CN110335386A - A kind of auth method, device, terminal and storage medium - Google Patents

A kind of auth method, device, terminal and storage medium Download PDF

Info

Publication number
CN110335386A
CN110335386A CN201910557166.6A CN201910557166A CN110335386A CN 110335386 A CN110335386 A CN 110335386A CN 201910557166 A CN201910557166 A CN 201910557166A CN 110335386 A CN110335386 A CN 110335386A
Authority
CN
China
Prior art keywords
data
reference data
mode
facial image
authentication
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910557166.6A
Other languages
Chinese (zh)
Other versions
CN110335386B (en
Inventor
段克晓
王松健
赵伟
吴锐洲
邓攀
杨程
杨帆
李火荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201910557166.6A priority Critical patent/CN110335386B/en
Publication of CN110335386A publication Critical patent/CN110335386A/en
Application granted granted Critical
Publication of CN110335386B publication Critical patent/CN110335386B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration

Abstract

The embodiment of the invention discloses a kind of auth method, device, terminal and storage mediums, wherein auth method includes: the network environment information that door access machine is acquired in the authentication request for detecting user and the facial image of user；Obtain authentication mode corresponding with the network environment information and reference data obtaining mode；According to the reference data obtaining mode, data are read from the database of door access machine as reference data set；It is matched according to the data that the authentication mode concentrates the facial image and reference data；If matching result meets preset condition, it is determined that the authentication of the user passes through, and access control machine allows user current, and the efficiency and validity of face verification can be improved in the program.

Description

A kind of auth method, device, terminal and storage medium
Technical field
The present invention relates to fields of communication technology, and in particular to a kind of auth method, device, terminal and storage are situated between Matter.
Background technique
Face verification technology refers to using image processing techniques, carries out by acquiring facial image, and to the image of acquisition Analysis is compared to obtain a kind of technology for needing information.
Existing face verification access control system is usually what client and server was used in combination, passes through face verification The setting of access control system, the personnel only registered can just be admitted into.However, when network occurs abnormal, server Connection between end and client will appear exception, cause the time of face verification longer, or even will appear face verification failure The problem of, therefore, reduce the efficiency and validity of face verification.
Summary of the invention
The embodiment of the present invention provides a kind of auth method and device, and the efficiency of face verification can be improved and have Effect property.
The embodiment of the invention provides a kind of auth methods, comprising:
In the authentication request for detecting user, the network environment information of door access machine and the face figure of user are acquired Picture；
Obtain authentication mode corresponding with the network environment information and reference data obtaining mode；
According to the reference data obtaining mode, data are read from the database of door access machine as reference data set；
It is matched according to the data that the authentication mode concentrates the facial image and reference data；
If matching result meets preset condition, it is determined that the authentication of the user passes through, and access control machine allows User is current.
Correspondingly, the embodiment of the invention also provides a kind of authentication means, comprising:
Acquisition module, in the authentication request for detecting user, acquire door access machine network environment information and The facial image of user；
Module is obtained, obtains mould for obtaining authentication mode corresponding with the network environment information and reference data Formula；
Read module, for reading data conduct from the database of door access machine according to the reference data obtaining mode Reference data set；
Matching module, data for being concentrated according to the authentication mode to the facial image and reference data into Row matching；
Determining module when the matching result for obtaining in matching module meets preset condition, determines the body of the user Part is verified, and access control machine allows user current.
Optionally, in some embodiments of the invention, the acquisition module includes:
Determination unit, for determining current network state and current safety grade according to the network environment information；
First selection unit, for choosing authentication corresponding with current safety grade in default verification mode set Mode, and determine that reference data obtaining mode is network mode；
Second selection unit, for choosing authentication corresponding with current safety grade in default verification mode set Mode, and determine that reference data obtaining mode is local mode.
Optionally, in some embodiments of the invention, the read module is specifically used for:
If the reference data obtaining mode is network mode, data of the network data base there are update are being determined When, data after updating are obtained by current network, the database of door access machine are updated according to data after the update got, from update Data are read in database afterwards as reference data set；
If the reference data obtaining mode is local mode, data are read as reference number from the database of door access machine According to collection.
