image comprising certificate identifier information is identified, sentenced with obtaining the certificate true and false Disconnected result；Wherein, certificate true and false judging result is the confidence level that the certificate in certificate image is real docu-ment.

Certificate identifier information can be any information that can be identified for that real docu-ment.For example, certificate identifier information can wrap Include national emblem pattern, the certain special anti-false signs etc. on identity card or social security card.For example, real docu-ment is usually with more hidden The anti-false sign covered can determine the true and false of certificate by identifying anti-false sign.

The judgement of the certificate true and false is carried out above by characteristics of image and certificate true and false judgement is carried out by certificate identifier information Two examples can be realized simultaneously, you can judge to demonstrate,prove with its certificate identifier information with the characteristics of image simultaneously based on certificate image The true and false of part, those skilled in the art can understand the embodiment of this judgment mode by reading described above, this Place is without repeating.

It should be understood that the execution sequence of each step of identity identifying method 300 shown in Fig. 3 is only exemplary rather than limitation, example Such as, any moment that step S320 can be between step S310 and step S360 executes.

Fig. 4 shows the schematic flow chart of identity identifying method 400 in accordance with another embodiment of the present invention.Fig. 4 is described Be personnel to be certified identification information be certificate image in certificate information embodiment.Authentication shown in Fig. 4 The step S410 to S440 of method 400 is retouched above with respect to the step S210 to S240 of identity identifying method 200 shown in Fig. 2 It had been introduced in stating, details are not described herein again.According to the present embodiment, before step S470, identity identifying method 400 can also wrap Include step S450 and S460.In step S450 and S460, executes above-mentioned face consistency and judge operation.In step S470, root Determine whether the identity of personnel to be certified is legal according to certificate authentication result, In vivo detection result and face consistency judging result.

In step S450, the certificate face of personnel to be certified is obtained according to certificate image.

In one example, step S450 may include：Face is detected from certificate image, to obtain personnel's to be certified Certificate face.

Face (being typically human face photo) is generally included on certificate, herein referred as " certificate face ", with in facial image Face distinguish.In the case where certificate includes face, face can be detected from certificate image.In this way, can be straight The face that be detected from certificate image is connect as the certificate face of personnel to be certified, for the face in facial image into Row comparison.In addition, can be seen from the foregoing, the face detected from certificate image, which can also be used as identification information, to be made With.

In another example, step S450 may include：Text region is carried out to certificate image, to obtain the certificate Text information in image；Based on the text information in certificate image matched card is searched for from certification certificate information database Part information；And determine the certificate face in certificate information search, matched for the certificate face of personnel to be certified.

May not include face on certain certificates, in such a case, it is possible to utilize certification certificate information database In certificate information find out the certificate face of personnel to be certified.Certainly, it in the case where certificate includes face, can equally adopt The certificate face of personnel to be certified is found out in this way.

For example, certificate image is the ID Card Image of personnel X, Text region can be carried out from ID Card Image, to know The text informations such as other identification card number may then based on the text informations such as identification card number from the identity card database of public security system Search for matched ID card information.It, can be with if put on record the ID card information of personnel X in identity card database Search matched ID card information.The identification card number of personnel X, name, gender, people can be typically comprised in ID card information The essential informations such as face photo.The human face photo is required certificate face.Then, can by the certificate face with obtain before Facial image in face compared.

In step S460, the certificate face of personnel to be certified is compared with the face in facial image, to obtain people Face consistency judging result.

It will be compared with certificate face by the face of image acquisition device (face i.e. in facial image), such as Fruit similarity between the two is more than preset similarity threshold, it may be considered that the face and certificate face of acquisition belong to same People, otherwise, it is believed that the two is not belonging to same people.Thus, it is possible to obtain face consistency judging result.Illustratively, one Cause property judging result can be the similarity between face in certificate face and facial image, i.e., consistency result can be [0,1] any value in range.Illustratively, consistency judging result can also be one of 1 and 0, wherein 1 indicates certificate Face belongs to same people with the face in facial image, and 0 expression certificate face is not belonging to same people with the face in facial image.

Illustratively, if in certificate authentication result, In vivo detection result and face consistency judging result any one Person is 0, then can determine that the identity of personnel to be certified is illegal, otherwise can determine that the identity of personnel to be certified is legal.

It should be understood that similarly with Fig. 3, the execution sequence of each step of identity identifying method 400 shown in Fig. 4 is only example And it is unrestricted, for example, step S450 can before step S420 or after step S420 and before step S430 or It is performed simultaneously after step S430 and before step S440 or with step S420 or S430, while step S460 can be in step Before S440, later or simultaneously execute.Certainly, step S450 can also be performed simultaneously with step S440.

Above the implementation that the certificate true and false judges operation and face consistency judges operation is described respectively in connection with Fig. 3 and Fig. 4 Mode, it is to be understood that further decision operation may include that the certificate true and false judges that operation and face consistency judge operation. That is in authentication procedures, the true and false of certificate and the consistency of face can be judged simultaneously, and according to certificate Authentication result, In vivo detection result, certificate true and false judging result and face consistency judging result these four results, which determine, to wait recognizing Whether the identity of witness person is legal.

According to embodiments of the present invention, it is waited for according to the determination of certificate authentication result, In vivo detection result and further decision result It is every in certificate authentication result, In vivo detection result and further decision result during whether the identity of certification personnel is legal A result has respective weight coefficient.

Can be certificate authentication result in advance, (including for example above-mentioned certificate is true for In vivo detection result and further decision result Pseudo- judging result and/or face consistency judging result) in each result distribute weight coefficient.The weight coefficient of each result Size can as needed depending on, the present invention limits not to this.

Illustratively, the weight coefficient can be based on to certificate authentication result, In vivo detection result and further decision knot Fruit is weighted averagely, obtains averaged result.It is then possible to averaged result and preset threshold value are compared, If it is more than threshold value, it may be considered that the identity of personnel to be certified is legal, otherwise it is assumed that the identity of personnel to be certified does not conform to Method.

In the case where the identification information of personnel to be certified is the certificate information in certificate image, certificate certification knot Fruit, certificate true and false judging result and face consistency judging result may each be any value in [0,1] range.Certainly, The value of this three can also only be one of 0 and 1.The value of In vivo detection result is one of 0 and 1.It therefore, can be to these knots Fruit is weighted average or arithmetic average, acquires averaged result.Then, averaged result is compared with threshold value.

It is of course also possible to which directly the various detections for participating in authentication or judging result are simply summed, obtain The long and compares the long and with threshold value, judges whether the identity of personnel to be certified is legal.

Each result has respective weight coefficient, facilitates identity authorization system according to involved each in authentication Judge or the importance of detection operation adjusts its participation in authentication procedures, and then the standard of authentication can be improved Exactness.

According to embodiments of the present invention, step S220 (S330, S420) may include：Text region is carried out to certificate image, To obtain the text information in certificate image；And based on the text information in certificate image in certification certificate information database In scan for, to obtain certificate authentication result；Wherein, it is certification that certificate authentication result, which is the certificate information in certificate image, The confidence level of certificate information.

As described above, knowledge can be may then based on from the text information identified in certificate image in certificate image The text information not gone out searches for matched certificate information from certification certificate information database.Search result has typically been recognized There are the probability of matched certificate information (being referred to as confidence level) in card certificate information database, in this case, card Part authentication result can be search result.

According to embodiments of the present invention, Text region is carried out to certificate image, it can with the text information obtained in certificate image To include：Word in certificate image is positioned, to obtain the image block for including word；And to the image comprising word Word in the block is identified, to obtain the text information in certificate image.

The step of carrying out Text region to certificate image may be used any suitable Text region mode and realize.It retouches below State a kind of embodiment of Text region step.

It is possible, firstly, to be positioned to the word in certificate image, the position of word is determined.It then can be from certificate image It is middle to extract the image block for including word.Illustratively, certificate image can be inputted to trained neural network, with to certificate figure Word as in is positioned.

For example, a large amount of sample certificate image can be collected, by way of artificial or machine mark, sample certificate is indicated The position of image context word.Based on a large amount of sample certificate image marked by machine learning algorithm training for fixed The neural network of the position of position word.Certificate image acquired in actual identity verification process is inputted into trained nerve net Network, neural network can export the position of the word in the certificate image, for example, the apex coordinate of word region.

Then, the word in the image block (character area) comprising word can be identified, obtains Text region knot Fruit.It refers to converting the picture material of the image block comprising word to word that image comprising word word in the block, which is identified, Accord with the process of string.Illustratively, may be used traditional optical character recognition (Optical Character Recognition, OCR method) is identified：It is partitioned into each character first with binarization operation, then with template matches or pattern classification Mode identifies all characters.

Optionally, can also use sliding window (sliding window) recognition methods, from certificate image positioning and Word is identified, without relying on the result of binarization segmentation.

According to embodiments of the present invention, before the word in the block of the image comprising word is identified, authentication side Method 200 (300,400) can also include：Image block comprising word is corrected to horizontality.

In the step for carrying out positioning to the word in certificate image and the word in the block of the image comprising word being identified Can also include the steps that being adjusted (correction) to the position of word between rapid.In practical applications, the card in certificate image There may be certain angles of inclination for part, that is to say, that there may be certain angles of inclination for the image block comprising word.Cause This, can carry out school before the word in identifying certificate image to the image block (region i.e. where word) comprising word Just, it is converted into horizontal concordant state.Illustratively, due to the step of being positioned to the word in certificate image In, the coordinate on four vertex of word region in certificate image is had been obtained for, and obtained four vertex and included Image-region, that is, include the image block of word, therefore, only need to rotate it to water according to the coordinate of the image block comprising word Level state.

Image block comprising word is corrected to horizontality can be conveniently subsequently to the text in the block of the image comprising word Word is identified.

According to embodiments of the present invention, it is identified to the word in the block of the image comprising word, to obtain certificate image In text information after, to certificate image carry out Text region, further include with the text information obtained in certificate image：Output Text information in certificate image, so that user checks；Receive word update information input by user；By word update information institute The text word to be repaired indicated is compared with the corresponding word in the text information in certificate image；And if word amendment is believed Difference between the indicated text word to be repaired of breath and the corresponding word in the text information in certificate image is less than preset difference Different threshold value then utilizes the text information in word update information update certificate image.

During Text region, the step of word corrects can also be increased.When identifying word using OCR methods, for Some rarely used words, nearly word form, the word more than character stroke can have the case where identification mistake or recognition failures.Therefore, allow to use Family modification word can flexibly and easily solve the problems, such as that Text region exists, and improve the precision of Text region.Use described herein Family can be personnel to be certified described herein, can also be the other staff in addition to personnel to be certified, such as authentication system The administrative staff etc. of system.

Illustratively, the word letter identified from certificate image can be exported in the form of text importing or speech play etc. Breath, so that user checks.When user has found that Text region result has mistake, word update information can be inputted.It is receiving To after word update information input by user, can by indicated by word update information text word to be repaired and pair that identifies Word is answered to be compared.If difference between the two is less than preset discrepancy threshold, word update information can be utilized more Otherwise text information in new certificate image can not update text information.For example, if a word on certificate is known Not Wei " one ", which should be modified to " one " by word update information input by user instruction, since the two differs greatly, Identity authorization system can refuse the amendment requirement of user, be not modified to the word.