Optionally, in some embodiments of the invention, the matching module is specifically used for:
It calculates the facial image and reference data concentrates the similarity of registered images；
If similarity is greater than the first preset threshold, it is determined that the matching of the data of the facial image and reference data concentration As a result meet preset condition.
Optionally, in some embodiments of the invention, the matching module is specifically used for:
It calculates the facial image and reference data concentrates the similarity of registered images；
Obtain the identity information that similarity is greater than the registered images of the second preset threshold；
If reference data concentration be stored with related information corresponding with the identity information, it is determined that the facial image and The matching result for the data that reference data is concentrated meets preset condition.
Optionally, in some embodiments of the invention, further include relating module, the relating module is specifically used for:
The identity information of each registered images in the database of door access machine is set；
The registered images with the associated object of the identity information are obtained, affiliated partner image is obtained；
The incidence relation for establishing the identity information Yu the affiliated partner image, obtains related information；
The related information is stored in the database of door access machine.
Optionally, in some embodiments of the invention, the matching module is specifically used for:
Detect the set of characteristic points of the facial image；
When the set of characteristic points determine the face deflection angle of the facial image less than predetermined angle threshold value, joining Acquisition and the matched registered images of the set of characteristic points in data set are examined, target image set is obtained；
It calculates the facial image and the target image concentrates the similarity of registered images；
If similarity is greater than third predetermined threshold value, it is determined that the matching of the data of the facial image and reference data concentration As a result meet preset condition.
It optionally, in some embodiments of the invention, further include In vivo detection module, the In vivo detection module is specific For:
Obtain the caloric information of the facial image；
In vivo detection is carried out to the user according to the caloric information；
The acquisition module, for obtaining and the network rings when In vivo detection result indicates that the user is living body The corresponding authentication mode of border information and reference data obtaining mode.
Optionally, in some embodiments of the invention, further include update module, the update module is specifically used for:
The data that receiving network data library periodically issues update packet, update packet to the data of door access machine according to the data Library is updated；Alternatively,
The data in network data base are monitored according to predetermined period, when monitoring that data change, according to The data of variation are updated the database of door access machine.
The embodiment of the present invention acquires the network environment information and use of door access machine in the authentication request for detecting user Then the facial image at family obtains authentication mode corresponding with the network environment information and reference data obtaining mode, Further according to the reference data obtaining mode, reading data are as reference data set from the database of door access machine, then, according to The data that the authentication mode concentrates the facial image and reference data match, and preset if matching result meets Condition, it is determined that the authentication of the user passes through, and access control machine allows user current.Relative to existing face verification Scheme for, can according to current network environment carry out face verification, when the connection between server end and client can go out It is now abnormal, data can be read from the database of door access machine, and according to the data pair read from the database of door access machine User carries out authentication, is not in face verification the problem of the time is longer and face verification fails, therefore, Ke Yiti The efficiency and validity of high face verification.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached Figure.
Fig. 1 a is the first schematic diagram of a scenario of auth method provided in an embodiment of the present invention；
Fig. 1 b is the flow diagram of auth method provided in an embodiment of the present invention；
Fig. 2 a is another flow diagram of auth method provided in an embodiment of the present invention；
Fig. 2 b is second of schematic diagram of a scenario of the method for authentication provided in an embodiment of the present invention；
Fig. 2 c is the third schematic diagram of a scenario of the method for authentication provided in an embodiment of the present invention；
Fig. 3 a is the structural schematic diagram of the first embodiment of authentication means provided in an embodiment of the present invention；
Fig. 3 b is the structural schematic diagram of second of embodiment of authentication means provided in an embodiment of the present invention；
Fig. 3 c is the structural schematic diagram of the third embodiment of authentication means provided in an embodiment of the present invention；
Fig. 3 d is the structural schematic diagram of the 4th kind of embodiment of authentication means provided in an embodiment of the present invention；
Fig. 3 e is another schematic diagram of a scenario of auth method provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of terminal provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, those skilled in the art's every other implementation obtained without creative efforts Example, shall fall within the protection scope of the present invention.
The embodiment of the present invention provides a kind of auth method and device.
Wherein, which can integrate in the terminal, as shown in Figure 1a, for example, can be with the shape of client Formula is mounted in door access machine.