According to embodiments of the present invention, step S230 (S340 and S350 or S430 and S440) may include：It is dynamic to generate live body It instructs, live body action command is used to indicate personnel to be certified and executes corresponding live body action；Acquisition acquires to be certified in real time The facial image of personnel；Detect the face in facial image；And judge whether the face in facial image executes live body action The indicated live body action of instruction, to obtain In vivo detection result.

In one example, it can be generated by client device (such as mobile terminal, VTM etc. including camera) and defeated Go out live body action command, acquisition facial image (including still image or video), and In vivo detection is carried out using facial image. In another example, can live body action command be generated by cloud server, by client device (such as the shifting including camera Dynamic terminal, VTM etc.) it exports live body action command and acquires facial image, subsequent client device will be on the facial image of acquisition Cloud server is passed to, cloud server detects the face in facial image, and judges the authenticity of face.If sentenced Breaking, face be real human face, it may be considered that personnel to be certified are live bodies, otherwise it is considered that personnel to be certified are not live bodies. Illustratively, it in cloud server may include trained face true and false grader and false face type classification device.The face true and false Grader can be used for judging that the true and false of face, false face type classification device can be used for judging the case where face is false face The type of the lower falseness face.

The implementation that the action based on the face in facial image carries out the embodiment of In vivo detection is described below by example Mode, in order to the understanding to the present embodiment.

Live body action command can indicate that personnel to be certified make corresponding live body according to instruction and act.Live body action command Indicated live body action can be that single static state acts and (is equivalent to one posture of pendulum), can also be the action of variation.Show Example property, live body action command can be generated and be exported before acquiring facial image, during acquiring facial image not It changes.Illustratively, live body action command can also be continuous instruction sequence, i.e., during acquiring facial image It is continuously generated and is exported different instructions, indicates that personnel to be certified follow instruction to change the live body action that it is made.

Above-mentioned live body action can be, for example, finger presses two cheek skins, gulping down gas in mouth heaves two cheeks, or reads aloud one Section word etc..When personnel to be certified execute one or more live body actions, its facial image can be acquired, is judged performed by it Live body action it is whether qualified, if so, In vivo detection success, otherwise, In vivo detection failure.For example, if live body action refers to It enables indicated live body action to read aloud passage, then can acquire the facial image during reading aloud, judge facial image In face lip it is dynamic whether with the dynamic matching of the lip of corresponding word, if matching, In vivo detection is successful.

According to embodiments of the present invention, step S230 (S340 and S350 or S430 and S440) may include：It is dynamic to generate live body It instructs, live body action command is used to indicate personnel to be certified and executes corresponding live body action；Acquisition acquires to be certified in real time The facial image of personnel；The skin area image before live body acts is executed from personnel to be certified are captured in the facial image acquired With the skin area image after execution live body action；And by personnel to be certified execute live body action before skin area image and It executes the skin area image after live body action and inputs skin elasticity grader, to obtain In vivo detection result.

When personnel to be certified execute one or more live body actions, can respectively be captured from collected facial image The personnel to be certified execute the skin area image after the preceding live body action with execution of live body action.Whether personnel to be certified, which start, is held The action of row live body can be judged according to collected facial image.For example, the face in facial image can be monitored, according to The state change of face determines that personnel to be certified start to execute the time of live body action.The face acquired before the time started Image executes the facial image before live body action as personnel to be certified.Then, the face in facial image can be continued to monitor For a period of time, which is the estimation duration of live body action.The face figure acquired after the duration terminates As executing the facial image after live body action as personnel to be certified.Can respectively from personnel to be certified execute live body action before and Execute before extracting personnel's execution live body action to be certified in the facial image after live body action and execute the skin after live body acts Area image.

Then, the skin area image obtained can be inputted skin elasticity grader, which is One advance trained disaggregated model.For example, if the face skin of acquisition is skin of living body, the skin elasticity grader 1 can be exported, otherwise exports 0.

According to embodiments of the present invention, the skin before capturing personnel's execution live body action to be certified in the facial image acquired Skin area image and the skin area image executed after live body action include：People to be certified is selected from the facial image acquired Member executes the facial image before live body action and executes the facial image after live body action；Using Face datection model to waiting recognizing The face that witness person executes the facial image before live body action and executes in the facial image after live body action is positioned；It utilizes Face key point location model is to executing the facial image before live body action in personnel to be certified and executing the people after live body action The key point of face in face image is positioned；And the face location obtained according to positioning and key point position are to waiting recognizing The face that witness person executes the facial image before live body action and executes in the facial image after live body action carries out region division, The skin area image before live body action and the skin area image after execution live body action are executed to obtain personnel to be certified.

The extraction of skin area image can be realized based on existing Face datection and face key point location algorithm. For example, the facial image that can be executed personnel to be certified before live body action inputs trained Face datection model and people respectively Face key point location model obtains face location (such as coordinate of facial contour point) and key point position (each key point respectively Coordinate).Key point can be arbitrary point on face, such as left eye angle, nose, left labial angle etc..Certainly, key point can also It is facial contour point.Illustratively, human face region can be cut into a series of triangles according to face location and key point position Piece member, and can will be located at chin, the triangular plate member image block of cheekbone, the regions such as two cheeks is obtained as face skin area Skin area image.The extracting mode that personnel to be certified execute the skin area image after live body action is similar with aforesaid way, It repeats no more.For each facial image, region division mode and the selected area as face skin area The position that domain number and each region include can be set as needed, and the present invention limits not to this.

In one example, deep neural network reality may be used in Face datection model and face key point location model It is existing.Deep neural network is a kind of network for capableing of autonomous learning, can accurately and efficiently be detected using deep neural network and Face in locating human face's image and key point.

According to embodiments of the present invention, identity identifying method 200 (300,400) can also include：Sample facial image is obtained, The position of face in sample facial image and the position of the key point of face are to have marked；And utilize sample face figure As carrying out neural metwork training, to obtain Face datection model and face key point location model.

A large amount of (such as 10000 or so) sample facial images can be collected in advance, manually in each sample face The canthus of face, the corners of the mouth, the wing of nose, a series of position of key points such as cheekbone peak and facial contour point are marked out in image Position.Then, can use machine learning algorithm (such as deep learning or the regression algorithm based on local feature) will before It states the sample facial image marked and carries out neural metwork training as input, thus the Face datection model needed for obtaining and people Face key point location model.

According to embodiments of the present invention, identity identifying method 200 (300,400) can also include the instruction of skin elasticity grader Practice step.Showing for the training step S500 of skin elasticity grader according to an embodiment of the invention is described with reference to Fig. 5 Meaning property flow chart.

As shown in figure 5, the training step S500 of skin elasticity grader includes the following steps.

In step S510, obtains true personnel and execute the facial image before live body action and execute the face after live body action Image, and false personnel execute the facial image before live body action and execute the facial image after live body action.

In step S520, executes the facial image before live body action from true personnel and execute the face figure after live body action True personnel are extracted as in execute the facial image before live body action and execute the skin area image after live body action as just Sample image.

In step S530, executes the facial image before live body action from false personnel and execute the face figure after live body action False personnel are extracted as in execute the facial image before live body action and execute the skin area image after live body action as negative Sample image.

In step S540, sorter model is trained using positive sample image and negative sample image, to obtain skin elasticity point Class device.

Illustratively, the training of skin elasticity grader can carry out offline.True personnel can be collected in advance executes rule Before fixed live body action and the facial image after live body action is executed, while live body as defined in false personnel's execution can also be collected Facial image before action and after execution live body action.False personnel can be, such as the photo comprising face, include face Three-dimensional (3D) model of video, scraps of paper mask or face etc..

It can refer to from the mode of extraction skin area image in the facial image of true personnel or false personnel and close above The description of the extracting mode of skin area image in actual identity verification process, details are not described herein.Illustratively, it is obtaining After obtaining positive sample image and negative sample image, the statistical learning methods such as deep learning or SVM can be used to train grader mould Type, to obtain skin elasticity grader.

According to embodiments of the present invention, step S230 (S340 and S350 or S430 and S440) may include：It obtains by binocular Camera is directed to the facial image that the face of the personnel to be certified under structure light irradiation is acquired；It is waited for according to facial image determination Whether the face of certification personnel belongs to live body, to obtain In vivo detection result.

The action done according to face or the master in the way of skin elasticity grader progress In vivo detection described above To be directed to the weaker application scenarios of some safety requirements.For the higher application scenarios of some safety requirements, can select to be based on Special hardware carries out the mode of In vivo detection.For example, the facial image under binocular camera acquisition structure light irradiation may be used, To carry out In vivo detection using collected face information and structure light irradiation information.

It in one example, can be based on the facial image under the structure light irradiation acquired, to determine instruction structure light The detection parameters of degree are scattered in the sub-surface of personnel face to be certified, then, detection parameters and predetermined can be based on Parameter threshold determines whether the face of personnel to be certified is live body.Due to the sub- table of the false face and real human face such as 3D masks Area scattering degree is different (when sub-surface scattering is stronger, image gradient is smaller, to which diffusion is smaller), for example, by general Paper or the materials such as plastics made of the sub-surface scattering degree of mask be far weaker than real human face, and by materials such as general silica gel The sub-surface of manufactured mask scatters degree much stronger than real human face, therefore can be by the judgement to image diffusion come area Divide false face and real human face, so as to effectively defend mask attacker.

In another example, the depth information of the face of personnel to be certified can be obtained according to facial image.In addition, may be used also The hot spot pattern that face to obtain personnel to be certified is formed under structure light irradiation.It can be obtained according to hot spot pattern to be certified The texture information of the face of personnel.Then, can be determined in conjunction with depth information and texture information personnel to be certified face whether Belong to live body.

Different material-structures can form different hot spot patterns under structure light.People can be obtained according to hot spot pattern The texture information of face, i.e. the material property on face surface.If it find that the texture information of the face of personnel to be certified does not meet people Dermatoglyph manages the regularity of distribution, it is determined that the face of personnel to be certified is not belonging to live body, is judged as mask attack etc..Since attacker can To use the mask of apery skin material to implement attack, therefore, even if the texture information of the face of personnel to be certified meets fell line The regularity of distribution is managed, also not necessarily can determine that the face of personnel to be certified belongs to live body, therefore can judge in conjunction with depth information Wait for whether the face of personnel belongs to live body.Personnel to be certified can be obtained from the facial image acquired under two different visual angles Face depth information.It should be appreciated that true face is typically to have fluctuating, for example, the seat of its eye and nose areas It is different to mark depth, and gap is larger, and the coordinate of the mask fluctuating very little made of apery skin material, eyes and nose areas Depth difference is away from very little.Therefore, it can further judge whether the face of personnel to be certified belongs to live body in conjunction with depth information.

Therefore, in embodiments of the present invention, binocular camera and structure light can be combined, is acquired by binocular camera There are the 3D faces of structured light patterns, then the sub-surface scattering degree according to structure light on 3D faces or the depth of combination face The hot spot pattern that information is formed with structure light on face is spent to carry out In vivo detection.

According to embodiments of the present invention, the In vivo detection process in identity identifying method can also have other realization sides Formula.Another In vivo detection mode is described below.To distinguish really it is face based on reflective character in the In vivo detection mode With the false face on photo or screen.

In vivo detection module in In vivo detection step and identification authentication system in identity identifying method is described below Exemplary realisations.It may be noted that " live body verification " as described herein is identical as " In vivo detection " the two meaning, can be interchanged makes With.

Fig. 6 shows that the exemplary electron for realizing identity identifying method in accordance with another embodiment of the present invention and device is set Standby 600.Electronic equipment 600 includes one or more processors 602, one or more storage device 604, input unit 606, defeated Go out device 608, image collecting device 610 and light source 612, the connection that these components pass through bus system 614 and/or other forms Mechanism (not shown) interconnection.It is processor 602, storage device 604, input unit 606 in electronic equipment 600 shown in fig. 6, defeated Go out device 608, image collecting device 110 and bus system 614 to fill with processor 102 shown in FIG. 1, storage device 104, input It is similar with the structure and working principle of bus system 112 to set 106, output device 108, image collecting device 110, repeats no more.

Light source 612 can be the device that can be shone, and may include the special light sources such as light emitting diode, can also include Show the unconventional light sources such as screen.Situation in the mobile terminal that identity identifying method and device are implemented in such as smart mobile phone Under, input unit 606, output device 608 and light source 612 can be same display screens.

Fig. 7 show In vivo detection step S700 according to an embodiment of the invention (correspond to above-mentioned steps S220 or S340 and S350 or S430 and S440) schematic flow chart.As shown in fig. 7, In vivo detection step S700 includes following step Suddenly.

In step S710, one or more acquired for the face of the personnel to be certified under the irradiation of detection light is obtained A light image.

Illustratively, light source can be utilized to emit detection light to the face of personnel to be certified.Light source can be by processor control System is to shine.Illustratively, light source can share other light-emitting devices (for example, at least partly region of display screen, projecting apparatus In light source) be used as light source.In another example light source can also be special light source (for example, one or more arranged according to certain way A Light-Emitting Diode or laser diode, such as the flash lamp etc. for camera), or display screen and other types Light source combination etc..

The pattern of detection light can include but is not limited to the color of detection light, the position of light-emitting zone, detection light intensity, The frequency etc. of the irradiating angle of detection light, the wavelength of detection light, detection light.

Illustratively, during irradiating the face of personnel to be certified, the pattern of detection light can not change, That is single constant light may be used to irradiate the face of personnel to be certified in light source.For example, in a preferred embodiment In, used light source is the display screen of mobile terminal.On the display screen, color and the brightness of each pixel can be controlled Deng so that display screen can emit the light that specific pattern is presented, such as structure light, at this point, screen is aobvious in specific pixel region The particular color shown or brightness can be the patterns for the specific detection light chosen after being optimized according to lot of experimental data, It, can be rapidly and accurately to be verified right by special algorithm corresponding with the pattern of the detection light under the pattern of such detection light As carrying out live body verification.In this case, one or more light images, base can be acquired under the irradiation of constant detection light Live body verification is carried out in light image.

Compare it is appreciated that during irradiating the face of personnel to be certified, the pattern of detection light at least changes once. In such a case, it is possible to which the pattern for coordinating control detection light changes the frequency acquisition of frequency and image, so that in each mould At least one light image can be collected under the detection light of formula.

More preferably, it changes between the pattern of detection light is at the time of each two is continuous.The moment can be with It is the time point of any specific in predetermined period.For example, the pattern of detection light can change once every 1 second.Do not stop to change The pattern of detection light can obtain abundanter reflective character information, be conducive to more accurately and efficiently implement to be based on light The live body of reflection characteristic is verified.

Optionally, during irradiating the face of personnel to be certified, the pattern of detection light is changing at random or advance It sets.In one example, the pattern of detection light be completely random change.For example, in a preferred embodiment, Used light source is the display screen of mobile terminal.On the display screen, the color that each region can be controlled, for each Region randomly selects a certain rgb value within the scope of scheduled rgb value and is shown as the color value in the region every time.Region Division can arbitrarily set, for example, each region may include one or more pixels, the sizes of two different zones can be with It is identical, it can also be different.

In another example, the pattern of detection light can be pre-set.For example, can set detection light is total to prolonged exposure 10 seconds, change one mode per second, the color of the detection light emitted every time, position, intensity etc. were pre-set.In live body In verification process, light source can emit the detection light of 10 kinds of patterns successively according to pre-set mode.Pre-set The pattern of detection light can be obtained based on first experience, to live body verification for relatively effective pattern, this is conducive to carry The accuracy rate and efficiency of high live body verification.

For example, can dynamically change the people for being irradiated to personnel to be certified by dynamically changing the luminescent color of detection light The pattern of the detection light of face.In another example (can also be examined that is, changing by dynamically changing the position of the light-emitting zone of detection light Survey the position of light) carry out the pattern that dynamic changes the detection light for being irradiated to the face of personnel to be certified.For another example can also be by dynamic Change simultaneously to state the luminescent color of detection light and the light-emitting zone of detection light position come dynamic change be irradiated to it is to be certified The pattern of the detection light of the face of personnel.

For example, can dynamically change the position of the light-emitting zone of detection light by changing the position of light source, this can be with Change the position that detection light is irradiated to the face of personnel to be certified.In another example the emergent ray of change light source can also be passed through Angle dynamically changes the position that detection light is irradiated to the face of personnel to be certified.

In a preferred embodiment, used light source is the display screen of mobile terminal, and image collector is set to this The camera (such as front camera) for being located at the same side with display screen of mobile terminal.Relative to using additional dedicated optical The scheme in source, this programme can be realized using existing mobile terminals such as mobile phones, do not limited, can examine the live body by external condition Survey scheme is preferably applied for carrying out remotely open an account equal application scenarios by individual mobile terminal.

Further, in the further preferred scheme of above preferred embodiment, the pattern of used light is the face of light The integrated mode of the position of color and light-emitting zone, such as：Synchronization sends out different colours in the different location of display screen Light, alternatively, color of the synchronization in the light that the different location of display screen sends out the light of same color but different moments send out Difference etc..Using the scheme of the integrated mode of the position of the color and light-emitting zone of light, relative to select change light intensity etc. other The scheme of the pattern of light, not only In vivo detection effect is more preferable, but also can reduce stimulation of the light to human eye, to promote user's body It tests.

In the case of irradiation of the face of personnel to be certified by detection light, can utilize image collecting device (such as The image collecting device 610 of electronic equipment 600) image of the face of personnel to be certified under the irradiation of detection light is acquired, it obtains The light image.Image collecting device can be controlled by processor to acquire image.Image collecting device will be one or more The processor that light image is transmitted to identity authorization system is verified for live body.Illustratively, in the irradiation of the light of same pattern Under the number of collected light image can be one or more, the present invention limits not to this.Those skilled in the art It is understood that live body verification is mainly based upon the verification of face progress, therefore, according to embodiment hereof, in acquisition illumination When image and subsequent motion images and realtime graphic, it is therefore intended that collect the image comprising face, tested for carrying out live body Card.

Illustratively, light image can be by client device (such as mobile terminal, long-distance video cabinet including camera Member's machine (Video Teller Machine, VTM) etc.) electronic equipment 600 is sent to by the processor 602 of electronic equipment 600 It is handled, the image collecting device 610 (such as camera) that can also include by electronic equipment 600 acquires and is transmitted to processing Device 602 is handled.

In step S720, the light reflection that the face based on personnel to be certified is showed in one or more light images is special Property determines whether the face of personnel to be certified belongs to live body, to obtain illumination live body verification result.

The human skin of such as face skin is a kind of irreflexive material, and face is three-dimensional；In contrast, all As the display screen of liquid crystal display (LCD) or Organic Light Emitting Diode (OLED) display is considered self luminous object Body and also generally include partial specular reflection component, and photo etc. be typically plane and also to generally include partial mirror anti- Component is penetrated, and either shows screen or photo, reflection characteristic on the whole is three-dimensional that is uniform and lacking face Characteristic.The reflective character of face is different from display screen or the reflective character of photo, it is possible thereby to by being based on waiting recognizing The reflective character of the face of witness person judges whether the face of personnel to be certified is to belong to live body.

In step S730, at least determine whether personnel to be certified are verified by live body based on illumination live body verification result, with Obtain In vivo detection result.

In one example, illumination live body verification result can be directly based upon and determine final In vivo detection result, that is, such as Fruit illumination live body verification result indicates that the face of personnel to be certified belongs to live body, it is determined that personnel to be certified are verified by live body, It is the In vivo detection result property of can be exemplified 1；If illumination live body verification result indicates that the face of personnel to be certified is not belonging to live Body, it is determined that personnel to be certified are not verified by live body, are the In vivo detection result property of can be exemplified 0.This In vivo detection side The calculation amount of formula is smaller, and efficiency is higher.In another example, illumination live body can be verified in conjunction with other live body verification modes As a result it combines consideration with based on other live body verification results that other live body verification modes obtain, waits recognizing with final determination Whether witness person is verified by live body.The accuracy rate of this In vivo detection mode is higher.

As described above, not due to the reflective character of the reflective character of face and the display objects such as screen or photo Together, therefore based on reflective character the face on the face or photo played back on real human face and screen can effectively be distinguished.Cause This, screen or photograph can be effectively defendd using the identity identifying method and device of biopsy method according to the ... of the embodiment of the present invention Piece attacker, so as to improve safety and the user experience of identity authorization system.

It illustratively, can be with depositing using the identity identifying method of biopsy method according to the ... of the embodiment of the present invention It is realized in the unit or system of reservoir and processor.

Identity identifying method according to the ... of the embodiment of the present invention can be deployed at Image Acquisition end, for example, can be deployed in It is mobile at the Image Acquisition end of the financial systems such as bank management system or to be deployed in smart mobile phone, tablet computer etc. At terminal.Alternatively, identity identifying method according to the ... of the embodiment of the present invention is deployed in server end (or cloud in which can also be distributed End) and client at.For example, the face that can be obtained identification information in client, emit light and acquire personnel to be certified Image, client sends the identification information of acquisition and the image collected to server end (or high in the clouds), by servicing Device end (or high in the clouds) carries out authentication information and judges and In vivo detection, to obtain identity authentication result, and by identity authentication result Return to client.Server has the data operation ability of bigger relative to client, and server end is transferred in authentication It carries out, certification speed can be promoted, promote user experience, further, since server has the arithmetic speed of bigger therefore can adopt With increasingly complex authentication algorithm, the accuracy rate of authentication can be promoted by carrying out authentication in server end.