Specifically, the door access machine where authentication means is detecting user when user needs to carry out authentication Authentication request when, acquire the network environment information of door access machine and the facial image of user, then, authentication means obtain Take authentication mode corresponding with network environment information and reference data obtaining mode, and according to reference data obtaining mode, From the database of door access machine read data as reference data set, then, according to corresponding verification mode to facial image with The data that reference data is concentrated are matched, when matching result meets preset condition, it is determined that the authentication of the user is logical It crosses, and access control machine allows user current.
For example, when the user clicks the triggering key of authentication when, as click door access machine on " verifying " control key, door access machine Meeting identity-based checking request carries out recognition of face to user, to obtain the facial image of user, also, door access machine can also obtain Take current network environment information.Door access machine determines its corresponding verification mode and reference by current network environment information Number obtaining mode, and according to reference data obtaining mode, data are read from the database of door access machine as reference data set, so Afterwards, it is matched according to the data that corresponding verification mode concentrates facial image and reference data, when matching result meets in advance If when condition, it is determined that the authentication of the user passes through, and access control machine allows user current.
It should be noted that the database of door access machine is arranged in door access machine, therefore, tested when user needs to carry out identity When card, and the database of door access machine is stored with the image (i.e. registered images) of user, door before the user initiates authentication Taboo machine can carry out authentication to the user according to registered images, it is thus possible to improve face verification efficiency.It also needs to illustrate , environmental factor when due to user's typing registered images is different from environmental factor when user's progress authentication, When terminal and server have network connection, (server can be arranged according to network data base in the database of door access machine Database) it is updated, to improve the validity of verifying.
It is described in detail separately below, it should be noted that, the following description sequence is not as excellent to embodiment The restriction of first sequence.
A kind of auth method, comprising: in the authentication request for detecting user, acquire the network rings of door access machine The facial image of border information and user, obtains authentication mode corresponding with network environment information and reference data obtains mould Formula reads data as reference data set, last basis then according to reference data obtaining mode from the database of door access machine The data that authentication mode concentrates facial image and reference data match, if matching result meets preset condition, Determine that the authentication of user passes through, and access control machine allows user current.
Fig. 1 b is please referred to, Fig. 1 b is the flow diagram of auth method provided in an embodiment of the present invention.Authentication The detailed process of method can be such that
101, in the authentication request for detecting user, the network environment information of door access machine and the face of user are acquired Image.
For example, can receive user by authentication request transmitted by triggering authentication triggering key, for example, user The triggering keys such as " unlock " or " verifying " can be clicked or slided to trigger the authentication request, etc..Then, it is tested according to identity Card request acquires the facial image of current network environment information and user.Wherein, network environment information may include network Connection mode and network insertion type.Network connection mode may include online mode and offline mode, network insertion type It may include data access and wireless access.Wherein, data access may include local area network or mobile network, and wireless access can be with Including WiMAX.In addition, it is necessary to explanation, due to noise, illumination or equipment itself, what is usually obtained is original The quality of image is not very high, therefore is pre-processed to image, so that image is apparent, characteristics of image is become apparent from, convenient for into Image is identified and analyzed in one step.Carrying out pretreated method to image includes color space variation and denoising.In this reality It applies in example, the variation of color space is mainly carried out to the original image of acquisition, obtains facial image.
It should be noted that in order to improve the accuracy of authentication In vivo detection can be carried out to face, that is, one In a little embodiments, step " in the authentication request for detecting user, acquires the face figure of network environment information and user Picture " specifically can also include: later
(11) caloric information of facial image is obtained.
(12) In vivo detection is carried out to user according to caloric information.
When In vivo detection result instruction user is living body, 102 are thened follow the steps.
102, authentication mode corresponding with network environment information and reference data obtaining mode are obtained.
Wherein it is possible to corresponding verification mode be obtained according to network environment information, for example, can be according to network connection mode Obtain corresponding verification mode.For another example, phase can also be obtained according to the security level and current network state of actual scene The verification mode answered, that is, in some embodiments, step " obtains authentication mode corresponding with network environment information and ginseng Examine data acquisition ", it can specifically include:
(21) current network state and current safety grade are determined according to network environment information.