Screen or photo can be defendd to attack although carrying out live body verification based on reflective character, the attack of attacker There are many mode is possible, certain others attack patterns are possible to break through the live body verification carried out based on reflective character, such as Three-dimensional artificial mask is attacked.The case where being attacked for mask, the live body verification method based on reflective character is possibly can not be fine Ground is defendd.Therefore, in order to further improve live body verification method, the safety of raising live body verification can be based on light reflection On the basis of the live body verification of characteristic, In vivo detection is carried out further combined with other live body verification modes.It is described below one The illustrative realization method of kind.

Fig. 8 show In vivo detection step S800 in accordance with another embodiment of the present invention (correspond to above-mentioned steps S220 or S340 and S350 or S430 and S440) schematic flow chart.Step S810 in In vivo detection step S800 shown in Fig. 8 Corresponding with the step S710 to S730 of In vivo detection step S700 shown in Fig. 7 to S830, those skilled in the art can join The associated description for examining Fig. 7 understands step S810 to S830 shown in Fig. 8, and details are not described herein again.According to the present embodiment, In vivo detection Step S800 can also include step S840 to S870, also, step S830 may include：Based on illumination live body verification result and Action live body verification result determines whether personnel to be certified are verified by live body, to obtain In vivo detection result.

In step S840, output action instruction, wherein action command is used to indicate personnel to be certified and executes corresponding move Make.

Illustratively, it can be instructed randomly or by pre-defined rule output action.Action command may include individually referring to It enables, or the instruction sequence being made of series of instructions.For example, action command can indicate that personnel to be certified nod, shake the head, blink Eye is opened one's mouth, etc..

In step S850, the multiple motion images acquired for the face of personnel to be certified are obtained.

It can be directed to people to be certified while output action instructs or within a period of time after output action instruction The face of member carries out Image Acquisition, obtains multiple motion images.Illustratively, multiple motion images can be continuous video Frame.Motion images can equally be acquired by above-mentioned image collecting device 110, or by other image acquisition devices.

In step S860, the action performed by personnel to be certified is detected based on multiple motion images.

Illustratively, Face datection and key point identification can be carried out in each motion images, and are based on multiple actions Facial contour and/or face key point in image judge the action performed by face, for example, passing through identify facial contour And/or variation tendency of the face key point in multiple the continuous motion images got judges the action performed by face.With Afterwards, it can be determined that whether the action indicated by action and action command performed by face is consistent.

In step S870, determine whether the face of personnel to be certified belongs to living according to motion detection result and action command Body, to obtain action live body verification result.

Illustratively, if indicated by personnel to be certified action and action command performed in multiple motion images Keep strokes, it is determined that the face of personnel to be certified belongs to live body, if personnel to be certified are performed in multiple motion images Action and action command indicated by action is inconsistent or personnel to be certified be not carried out in multiple motion images it is any dynamic Make (action that personnel to be certified are not detected), it is determined that the face of personnel to be certified is not belonging to live body.Certainly, aforesaid way Only it is example, action live body is verified whether by that can have other methods of determination, for example, personnel to be certified are in multiple action diagrams Multiple actions are performed as in, multiple actions include and the action kept strokes indicated by action command, it is determined that wait recognizing The face of witness person belongs to live body.

Illustratively, in step S830, if illumination live body verification result and action live body verification result indicate to wait recognizing The face of witness person belongs to live body, it is determined that personnel to be certified are verified by live body, if illumination live body verification result and action Any of live body verification result indicates that the face of personnel to be certified is not belonging to live body, it is determined that personnel to be certified do not pass through Live body is verified.Certainly, aforesaid way is only example, and live body is verified whether by that can have other methods of determination.

It should be noted that the above-mentioned live body verification step (step S840-S870) based on action and the work based on reflective character The priority execution sequence of body verification step (step S810-S820) can arbitrarily be set, and the present invention limits not to this.

Including the biopsy method of the live body verification step based on action can be independently executed by Image Acquisition end, example It such as, can be by the shiftings such as the Image Acquisition end of the financial systems such as bank management system or smart mobile phone, tablet computer Dynamic terminal independently executes.Alternatively, including the biopsy method of the live body verification step based on action can also be by server (or high in the clouds) and client cooperation is held to execute.For example, action command can be generated in server end or client, adopted by client Collect the motion images of personnel to be certified, client sends collected motion images to server end (or high in the clouds), by servicing Device end (or high in the clouds) carries out the verification of the live body based on action, and verification result is returned to client.

Live body verification mode based on action can defend the attack patterns such as mask attack, and based on reflective character Live body verification mode be combined together, can effectively defend the attack of multiple types, to be further ensured that use the live body examine The identity authorization system of survey method or the safety of similar system, while it being also beneficial to the information security and its equity of protection user, With being extremely widely applied value and market prospects.

According to embodiments of the present invention, step S870 may include：If based in the period no more than the first preset time Interior acquired multiple motion images detect being executed by personnel to be certified, dynamic with keeping strokes indicated by action command Make, it is determined that the face of personnel to be certified belongs to live body, if based on the multiple action diagrams acquired in the first preset time As the action kept strokes indicated by executed by personnel to be certified and action command is not detected, it is determined that people to be certified The face of member is not belonging to live body.

Random output action instruction (such as words or the phonetic order such as " please nod ", " please open one's mouth ") is to be certified to indicate Personnel execute corresponding action (such as nod, open one's mouth), are detected to human face region key point to judge personnel to be certified Whether performed action is consistent with the action command of output.If being detected in the first preset time performed by personnel to be certified Action with export action command it is consistent, it is determined that the face of personnel to be certified belongs to live body；If in the first preset time It detects that the action command of the action and output performed by personnel to be certified is inconsistent, or is not detected in the first preset time To the action of personnel to be certified, then it can determine that the face of personnel to be certified is not belonging to live body.

According to embodiments of the present invention, identity identifying method (200,300 or 400) can also include：Step is being executed every time It is counted during S840 to step S870 once, verification number is acted with acquisition；After step S870, identity identifying method (200,300 or 400) can also include：If action live body verification result indicates that the face of personnel to be certified is not belonging to live body, The first error message is then exported, and judges whether action verification number reaches the first frequency threshold value, if action verification number reaches To the first frequency threshold value, then step S330 is gone to, if action verification number is not up to the first frequency threshold value, return to step The S340 or return to step S310 in the case where step S310 is executed before step S340, wherein the first error message is used In prompt for the live body authentication failed of personnel to be certified.

Illustratively, counter can be set, for being the live body verification step (step S340-S370) based on action It executes number to be counted, often executes a live body verification step based on action, counter can add one.The output of counter As a result it is action verification number.After entire In vivo detection step (In vivo detection step S800) termination, it can will count Device is reset.

If current action live body verification result indicates that the face of personnel to be certified is not belonging to live body, first can be exported Error message.First error message can prompt for personnel to be certified face live body authentication failed and prompt its again into Row live body is verified.If the execution number (action verification number) of the live body verification step at this time based on action has not yet been reached default The first frequency threshold value, then can attempt to re-execute the live body verification step based on action.Optionally, if being based on light reflection The live body verification step (step S810-S820) of characteristic executes before the live body verification step based on action, then can be direct It is back to step S810, that is, re-executes a live body verification step based on reflective character and the live body verification based on action Step, to promote the accuracy of live body verification.

First frequency threshold value can be any appropriate value, can be set as needed, the present invention limits not to this System.

Due in actual live body verification process, may having a various fortuitous events, for example, user do not make in time it is specified The image act, acquired is not clear enough, Face datection result is not accurate enough etc., these situations may cause user to be misidentified as Non-living body.Therefore, user experience and security of system in order to balance can set frequency threshold value, allow user in zone of reasonableness Interior multiple trial live body verification.If user is not correctly identified as live body yet when reaching frequency threshold value, it can be determined Really it is not belonging to live body.

According to embodiments of the present invention, before step S710 (or S810), identity identifying method (200,300 or 400) is also May include：Step S708：Judge whether the Image Acquisition condition of personnel to be certified meets preset requirement, if Image Acquisition item Part meets preset requirement, then goes to step S710 (or S810), wherein Image Acquisition condition includes that personnel to be certified adopt in image The relative angle of location and/or personnel to be certified and image collecting device in the image acquisition region of acquisition means.

Before executing live body verification step or other live body verification steps based on reflective character, it can treat first The Image Acquisition condition of certification personnel is detected, and judges whether it meets preset requirement.It can be personnel's only to be certified Image Acquisition condition just executed in the case of meeting preset requirement the subsequent live body verification step based on reflective character or its His live body verification step, can ensure the quality of image (including light image, motion images etc.) verified for live body in this way, Be conducive to the face in correct detection image, to be conducive to improve the accuracy rate of live body verification.

According to embodiments of the present invention, before step S708 or with step S708 simultaneously, identity identifying method (200, 300 or 400) can also include：Step S706：Export the first prompt message, wherein the first prompt message is to be certified for prompting Personnel are by face's face image collecting device and close to image collecting device.

Any suitable way output may be used in first prompt message.Illustratively, step S706 may include：Pass through The first prompt message of one or more outputs in speech form, image format and written form.For example, can be in mobile terminal Display screen on output " asking face screen " (face screen is equivalent to face image collecting device) as word, Huo Zheke Signal language as " asking face screen " is sent out with the loud speaker by mobile terminal.

Illustratively, identity identifying method can be by the application (APP) on the electronic equipments such as mobile terminal To realize.When user opens the application and when subsequently entering the In vivo detection stage, can start to export the first prompt message, with It prompts user to keep suitable relative position relation with mobile terminal, ideal face is acquired in order to the camera of mobile terminal Image is verified for live body.In one example, the first prompt message can meet in the Image Acquisition condition of personnel to be certified It constantly or is at intervals exported before preset requirement.

It can (be mainly image therein in order to instruct user to adjust identification authentication system in time to export the first prompt message Harvester) and the relative position relation of itself, meanwhile, the interaction of this user and system can also promote user experience.

According to embodiments of the present invention, step S708 may include：Obtain the real-time of the face acquisition for being directed to personnel to be certified Image；The human face region in predeterminable area and realtime graphic of the output for calibrating Image Acquisition condition is for showing in real time； And judge whether Image Acquisition condition meets preset requirement according to the human face region detected in realtime graphic, if face Region is located in predeterminable area and human face region proportion in realtime graphic is more than the first preset ratio, it is determined that image Acquisition condition meets preset requirement, if human face region is not in predeterminable area or human face region institute in realtime graphic Accounting example is not more than the first preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

In one example, it can judge personnel's to be certified according to the image that the face for personnel to be certified acquires Whether Image Acquisition condition meets preset requirement.The pedestrian for example, mobile terminal can be gone forward side by side by camera acquisition realtime graphic Face detects.Face datection can obtain human face region, and human face region is the image block for including face.It can be existed according to human face region The location of in realtime graphic and human face region proportion in realtime graphic judges that the image of personnel to be certified is adopted Whether collection condition meets preset requirement.For example, predeterminable area can be delimited in realtime graphic.It can be limited by predeterminable area Position of the face of personnel to be certified in the image acquisition region of image collecting device.The size of human face region, which can reflect, to be waited for Certification personnel are at a distance from image collecting device and relative angle.Predeterminable area and the first preset ratio can be set as needed Fixed, the present invention limits not to this.