It can determine that current network state is presence or off-line state according to network connection mode, it can basis Network insertion type determines current safety grade, for example, can determine current safety etc. when network insertion type is wireless access Grade is inferior grade, when network insertion type is data access, can determine that current safety grade is high-grade.
(22) it if current network state is presence, is chosen and current safety grade in default verification mode set Corresponding authentication mode, and determine that reference data obtaining mode is network mode.
(23) it if current network state is off-line state, is chosen and current safety grade in default verification mode set Corresponding authentication mode, and determine that reference data obtaining mode is local mode.
It should be noted that current safety grade refers to that the security level of current scene, predetermined manner set can wrap Multiple predetermined manners are included, for example, specifically, the gate inhibition of Corporate Finance room is superior to the door at company gate in a company Prohibit rank, when user need enter company gate when, it is assumed that gate inhibition's grade at company gate be it is low, if current network state be Linear state then chooses authentication mode corresponding with inferior grade in default verification mode, and determines that reference data obtains mould Formula is network mode；If current network state is off-line state, body corresponding with inferior grade is chosen in default verification mode Part verification mode, and determine that reference data obtaining mode is local mode.
103, according to reference data obtaining mode, data are read from the database of door access machine as reference data set.
By taking a company as an example, if the database of door access machine includes the data of multiple door access machines, such as the door of accounting office The data of taboo machine, the data of general office door access machine, that is at this point, corresponding note can be screened according to corresponding door access machine Volume image obtains registered images corresponding to accounting office if accounting office, can not compare other offices as reference data set The registered images of room.
Alternatively, it is also understood that preliminary screening is carried out to the data in the database of door access machine, for example, if can sentence Disconnected current face's image is women, then only needs to obtain women registered images at this time and be compared, therefore, it is possible to reduce meter Calculation amount.
Reference data obtaining mode may include network mode and local mode, if reference data obtaining mode is network mould When formula, and network data library can be carried out more there are when data update by database of the updated data to door access machine Newly, then, data are read then from updated database as reference data set, and pass through the reference data set to user into Row authentication, it is thus possible to improve the reliability of authentication；If reference data obtaining mode is local mode, from door The database of taboo machine reads data as reference data set, and the reference data set obtained by the database in door access machine to Family carries out authentication, the efficiency of authentication can be improved, that is, in some embodiments, step " is obtained according to reference data Mode reads data as reference data set from the database of door access machine ", it can specifically include:
(31) if reference data obtaining mode is network mode, data of the network data base there are update are being determined When, data after updating are obtained by current network, the database of door access machine are updated according to data after the update got, from update Data are read in database afterwards as reference data set；
(32) if reference data obtaining mode is local mode, data are read as reference number from the database of door access machine According to collection.
104, it is matched according to the data that authentication mode concentrates facial image and reference data.
According to authentication mode, the data concentrated to facial image and reference data are matched, when facial image and When the matching result for the data that reference data is concentrated meets preset condition, 105 are thened follow the steps；When facial image and reference data When the matching result of the data of concentration is unsatisfactory for preset condition, at this point, the authentication that the user can be generated in terminal does not pass through Information, and show the unacceptable prompt information of corresponding authentication, so that related personnel can be with timely learning.Authentication side What formula can be determined according to current safety grade, the data that reference data is concentrated may include registered images and related information.
For example, if when current safety grade is inferior grade, it can be determined that the registered images and user that reference data is concentrated Similarity between facial image, when the similarity between the reference data registered images concentrated and the facial image of user is greater than When the first preset threshold, then it can determine that the matching result for the data that facial image and reference data are concentrated meets preset condition, That is, in some embodiments, step " the data progress that facial image and reference data are concentrated according to authentication mode With ", it can specifically include:
(41) it calculates facial image and reference data concentrates the similarity of registered images.
(42) if similarity is greater than the first preset threshold, it is determined that the matching of the data of facial image and reference data concentration As a result meet preset condition.
Specifically, after door access machine is by scanning employee A, calculating employee A's when the employee A of T company needs to enter company Facial image and reference data concentrate the similarity of registered images, when similarity is greater than the first preset threshold, it is determined that employee A and The matching result for the data that reference data is concentrated meets preset condition.