For example, if the human face region of personnel to be certified is located in predeterminable area, but human face region is in realtime graphic Proportion is less than the first preset ratio (such as 2/3rds), it is likely that is personnel to be certified relative to image collecting device Be too greatly inclined and/or range image harvester farther out, at this time it is considered that Image Acquisition condition be unsatisfactory for preset requirement.

Illustratively, identity identifying method (200,300 or 400) can also include：If human face region is in realtime graphic Middle proportion is not more than the first preset ratio, then the first acquisition of output in real time prompt message, to prompt personnel to be certified and figure As harvester is close.

Optionally, the first acquisition prompt message can by one kind in speech form, image format and written form or A variety of outputs.If for example, finding that human face region proportion in realtime graphic is not more than the first preset ratio, can show Such as " please be close to camera " (or " please be close to mobile phone ") this kind of prompt message is shown on screen.

According to embodiments of the present invention, step S708 may include：Obtain the real-time of the face acquisition for being directed to personnel to be certified Image；The human face region in predeterminable area and realtime graphic of the output for calibrating Image Acquisition condition is for showing in real time； And judge whether Image Acquisition condition meets preset requirement according to the human face region detected in realtime graphic, if face Region is located in predeterminable area and human face region proportion in predeterminable area is more than the second preset ratio, it is determined that image Acquisition condition meets preset requirement, if human face region is not in predeterminable area or human face region institute in predeterminable area Accounting example is not more than the second preset ratio, it is determined that Image Acquisition condition is unsatisfactory for preset requirement.

In one example, it can judge personnel's to be certified according to the image that the face for personnel to be certified acquires Whether Image Acquisition condition meets preset requirement.The pedestrian for example, mobile terminal can be gone forward side by side by camera acquisition realtime graphic Face detects.Face datection can obtain human face region, and human face region is the image block for including face.It can be existed according to human face region The location of in realtime graphic and human face region proportion in predeterminable area judges that the image of personnel to be certified is adopted Whether collection condition meets preset requirement.For example, predeterminable area can be shown on the display screen.It can be limited by predeterminable area Relative position between personnel to be certified and screen.The size of human face region can reflect personnel to be certified and image collecting device Distance and relative angle, such as when detecting face apart from screen from the distant to the near, the face area of real-time display on the screen Domain is changed from small to big, and so that the human face region size shown on screen is met preset condition when face sufficiently closes to screen, certainly, The human face region of real-time display can also only be sized to meet under conditions of face sufficiently closes to screen default on screen Condition is not limited thereto.Predeterminable area and the second preset ratio can be set as needed, and the present invention limits not to this System.

For example, if the human face region of personnel to be certified is located in predeterminable area, but human face region is in predeterminable area Proportion is less than the second preset ratio (such as 2/3rds), it is likely that is personnel to be certified relative to image collecting device Be too greatly inclined and/or range image harvester farther out, at this time it is considered that Image Acquisition condition be unsatisfactory for preset requirement.

Illustratively, identity identifying method (200,300 or 400) can also include：If human face region is in predeterminable area Middle proportion is not more than the second preset ratio, then the second acquisition of output in real time prompt message, to prompt personnel to be certified and figure As harvester is close.

Optionally, the second acquisition prompt message can by one kind in speech form, image format and written form or A variety of outputs.If for example, finding that human face region proportion in predeterminable area is not more than the second preset ratio, can show Such as " please be close to camera " (or " please be close to mobile phone ") this kind of prompt message is shown on screen.

According to embodiments of the present invention, identity identifying method (200,300 or 400) can also include：Real-time judge face area Relative position relation between domain and predeterminable area；And it is real based on the relative position relation between human face region and predeterminable area When output third acquire prompt message, with prompt change the relative position relation between personnel to be certified and image collecting device with So that human face region and predeterminable area are close.

For example, when realizing identity identifying method and device according to the ... of the embodiment of the present invention on mobile terminals, Ke Yi Real-time display human face region (image block for including face extracted from realtime graphic) and use on the display screen of mobile terminal In the icon (i.e. the predeterminable area of real-time display on the screen) for indicating predeterminable area.Real-time display human face region and for indicating The icon of predeterminable area can facilitate user to know which kind of situation is its current Image Acquisition condition be in, the difference with preset requirement It is much away from having, to facilitate user to adjust itself or image collecting device (or identification authentication system comprising image collecting device) Posture, to enter subsequent live body Qualify Phase as early as possible.Therefore, real-time display human face region and the figure for indicating predeterminable area Mark can improve user experience, and can improve the efficiency of live body verification.

Further, it is also possible to third acquisition prompt message be exported, to prompt user to change personnel to be certified and image collector Relative position relation between setting is so that human face region is close with predeterminable area.Optionally, third acquisition prompt message can be with Pass through one or more outputs in speech form, image format and written form.If for example, finding that human face region is not at In predeterminable area, then can show on the display screen such as " please close to circle center " (predeterminable area on the display screen with Circular icon is shown) this kind of prompt message.It is directed toward predeterminable area further, it is also possible to be shown on the display screen from human face region Arrow facilitates user to understand and how to move itself or image collecting device so that human face region enters predeterminable area as early as possible.On One can be shown or select simultaneously and show by stating " please be close to circle center " this kind of text prompt information and this kind of picture cues information of arrow Show.

According to embodiments of the present invention, step S708 may include：Obtain the posture information of image collecting device；And according to Posture information judges whether image collecting device is in vertical placement status, if it is, it is pre- to determine that Image Acquisition condition meets If it is required that otherwise determining that Image Acquisition condition is unsatisfactory for preset requirement.

For example, when identity identifying method according to the ... of the embodiment of the present invention is applied to mobile terminal scene, image collector The posture information for setting (i.e. the camera of mobile terminal) can be using the gyro sensor and/or acceleration built in mobile terminal The devices such as sensor measure.When mobile terminal is in vertical placement status, image collecting device is also at vertical state, this In the case of kind, more satisfactory facial image can be collected.Therefore, it can be waited for based on the posture of image collecting device to weigh Whether the Image Acquisition condition of certification personnel meets the requirements.

According to embodiments of the present invention, identity identifying method (200,300 or 400) can also include：Step is being executed every time It is counted during S710 to step S720 (or step S810 to step S820) once, number is verified to obtain illumination；In step After rapid S720 (or S820), identity identifying method (200,300 or 400) can also include：If illumination live body verification result It indicates that the face of personnel to be certified is not belonging to live body, then exports the second error message, and judge whether illumination verification number reaches Second frequency threshold value goes to step S230 (or S330), if illumination if illumination verification number reaches the second frequency threshold value Verification number is not up to the second frequency threshold value, then return to step S208 or return to step S210 (or S310), wherein the second mistake Information is used to prompt the live body authentication failed for personnel to be certified.

Similarly with the live body verification step based on action, for live body verification step (Fig. 7 institutes based on reflective character The step S710-S720 or shown in Fig. 8 step S810-S820 shown) for, if it is determined that the face of personnel to be certified is not belonging to Live body can equally be attempted to re-execute the live body verification step based on reflective character, principle and advantage and be based on action Live body verification step it is similar, details are not described herein again.

It illustratively, can also be since step S708 in the case where identity identifying method includes above-mentioned steps S708 It re-executes.

According to embodiments of the present invention, before step S710 (or S810) or in execution step S710 (or S810) and step During S720 (or S820), identity identifying method (200,300 or 400) can also include：The second prompt message is exported, In, the second prompt message is for prompting personnel to be certified to be remained stationary as in the second preset time.

Illustratively, the second preset time can be the live body verification step (step shown in Fig. 7 based on reflective character S710-S720 or shown in Fig. 8 step S810-S820) the execution time.It is held in the live body verification step based on reflective character When row, i.e., when irradiating the face of personnel to be certified using detection light, personnel to be certified can be prompted to be kept not within this period It is dynamic, in order to avoid influence image collection effect and live body verification result.Illustratively, if personnel to be certified are in the second preset time Movement causes the Image Acquisition condition of personnel to be certified no longer to meet preset requirement, then can be with return to step S706 or step S708 re-executes one or more steps in following steps：Judge Image Acquisition condition, exports the first prompt message, is defeated Go out various acquisition prompt messages.

Illustratively, the second prompt message can be count down information corresponding with the second preset time.Optionally, The realization of one or more forms in word, dynamic image and voice may be used in clocking information.Count down information can facilitate User understands In vivo detection progress, and can improve the interactive experience of user.

The 9 a kind of implementation process for describing In vivo detection step according to the ... of the embodiment of the present invention below in conjunction with the accompanying drawings.Shown in Fig. 9 Application scenarios be mobile terminal.

As shown in figure 9, first, word as " asking face screen " is shown on the display screen of mobile terminal, prompt Face's face screen is shown icon (being indicated with circle) and the base for indicating predeterminable area by user on the display screen In the human face region that realtime graphic detects.When user changes position and/or the posture of itself face, and/or change mobile end It, can word and the figure for indicating predeterminable area as continuously display " asking face screen " when the position at end and/or posture Mark, both information can remain unchanged.However, the size and location of human face region may all change, therefore, can show in real time Show continually changing human face region, user is facilitated to check.It then, can when the Image Acquisition condition of user meets preset requirement To enter next stage, i.e. the live body verification step based on reflective character.

In the implementation procedure of the live body verification step based on reflective character, can show on the display screen " please protect Hold motionless " as word (as shown in the 2nd and 3 width images of Fig. 9), prompt user to remain stationary as, while can also show Count down information is shown on screen.It uses and is indicated in for indicating preset areas in count down information the 3rd width image shown in Fig. 9 Colored progress bar on the icon (i.e. circle) in domain indicates.

After the live body verification step based on reflective character is completed, it can start to execute the live body verification based on action Step.As shown in the 4th width image of Fig. 9, show that word as " please nod ", instruction user execute corresponding on the display screen Action.

Finally, final In vivo detection is exported on the display screen as a result, word as such as " live body is verified ".

According to a further aspect of the invention, a kind of identification authentication system is provided.Figure 10 is shown according to one implementation of the present invention The schematic block diagram of the identification authentication system 1000 of example.

As shown in Figure 10, identification authentication system 1000 according to the ... of the embodiment of the present invention includes data obtaining module 1010, Authentication information judgment module 1020, In vivo detection module 1030 and identity determining module 1040.The modules can be held respectively Each step/function of the row above in conjunction with Fig. 2-9 identity identifying methods described.Below only to the identification authentication system 1000 The major function of each component be described, and omit the detail content having been described above.

Data obtaining module 1010 is used to obtain the identification information of personnel to be certified.Data obtaining module 1010 can be with The program instruction that is stored in 102 Running storage device 104 of processor in electronic equipment as shown in Figure 1 is realized.