For another example, if current safety grade is inferior grade, can also by registered images and related information to user into Row authentication, when the similarity between the reference data registered images concentrated and the facial image of user is greater than the second default threshold When value, the identity information that similarity is greater than the registered images of the second preset threshold is obtained, when reference data concentration is stored with and body The corresponding related information of part information, it is determined that the matching result of the data of facial image and reference data concentration meets default item Part, that is, in some embodiments, step " is carried out according to the data that authentication mode concentrates facial image and reference data Matching ", can specifically include:
(51) it calculates facial image and reference data concentrates the similarity of registered images.
(52) identity information that similarity is greater than the registered images of the second preset threshold is obtained.
(53) if reference data concentration is stored with related information corresponding to the identity information, it is determined that facial image and reference The matching result of data in data set meets preset condition.
Specifically, door access machine calculates the facial image of visitor A by scanning visitor A when visitor A needs to call on T company The similarity of registered images is concentrated with reference data, obtains the identity letter that similarity is greater than the registered images of the second preset threshold Breath, for example, second preset threshold is 85%, identity information can be visitor, if reference data concentration is stored with and identity The corresponding related information of information, it is determined that the matching result of the data of facial image and reference data concentration meets preset condition, For example, reference data, which is concentrated, is stored with the cell-phone number for inviting people corresponding with visitor, it is determined that facial image and reference data set In the matching results of data meet preset condition；For another example, reference data, which is concentrated, is stored with invitation people's corresponding with visitor Facial image, it is determined that the matching result of the data of facial image and reference data concentration meets preset condition.
In addition, it is necessary to explanation, which can be is pre-established by operation maintenance personnel, and it is pre- to be also possible to terminal It first establishes, depending on actual conditions.That is, " acquisition similarity is greater than the registered images of the second preset threshold to step Identity information " specifically can also include:
(61) identity information of each registered images in the database of door access machine is set.
(62) registered images with the associated object of identity information are obtained, affiliated partner image is obtained
(63) incidence relation for establishing identity information Yu affiliated partner image, obtains related information.
(64) related information is stored in the database of door access machine.
It should also be noted that, the affiliated partner refers to the inviter for having incidence relation with user, affiliated partner figure As referring to the registered images of inviter, for example, when there is multiple visitors to need to call between T company, door access machine is by these visitors Identity information stored to corresponding registered images respectively, then, door access machine obtains and identity information affiliated partner again Registered images, for example, door access machine, which is obtained, then establishes visitor with the registered images of the associated inviter of identity information of visitor A The incidence relation of the registered images of the identity information and inviter of A obtains the corresponding related information of identity information of visitor A, most Afterwards, related information is stored in the database of door access machine.
For another example, if current safety grade is high-grade, the people can be judged by the set of characteristic points of facial image Whether the face deflection angle of face image is less than predetermined angle, when face deflection angle is less than predetermined angle, further according to feature point set It closes and concentrates acquisition and the matched registered images of set of characteristic points in reference data, when similar between facial image and registered images When degree is greater than third predetermined threshold value, determine that the matching result for the data that facial image and reference data are concentrated meets preset condition.
Specifically, the employee A when T company needs to enter the higher place of security level by door access machine, such as accounting office, Door access machine is by scanning employee A, and when the eyes for determining the employee A look at door access machine straight, i.e., the face deflection angle of employee A is less than pre- If when angle, acquisition can be concentrated matched with set of characteristic points in reference data based on the set of characteristic points of the facial image Registered images determine face figure when the similarity between the facial image of employee A and registered images is greater than third predetermined threshold value The matching result for the data that picture and reference data are concentrated meets preset condition.
It should be noted that preset condition can be what operation maintenance personnel was configured in advance, preset when matching result meets Condition thens follow the steps 105；When matching result is unsatisfactory for preset condition, at this point it is possible to generate the authentication of the user not By information, and the unacceptable prompt information of corresponding authentication is shown, so that related personnel can be with timely learning.
In order to guarantee door access machine database data accuracy, which can also include:
Data that receiving network data library periodically issues update packet, according to data update packet to the database of door access machine into Row updates；Alternatively, the data in network data base are monitored according to predetermined period, when monitoring that data change, It is updated according to database of the data of variation to door access machine.