Authentication information judgment module 1020 is for judging whether identification information is authentication information, to obtain information Authentication result.The operation storage dress of processor 102 in the electronic equipment that authentication information judgment module 1020 can be as shown in Figure 1 The program instruction that is stored in 104 is set to realize.

In vivo detection module 1030 is used to carry out In vivo detection to personnel to be certified, to obtain In vivo detection result.Live body Detection module 1030 can be as shown in Figure 1 electronic equipment in 102 Running storage device 104 of processor in the program that stores refer to It enables to realize.

Identity determining module 1040 is used to determine personnel to be certified according at least to certificate authentication result and In vivo detection result Identity it is whether legal.Identity determining module 1040 can be as shown in Figure 1 electronic equipment in processor 102 operation storage dress The program instruction that is stored in 104 is set to realize.

Those of ordinary skill in the art may realize that lists described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually It is implemented in hardware or software, depends on the specific application and design constraint of technical solution.Professional technician Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed The scope of the present invention.

Figure 11 shows the schematic block diagram of identity authorization system 1100 according to an embodiment of the invention.Authentication System 1100 includes image collecting device 1110, storage device 1120 and processor 1130.

Image collecting device 1110 is for acquiring image, such as facial image, certificate image of personnel to be certified etc..Image Harvester 1110 is optional, and identity authorization system 1100 can not include image collecting device 1110.In this case, Image of other image acquisition devices for authentication can be utilized, and the image of acquisition is sent to authentication system System 1100.

The storage device 1120 stores for realizing the corresponding step in identity identifying method according to the ... of the embodiment of the present invention Rapid computer program instructions.

The processor 1130 is for running the computer program instructions stored in the storage device 1120, to execute root According to the corresponding steps of the identity identifying method of the embodiment of the present invention, and for realizing authentication according to the ... of the embodiment of the present invention Data obtaining module 1010 in device, authentication information judgment module 1020, In vivo detection module 1030 and identity have determined mould Block 1040.

In one embodiment, for executing following step when the computer program instructions are run by the processor 1130 Suddenly：Obtain the identification information of personnel to be certified；Judge whether identification information is authentication information, is recognized to obtain information Demonstrate,prove result；In vivo detection is carried out to personnel to be certified, to obtain In vivo detection result；And according at least to authentification of message result and In vivo detection result determines whether the identity of personnel to be certified is legal.

In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage Instruction, the identity identifying method when described program instruction is run by computer or processor for executing the embodiment of the present invention Corresponding steps, and for realizing the corresponding module in identification authentication system according to the ... of the embodiment of the present invention.The storage medium Such as may include the storage card of smart phone, the storage unit of tablet computer, the hard disk of personal computer, read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage, Or the arbitrary combination of above-mentioned storage medium.

In one embodiment, the computer program instructions can to calculate when by computer or processor operation Machine or processor realize each function module of identification authentication system according to the ... of the embodiment of the present invention, and/or can execute Identity identifying method according to the ... of the embodiment of the present invention.

In one embodiment, the computer program instructions are used to execute following steps at runtime：It obtains to be certified The identification information of personnel；Judge whether identification information is authentication information, to obtain authentification of message result；It treats and recognizes Witness person carries out In vivo detection, to obtain In vivo detection result；And according at least to authentification of message result and In vivo detection result Determine whether the identity of personnel to be certified is legal.

Each module in identity authorization system according to the ... of the embodiment of the present invention can pass through reality according to the ... of the embodiment of the present invention The processor computer program instructions that store in memory of operation of the electronic equipment of authentication are applied to realize, or can be with The computer instruction stored in the computer readable storage medium of computer program product according to the ... of the embodiment of the present invention is counted Calculation machine is realized when running.

According to a further aspect of the invention, a kind of identification authentication system, including information collecting device, processor and storage are provided Device, wherein information collecting device is used to receive the identification information of personnel to be certified；It is stored with computer in the memory Program instruction, for executing following steps when the computer program instructions are run by the processor：It obtains described to be certified The identification information of personnel, wherein the identification information is the initial information or is obtained based on the initial information； Judge the identification information whether be authentication information to obtain authentification of message result；It lives to the personnel to be certified Physical examination is surveyed to obtain In vivo detection result；And determine institute according at least to described information authentication result and the In vivo detection result Whether the identity for stating personnel to be certified is legal.

Illustratively, the personal information harvester includes image collecting device and/or input unit.

Illustratively, the identification authentication system can also include：Image collecting device, for acquiring personnel's to be certified Facial image；The processing unit is further used for carrying out In vivo detection using facial image, to obtain In vivo detection result.

Illustratively, the identification authentication system can also include：Light source is examined for emitting to the face of personnel to be certified Survey light；Described image harvester is further used for acquiring one or more of the face of personnel to be certified under the irradiation of detection light A light image is as the facial image；The processing unit be further used for the face based on personnel to be certified at one or The reflective character showed in multiple light images determines whether the face of personnel to be certified belongs to live body, to obtain illumination work Experience card based on illumination live body verification result as a result, simultaneously at least determine whether personnel to be certified are verified by live body, to obtain work Body testing result.

According to a further aspect of the invention, a kind of identification authentication system is provided, including：Image collecting device is waited for for acquiring The identification information of certification personnel；Processing unit, for judge identification information whether be authentication information to obtain letter Authentication result is ceased, In vivo detection is carried out to obtain In vivo detection as a result, and according at least to authentification of message result to personnel to be certified Determine whether the identity of personnel to be certified is legal with In vivo detection result.

Illustratively, described image harvester is additionally operable to acquire the facial image of personnel to be certified；The processing unit It is further used for carrying out In vivo detection using facial image, to obtain In vivo detection result.

Illustratively, identity identifying method (200,300 or 400) (such as can be moved in individual identification authentication system Terminal etc.) on realize.Above-mentioned input unit may include one or more of keyboard, mouse, microphone and touch screen etc.. Identification information is the transformation of passport NO., name, certificate face, collection in worksite face, the transformed value of passport NO., name Value, the transformed value of certificate face and collection in worksite face transformed value in it is one or more in the case of, input can be utilized Device receives information input by user, to obtain required identification information.In identification information is certificate image In the case of certificate information, the certificate image of image acquisition device personnel to be certified can be utilized, to obtain required People's identification information.Certainly, passport NO., name, certificate face these personal information can also be extracted from certificate image, and The transformed value of these personal information can be obtained by pre-defined algorithm, that is to say, that can also obtain using image collecting device This kind of of the transformed value of passport NO., name, certificate face, the transformed value of passport NO., the transformed value of name and certificate face People's identification information.Certainly, identification authentication system may include both input unit and image collecting device, be obtained in conjunction with two kinds of information Mode is taken to obtain identification information.

According to a further aspect of the invention, a kind of identification authentication system is provided, including：Input unit, it is to be certified for receiving The identification information of personnel；Transmitting device for identification information to be sent to server, and is received from server and is serviced The whether legal authentication information of the identity about personnel to be certified that device obtains in the following manner：Judging identification information is It is no be authentication information to obtain authentification of message as a result, In vivo detection is carried out to obtain In vivo detection to personnel to be certified as a result, And determine whether the identity of personnel to be certified is legal according at least to authentification of message result and In vivo detection result.

Illustratively, the identification authentication system further includes：Image collecting device, the face for acquiring personnel to be certified Image；The transmitting device is additionally operable to the facial image being sent to server, wherein the server by utilizing facial image In vivo detection is carried out to obtain In vivo detection result.

Illustratively, the identification authentication system can also include：Light source is examined for emitting to the face of personnel to be certified Survey light；Described image harvester is further used for acquiring multiple illumination of the face of personnel to be certified under the irradiation of detection light Image is as the facial image；The transmitting device is further used for one or more light images being sent to server； Wherein, server carries out In vivo detection in the following manner：Face based on personnel to be certified is in one or more light images Middle showed reflective character determines whether the face of personnel to be certified belongs to live body, to obtain illumination live body verification result, And at least determine whether personnel to be certified are verified by live body based on illumination live body verification result, to obtain In vivo detection result.

According to a further aspect of the invention, a kind of identification authentication system is provided, including：Image collecting device is waited for for acquiring The identification information of certification personnel；Transmitting device for identification information to be sent to server, and is received from server The whether legal authentication information of the identity about personnel to be certified that server obtains in the following manner：Judge that person identifier is believed Breath whether be authentication information to obtain authentification of message as a result, to personnel to be certified carry out In vivo detection to obtain In vivo detection knot Fruit, and determine whether the identity of personnel to be certified is legal according at least to authentification of message result and In vivo detection result.

Illustratively, the identification authentication system can also include：Light source is examined for emitting to the face of personnel to be certified Survey light；Described image harvester is further used for acquiring one or more of the face of personnel to be certified under the irradiation of detection light A light image is as the facial image；The transmitting device is further used for one or more light images being sent to clothes Business device；Wherein, server carries out In vivo detection in the following manner：Face based on personnel to be certified is in one or more illumination The reflective character showed in image determines whether the face of personnel to be certified belongs to live body, to obtain illumination live body verification knot Fruit, and at least determine whether personnel to be certified are verified by live body based on illumination live body verification result, to obtain In vivo detection knot Fruit.

Illustratively, identity identifying method (200,300 or 400) can be realized on discrete device, such as in client It is realized on end and server.In this case, client may include input unit and/or image collecting device and transmission Device.Optionally, client can be (including light image, dynamic by the identification information of acquisition and collected facial image Make image, realtime graphic etc.) it uploads onto the server, authentication is carried out by server.Client receives server transmission After authentication information, execute certification by or not by operation, such as export about authentication by or unsanctioned information, permit Perhaps or refusal user executes subsequent business operation, etc..

Illustratively, the transmitting device of client can be by network or other technologies by identification information and face figure As being sent to server, and by network or other technologies authentication information is received from server.For example, the network can be because Special net, WLAN, mobile communications network etc., other technologies are such as may include Bluetooth communication, infrared communication.Example Such as, the server can be universal server or tailored version server, can be virtual server or Cloud Server etc..Visitor The transmitting device at family end (or server) may include modem, network adapter, bluetooth transmitting and receiving unit or infrared The operations such as unit etc. is transmitted and received, such as can also be encoded, be decoded to the information for sending or receiving.

It is completed since the major part of authentication is operated in server, the meter of the processing unit of client can be saved Resource is calculated, it is possible thereby to reduce the requirement to client performance and the manufacturing cost of identification authentication system, and use can be promoted The experience at family.

According to a further aspect of the invention, a kind of identification authentication system, including transmitting device and processing unit are provided, wherein The transmitting device is used to receive the identification information of personnel to be certified from client, and by the identity about personnel to be certified Whether legal authentication information is sent to client；The processing unit is for judging whether identification information is the letter of certification Breath is to obtain authentification of message as a result, carrying out In vivo detection to obtain In vivo detection as a result, according at least to information to personnel to be certified Authentication result and In vivo detection result determine whether the identity of personnel to be certified is legal to obtain the authentication information.

Illustratively, the transmitting device is additionally operable to receive the facial image of personnel to be certified；The processing unit is into one Step using facial image for carrying out In vivo detection, to obtain In vivo detection result.