Wherein, predetermined period can be pre-set by operation maintenance personnel, for example, can set predetermined period to 30 points Clock, 40 minutes or 180 minutes etc., with specific reference to actual conditions, details are not described herein.
105, determine that the authentication of user passes through, and access control machine allows user current.
The embodiment of the present invention acquires the network environment information and use of door access machine in the authentication request for detecting user Then the facial image at family obtains authentication mode corresponding with network environment information and reference data obtaining mode, then root According to reference data obtaining mode, data are read from the database of door access machine as reference data set, then, according to authentication The data that mode concentrates facial image and reference data match, if matching result meets preset condition, it is determined that user Authentication pass through, and access control machine allows user current.It, can basis for the scheme of existing face verification Current network environment carries out face verification, can be from door access machine when the connection between server end and client will appear exception Database in read data, and authentication is carried out to user according to the data read from the database of door access machine, no Will appear the problem of time is longer and face verification fails of face verification, it is thus possible to improve the efficiency of face verification with And validity.
Citing is further described below for the method according to described in embodiment.
It will be illustrated so that the authentication means specifically integrate in the terminal as an example in the present embodiment.
Fig. 2 a, a kind of auth method are please referred to, detailed process can be such that
201, door access machine acquires network environment information and the user of door access machine in the authentication request for detecting user Facial image.
For example, door access machine, which can receive user, passes through authentication request transmitted by triggering authentication triggering key, than Such as, user can click or slide the triggering keys such as " unlock " or " verifying " to trigger the authentication request, etc..Then, door Taboo machine can acquire the facial image of current network environment information and user according to authentication request.Wherein, network rings Border information may include network connection mode and network insertion type.Network connection mode may include on-line mode and offline Mode, network insertion type may include data access and wireless access.Wherein, data access may include local area network or movement Network, wireless access may include WiMAX.In addition, it is necessary to explanation, due to the original of noise, illumination or equipment itself Cause, the quality of the original image usually obtained is not very high, therefore is pre-processed to image, so that image is apparent, image Feature becomes apparent from, convenient for further image is identified and analyzed.It includes face that door access machine, which carries out pretreated method to image, Colour space variation and denoising.In the present embodiment, the variation that color space is mainly carried out to the original image of acquisition, obtains people Face image.
202, door access machine obtains the caloric information of facial image.
For example, door access machine can obtain the caloric information of the facial image of user by three-dimensional structure light technology.Specifically, Door access machine can be schemed by the face that infrared camera and infrared structure light projector carry out multiple angles to the face of user As acquisition, and then obtain the caloric information of facial image.
Herein, it should be noted that after the specific optical information to body surface of project structured light, can be caused according to object Optical signal variation come information such as the position and the depth that calculate object, and then restore the object in the space of project structured light 3-D image.
203, door access machine judges whether the face in facial image is living body, if in facial image according to caloric information Face is living body, then door access machine can execute step 204；If the face in facial image is not living body, door access machine can not The corresponding verification mode of network environment information is called, optionally, corresponding non-living body prompt information can be generated in door access machine at this time, And show the non-living body prompt information, so that related personnel can be with timely learning.
Wherein, judge the face in facial image whether be living body mode can there are many, for example, door access machine can be sentenced Whether the living body value in disconnected caloric information is equal to default living body value, if being equal to default living body value, it is determined that the people in facial image Face is living body, if not equal to default living body value, it is determined that the face in facial image is non-living body.
Wherein, which can be configured according to the demand of practical application, for example, can be set to 1, then this When, if the living body value in the caloric information that door access machine detects is 1, that is, it can determine that the face in facial image is living body.Again For example, this, which is preset living body value, to be 0.8, then, when the living body value in the caloric information that door access machine detects is 0.6, It can determine that the face in facial image is not living body, and so on.
204, door access machine obtains authentication mode corresponding with network environment information and reference data obtaining mode.