Illustratively, the transmitting device is further used for receiving one or more illumination of personnel to be certified from client Image, wherein one or more light images are acquired and obtained for the face of personnel to be certified under the irradiation of detection light ；The processing unit is further used for what the face based on personnel to be certified was showed in one or more light images Reflective character determines whether the face of personnel to be certified belongs to live body, to obtain illumination live body verification result, and is at least based on Illumination live body verification result determines whether personnel to be certified are verified by live body, to obtain In vivo detection result.

As described above, identity identifying method (200,300 or 400) can be realized on discrete device, such as in visitor It is realized on family end and server.The present embodiment describes a kind of reality that at least part of identity identifying method is realized on the server Existing scheme.

Identity identifying method and device according to the ... of the embodiment of the present invention, judge in conjunction with authentication information and In vivo detection comes really Whether the identity of fixed personnel to be certified is legal, therefore, with the conventional mode for being based purely on password or certificate progress authentication It compares, the authentication result of identity identifying method and device according to the ... of the embodiment of the present invention is more acurrate, can improve subscription authentication Safety, so as to the equity of effective guarantee user.The above method and device can be advantageously applied to various be related to identity The fields such as the field of certification, such as e-commerce, mobile payment or banking.

Although describing example embodiment by reference to attached drawing here, it should be understood that the above example embodiment is merely exemplary , and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims Within required the scope of the present invention.

In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only Only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can be tied Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.

In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail And technology, so as not to obscure the understanding of this description.

Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of each inventive aspect, To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure, Or in descriptions thereof.However, the method for the present invention should be construed to reflect following intention：It is i.e. claimed The present invention claims the more features of feature than being expressly recited in each claim.More precisely, such as corresponding power As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used It levies to solve corresponding technical problem.Therefore, it then follows thus claims of specific implementation mode are expressly incorporated in this specific Embodiment, wherein each claim itself is as a separate embodiment of the present invention.

It will be understood to those skilled in the art that other than mutually exclusive between feature, any combinations pair may be used All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method Or all processes or unit of equipment are combined.Unless expressly stated otherwise, this specification (including want by adjoint right Ask, make a summary and attached drawing) disclosed in each feature can be replaced by providing the alternative features of identical, equivalent or similar purpose.

In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of arbitrary It mode can use in any combination.

The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processors Software module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practice Microprocessor or digital signal processor (DSP) realize some moulds in identification authentication system according to the ... of the embodiment of the present invention The some or all functions of block.The present invention is also implemented as the part or complete for executing method as described herein The program of device (for example, computer program and computer program product) in portion.It is such to realize that the program of the present invention store It on a computer-readable medium, or can be with the form of one or more signal.Such signal can be from internet It downloads and obtains on website, either provide on carrier signal or provide in any other forms.

It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame Claim.

The above description is merely a specific embodiment or to the explanation of specific implementation mode, protection of the invention Range is not limited thereto, and any one skilled in the art in the technical scope disclosed by the present invention, can be easily Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim Subject to protection domain.

Claims

1. a kind of identity identifying method, including：

Obtain the identification information of personnel to be certified；

Judge whether the identification information is authentication information, to obtain authentification of message result；

In vivo detection is carried out to the personnel to be certified, to obtain In vivo detection result；And

Determine whether the identity of the personnel to be certified closes according at least to described information authentication result and the In vivo detection result Method.

2. identity identifying method as described in claim 1, wherein the identification information is passport NO., name, certificate Face, collection in worksite face, the transformed value of passport NO., the transformed value of name, the transformed value of certificate face and collection in worksite people It is one or more in the transformed value of face.

3. identity identifying method as described in claim 1, wherein the identification information for obtaining personnel to be certified it Before, the identity identifying method further includes：

Output is used to indicate the instruction information that the personnel to be certified provide the personal information of predefined type；

Wherein, the identification information is the personal information provided by the personnel to be certified or is obtained based on the personal information .

4. identity identifying method as described in claim 1, wherein the identification information be passport NO. transformed value, It is one or more in the transformed value of the transformed value of name, the transformed value of certificate face and collection in worksite face,

The identification information for obtaining personnel to be certified includes：

Obtain the initial information of the personnel to be certified, wherein the initial information be passport NO., name, certificate face and It is one or more in collection in worksite face；And

The initial information is converted based on pre-defined algorithm, to obtain the transformed value of the initial information as the individual Identification information.

5. identity identifying method as described in claim 1, wherein

Obtain the certificate image of the personnel to be certified, wherein described information authentication result is certificate authentication result；

It is described that In vivo detection is carried out to the personnel to be certified, include to obtain In vivo detection result：

Obtain the facial image of the personnel to be certified；And

In vivo detection is carried out using the facial image, to obtain the In vivo detection result.

6. identity identifying method as claimed in claim 5, wherein described according at least to described information authentication result and described Before In vivo detection result determines whether the identity of the personnel to be certified is legal, the identity identifying method further includes：

Further decision is executed using the certificate image and/or the facial image to operate, to obtain further decision result；

It is described to determine that the identity of the personnel to be certified is according at least to described information authentication result and the In vivo detection result It is no legal to include：

The personnel to be certified are determined according to the certificate authentication result, the In vivo detection result and the further decision result Identity it is whether legal.

7. identity identifying method as claimed in claim 6, wherein the further decision operation includes that the certificate true and false judges operation And/or face consistency judges operation, and the further decision result includes that certificate true and false judging result and/or face are consistent Property judging result,

The certificate true and false judges that operation includes：Judge whether the certificate in the certificate image is real docu-ment, to obtain State certificate true and false judging result；

The face consistency judges that operation includes：The certificate face of the personnel to be certified is obtained according to the certificate image； And compare the certificate face of the personnel to be certified with the face in the facial image, to obtain the face one Cause property judging result.

8. identity identifying method as claimed in claim 7, wherein described to obtain the people to be certified according to the certificate image Member certificate face include：

Face is detected from the certificate image, to obtain the certificate face of the personnel to be certified.

9. identity identifying method as claimed in claim 7, wherein described to obtain the people to be certified according to the certificate image Member certificate face include：

Text region is carried out to the certificate image, to obtain the text information in the certificate image；

Based on the text information in the certificate image matched certificate information is searched for from certification certificate information database；With And

Determine that the certificate face in matched certificate information search, described is the certificate face of the personnel to be certified.

10. identity identifying method as claimed in claim 7, wherein the certificate judged in the certificate image whether be Real docu-ment includes to obtain the certificate true and false judging result：

Extract the characteristics of image of the certificate image；And

Described image feature is inputted into trained certificate grader, to obtain the certificate true and false judging result；

Wherein, the certificate true and false judging result is the confidence level that the certificate in the certificate image is real docu-ment.

11. identity identifying method as claimed in claim 7, wherein the certificate judged in the certificate image whether be Real docu-ment includes to obtain the certificate true and false judging result：

Identification includes the image block of certificate identifier information from the certificate image；And

Image comprising the certificate identifier information certificate identifier information in the block is identified, to obtain the certificate true and false Judging result；

12. identity identifying method as claimed in claim 6, wherein described according to the certificate authentication result, the live body During testing result and the further decision result determine whether the identity of the personnel to be certified is legal, the certificate is recognized The each result demonstrate,proved in result, the In vivo detection result and the further decision result has respective weight coefficient.

13. identity identifying method as claimed in claim 5, wherein the certificate image packet for obtaining the personnel to be certified It includes：

Obtain the pre- shooting image that the certificate for the personnel to be certified under the conditions of current shooting acquires in real time；

The image attributes of the pre- shooting image is assessed in real time；

When the assessed value of the image attributes of the pre- shooting image is less than preset assessed value threshold value, according to the pre- shooting figure The image attributes of picture generates pre- shooting prompt message, for prompting the personnel to be certified to adjust the shooting condition of its certificate；With And

When the assessed value of the image attributes of the pre- shooting image is equal to or more than the preset assessed value threshold value, institute is preserved Pre- shooting image is stated with as the certificate image.

14. identity identifying method as claimed in claim 5, wherein described to judge whether the identification information is to have recognized Information is demonstrate,proved, includes to obtain authentification of message result：

Text region is carried out to the certificate image, to obtain the text information in the certificate image；And

It is scanned in certification certificate information database based on the text information in the certificate image, to obtain the card Part authentication result；

Wherein, the certificate authentication result is the confidence level that the certificate information in the certificate image is certification certificate information.

15. the identity identifying method as described in claim 9 or 14, wherein it is described that Text region is carried out to the certificate image, Include to obtain the text information in the certificate image：

Word in the certificate image is positioned, to obtain the image block for including word；And

Image comprising the word word in the block is identified, to obtain the text information in the certificate image.

16. identity identifying method as claimed in claim 15, wherein described to the text in the block of the image comprising word Before word is identified, the identity identifying method further includes：

The image block comprising word is corrected to horizontality.

17. identity identifying method as claimed in claim 15, wherein described to the text in the block of the image comprising word Word is identified, described to carry out Text region to the certificate image after obtaining the text information in the certificate image, Further include to obtain the text information in the certificate image：

The text information in the certificate image is exported, so that user checks；

Receive the word update information input by user；

By the text corresponding with the text information in the certificate image of the text word to be repaired indicated by the word update information Word is compared；And

If text word to be repaired indicated by the word update information with it is corresponding in the text information in the certificate image Difference between word is less than preset discrepancy threshold, then the text in the certificate image is updated using the word update information Word information.

18. identity identifying method as described in claim 1, wherein it is described that In vivo detection is carried out to the personnel to be certified, with Obtaining In vivo detection result includes：

Live body action command is generated, it is dynamic that the live body action command is used to indicate the corresponding live body of personnel's execution to be certified Make；

Obtain the facial image of the personnel to be certified acquired in real time；

Detect the face in the facial image；And

Judge whether the face in the facial image executes the live body action indicated by the live body action command, to obtain State In vivo detection result.

19. identity identifying method as described in claim 1, wherein it is described that In vivo detection is carried out to the personnel to be certified, with Obtaining In vivo detection result includes：

From captured in the facial image acquired the personnel to be certified execute the skin area image before live body action and Execute the skin area image after live body action；And

The personnel to be certified are executed into the skin area image before live body action and execute the skin area figure after live body action As input skin elasticity grader, to obtain the In vivo detection result.

20. identity identifying method as claimed in claim 19, wherein the identity identifying method includes：

It obtains true personnel to execute the facial image before live body action and execute the facial image after live body action, and false people Member executes the facial image before live body action and executes the facial image after live body action；

It executes the facial image before live body acts from the true personnel and executes in the facial image after live body action and extract very Real personnel execute the facial image before live body action and execute the skin area image after live body action as positive sample image；

It executes the facial image before live body acts from the false personnel and executes in the facial image after live body action and extract void Dummy person executes the facial image before live body action and executes the skin area image after live body action as negative sample image；With And

Sorter model is trained using the positive sample image and the negative sample image, is classified with obtaining the skin elasticity Device.

21. identity identifying method as claimed in claim 19, wherein described to capture institute from the facial image acquired Stating the skin area image that personnel to be certified execute the skin area image before live body action and execute after live body action includes：

Facial image and execution before live body action are executed from the personnel to be certified are selected in the facial image acquired Facial image after live body action；

It is acted using Face datection model to executing the facial image before live body action in the personnel to be certified and executing live body The face in facial image afterwards is positioned；

Using face key point location model to executing the facial image before live body action in the personnel to be certified and executing work The key point of the face in facial image after body action is positioned；And

The face location obtained according to positioning and key point position are to the face before the personnel to be certified execute live body action Image and the face executed in the facial image after live body action carry out region division, and work is executed to obtain the personnel to be certified The skin area image after skin area image and execution live body action before body action.

22. identity identifying method as claimed in claim 21, wherein the identity identifying method further includes：

Sample facial image is obtained, the position of the position of the face in the sample facial image and the key point of face is to have marked It is poured in；And

Neural metwork training is carried out using the sample facial image, it is crucial to obtain the Face datection model and the face Point location model.

23. identity identifying method as described in claim 1, wherein it is described that In vivo detection is carried out to the personnel to be certified, with Obtaining In vivo detection result includes：

It obtains and is directed to the facial image that the face of the personnel to be certified under structure light irradiation is acquired by binocular camera； And

Determine whether the face of the personnel to be certified belongs to live body according to the facial image, to obtain the In vivo detection knot Fruit.

24. identity identifying method as described in claim 1, wherein it is described that In vivo detection is carried out to the personnel to be certified, with Obtaining In vivo detection result includes：

Step S110：Obtain the one or more acquired for the face of the personnel to be certified under the irradiation of detection light Light image；

Step S120：The light reflection that face based on the personnel to be certified is showed in one or more of light images Characteristic determines whether the face of the personnel to be certified belongs to live body, to obtain illumination live body verification result；And

Step S130：At least determine whether the certification personnel are verified by live body based on the illumination live body verification result, with Obtain the In vivo detection result.

25. identity identifying method as claimed in claim 24, wherein in the process for the face for irradiating the personnel to be certified In, the pattern of the detection light at least changes once.

26. identity identifying method as claimed in claim 25, wherein in the process for the face for irradiating the personnel to be certified In, the pattern of the detection light at the time of each two is continuous between change.

27. identity identifying method as claimed in claim 25, wherein in the process for the face for irradiating the personnel to be certified In, the pattern of the detection light is changing at random or pre-set.

28. identity identifying method as claimed in claim 24, wherein

Step S140：Output action instructs, wherein the action command is used to indicate the certification personnel and executes corresponding move Make；

Step S150：Obtain the multiple motion images acquired for the face of the personnel to be certified；

Step S160：The action performed by the personnel to be certified is detected based on the multiple motion images；And

Step S170：Determine whether the face of the personnel to be certified belongs to living according to motion detection result and the action command Body, to obtain action live body verification result；

The step S130 includes：

Determine whether the personnel to be certified pass through based on the illumination live body verification result and the action live body verification result Live body is verified, to obtain the In vivo detection result.

29. identity identifying method as claimed in claim 28, wherein the step S170 includes：

If detected by described based on the multiple motion images acquired in the period no more than the first preset time The action kept strokes indicated by personnel to be certified the execute and action command, it is determined that the personnel's to be certified Face belongs to live body, if be not detected by institute based on the multiple motion images acquired in first preset time State the action kept strokes indicated by personnel to be certified the execute and action command, it is determined that the personnel to be certified Face be not belonging to live body.

30. identity identifying method as claimed in claim 28, wherein

The identity identifying method further includes：

It is counted during executing the step S140 to the step S170 every time once, verification number is acted with acquisition；

After the step S170, the identity identifying method further includes：

If the action live body verification result indicates that the face of the personnel to be certified is not belonging to live body, the first mistake is exported Information, and judge whether the action verification number reaches the first frequency threshold value, if action verification number reaches described First frequency threshold value then goes to the step S130, if action verification number is not up to first frequency threshold value, It returns to the step S140 or returns to the step in the case where the step S110 is executed before the step S140 S110, wherein first error message is used to prompt the live body authentication failed for the personnel to be certified.

31. identity identifying method as claimed in claim 24, wherein before the step S110, the authentication side Method further includes：

Step S108：Judge whether the Image Acquisition condition of the personnel to be certified meets preset requirement, if described image is adopted Collection condition meets the preset requirement, then goes to the step S110, wherein described image acquisition condition includes described to be certified Personnel are the location of in the image acquisition region of image collecting device and/or the personnel to be certified acquire with described image The relative angle of device.

32. identity identifying method as claimed in claim 31, wherein before the step S108 or with the step S108 Simultaneously, the identity identifying method further includes：

Step S106：Export the first prompt message, wherein first prompt message is for prompting the personnel to be certified by face Portion's face described image harvester and close described image harvester.

33. identity identifying method as claimed in claim 32, wherein the step S106 includes：Pass through speech form, image One or more outputs first prompt message in form and written form.

34. identity identifying method as claimed in claim 31, wherein the step S108 includes：

Obtain the realtime graphic acquired for the face of the personnel to be certified；

Human face region in predeterminable area and the realtime graphic of the output in real time for calibrating described image acquisition condition is used In display；And

Judge whether described image acquisition condition meets the preset requirement according to the human face region, if the human face region In predeterminable area and human face region proportion in the realtime graphic is more than the first preset ratio, it is determined that Described image acquisition condition meets the preset requirement, if the human face region is not in the predeterminable area or institute It states human face region proportion in the realtime graphic and is not more than first preset ratio, it is determined that described image pick-up slip Part is unsatisfactory for the preset requirement.

35. identity identifying method as claimed in claim 34, wherein the identity identifying method further includes：

If human face region proportion in the realtime graphic is not more than first preset ratio, export in real time First acquisition prompt message, to prompt the personnel to be certified and described image harvester close.

36. identity identifying method as claimed in claim 31, wherein the step S108 includes：

Judge whether described image acquisition condition meets the preset requirement according in the human face region,

If the human face region is located in predeterminable area and human face region proportion in the predeterminable area is big In the second preset ratio, it is determined that described image acquisition condition meets the preset requirement, if the human face region does not have position In in the predeterminable area or human face region proportion in predeterminable area ratio default no more than described second Example, it is determined that described image acquisition condition is unsatisfactory for the preset requirement.

37. identity identifying method as claimed in claim 36, wherein the identity identifying method further includes：

If human face region proportion in the predeterminable area is not more than second preset ratio, export in real time Second acquisition prompt message, to prompt the personnel to be certified and described image harvester close.

38. the identity identifying method as described in claim 34 or 36, wherein the identity identifying method further includes：

Relative position relation between human face region described in real-time judge and the predeterminable area；And

Third is exported in real time based on the relative position relation between the human face region and the predeterminable area acquires prompt message, Change the relative position relation between the personnel to be certified and described image harvester so that the face area with prompt Domain and the predeterminable area are close.

39. identity identifying method as claimed in claim 31, wherein the step S108 includes：

Obtain the posture information of described image harvester；And

Judge whether described image harvester is in vertical placement status according to the posture information, if it is, determining institute It states Image Acquisition condition and meets the preset requirement, otherwise determine that described image acquisition condition is unsatisfactory for the preset requirement.

40. identity identifying method as claimed in claim 31, wherein

The identity identifying method further includes：

It is counted during executing the step S110 to the step S120 every time once, number is verified to obtain illumination；

After the step S120, the identity identifying method further includes：

If the illumination live body verification result indicates that the face of the personnel to be certified is not belonging to live body, the second mistake is exported Information, and judge whether the illumination verification number reaches the second frequency threshold value, if illumination verification number reaches described Second frequency threshold value then goes to the step S130, if illumination verification number is not up to second frequency threshold value, It returns to the step S108 or returns to the step S110, wherein second error message waits recognizing for prompting for described The live body authentication failed of witness person.

41. identity identifying method as claimed in claim 24, wherein before the step S110 or executing the step During the S110 and step S120, the identity identifying method further includes：

Export the second prompt message, wherein second prompt message is for prompting the personnel to be certified when second is default It is interior to remain stationary as.

42. identity identifying method as claimed in claim 41, wherein second prompt message be with described second it is default when Between corresponding count down information.

43. identity identifying method as claimed in claim 24, wherein the detection light is by dynamically changing to described to be certified The color of the light of the face transmitting of personnel and/or position obtain.

44. identity identifying method as claimed in claim 24, wherein the detection light is by display screen emissions, the detection Light obtains in the following manner：Dynamically change the display screen emissions by changing the content shown on the display screen Light pattern, to emit the detection light to the face of the personnel to be certified.

45. a kind of identification authentication system, including processor and memory, wherein be stored with computer program in the memory Instruction, for executing following steps when the computer program instructions are run by the processor：

Obtain the identification information of personnel to be certified；

46. a kind of storage medium, stores program instruction on said storage, described program instruction is used to hold at runtime Row following steps：

Obtain the identification information of personnel to be certified；

47. a kind of identification authentication system, including information collecting device, processor and memory, wherein

Described information harvester is used to acquire the initial information of personnel to be certified；

Computer program instructions are stored in the memory, the computer program instructions are used for when being run by the processor Execute following steps：

Obtain the identification information of the personnel to be certified, wherein the identification information is the initial information or base It is obtained in the initial information；

Judge the identification information whether be authentication information to obtain authentification of message result；

In vivo detection is carried out to obtain In vivo detection result to the personnel to be certified；And

48. identification authentication system as claimed in claim 47, wherein the personal information harvester includes image collector It sets and/or input unit.

49. a kind of identification authentication system, including：

Information collecting device, the initial information for acquiring personnel to be certified；And

Transmitting device for the initial information to be sent to server, and receives the server from the server and passes through The whether legal authentication information of the identity about the personnel to be certified that following manner obtains：Obtain the personnel's to be certified Identification information, wherein the identification information is the initial information or is obtained based on the initial information；Judge institute State identification information whether be authentication information to obtain authentification of message result；In vivo detection is carried out to the personnel to be certified To obtain In vivo detection result；And it waits recognizing according at least to described in described information authentication result and In vivo detection result determination Whether the identity of witness person is legal.

50. identification authentication system as claimed in claim 49, wherein described information harvester includes image collecting device And/or input unit.

51. a kind of identification authentication system, including transmitting device, processor and memory, wherein

The transmitting device is used to receive the initial information of personnel to be certified from client, and will be about the personnel's to be certified The whether legal authentication information of identity is sent to the client；

52. a kind of identification authentication system, including：

Data obtaining module, the identification information for obtaining personnel to be certified；

Authentication information judgment module, for judging whether identification information is authentication information, to obtain authentification of message knot Fruit；

In vivo detection module, for carrying out In vivo detection to personnel to be certified, to obtain In vivo detection result；And

Identity determining module, for determining that the identity of personnel to be certified is according at least to authentification of message result and In vivo detection result It is no legal.