It should be noted that current safety grade refers to that the security level of current scene, predetermined manner set can wrap Include multiple predetermined manners, wherein door access machine can obtain corresponding verification mode according to network environment information, for example, door access machine Corresponding verification mode can be obtained according to network connection mode.For another example, door access machine can also be according to the safety of actual scene Grade and current network state obtain corresponding verification mode, for example, when user needs to enter company gate, if company is big Gate inhibition's grade of door is inferior grade, and when the current network state of the door access machine at company gate is presence, in default verifying Authentication mode corresponding with inferior grade is chosen in mode set, and determines that reference data obtaining mode is network mode；If Gate inhibition's grade at company gate be it is high-grade, and the current network state of the door access machine at company gate be presence when, pre- If in verification mode set choose with high-grade corresponding authentication mode, and determine reference data obtaining mode be network mould Formula；For another example, if gate inhibition's grade at company gate is inferior grade, and the current network state of the door access machine at company gate is offline It when state, presets and chooses authentication mode corresponding with inferior grade in verification mode set, and determine that reference data obtains mould Formula is local mode；Gate inhibition's grade at Ruo Ruo company gate is high-grade, and the current network state of the door access machine at company gate When for off-line state, presets and chosen in verification mode set and high-grade corresponding authentication mode, and determination reference data Obtaining mode is local mode.Door access machine obtains authentication mode corresponding with network environment information and reference data obtains mould After formula, 205 are thened follow the steps.
205, door access machine is matched according to the data that authentication mode concentrates facial image and reference data.
According to authentication mode, the data concentrated to facial image and reference data match door access machine, work as face When the matching result for the data that image and reference data are concentrated meets preset condition, 206 are thened follow the steps；When facial image and ginseng When examining the matching results of the data in data set and being unsatisfactory for preset condition, at this point, the identity that the user can be generated in door access machine is tested Card shows the unacceptable prompt information of corresponding authentication not by information, so that related personnel can be with timely learning.
Wherein, authentication mode can determine that the data that reference data is concentrated can wrap according to current safety grade Include registered images and related information.
For example, Fig. 2 b is please referred to, and when the employee A of T company needs to enter company by the door access machine at gate, the door at gate The security level of taboo machine is inferior grade, and the reference data obtaining mode of the door access machine at gate is network mode, the gate inhibition at gate Machine obtains data after updating by current network, according to what is got when determining data of the network data base there are update Data update the database of the door access machine at gate after update, from data are read after update in database as reference data set, member After work A initiates the request of authentication to the door access machine at gate, the door access machine at gate gets the facial image of employee A, calculates The facial image and reference data of employee A concentrate the similarity of registered images, registered images and user when reference data concentration Facial image between similarity be greater than the first preset threshold when, first preset threshold can be 80%, work as reference data When similarity between the registered images of concentration and the facial image of user is greater than 80%, then employee A and reference number can be determined Matching result according to the data of concentration meets preset condition.
For another example, need to call on T company please continue to refer to Fig. 2 b, visitor A, when visitor A needs the door access machine by gate When into company, the security level of the door access machine at gate is inferior grade, and the reference data obtaining mode of door access machine is network mould Formula, door access machine obtain data after updating by current network, according to obtaining when determining data of the network data base there are update Data update the database of the door access machine at gate after the update got, from data are read after update in database as reference data Collection, after visitor A initiates the request of authentication to the door access machine at gate, as the people of registered images and user that reference data is concentrated When similarity between face image is greater than the second preset threshold, which can be 85%, available to be greater than The identity information of 85% whole registered images, identity information can be visitor, believe if reference data concentration is stored with identity Ceasing corresponding related information, it is determined that the matching result of the data of facial image and reference data concentration meets preset condition, than Such as, reference data, which is concentrated, is stored with the cell-phone number for inviting people corresponding with visitor, it is determined that facial image and reference data are concentrated The matching results of data meet preset condition；For another example, reference data, which is concentrated, is stored with the people for inviting people corresponding with visitor Face image, it is determined that the matching result of the data of facial image and reference data concentration meets preset condition.
For another example, or by taking Fig. 2 b as an example, when the employee A of T company needs to enter accounting office by door access machine, accounting office Door access machine security level be it is high-grade, and the reference data obtaining mode of the door access machine of accounting office be network mode, finance The door access machine of room obtains data after updating by current network when determining data of the network data base there are update, according to Data update the database of the door access machine of accounting office after the update got, from data are read after update in database as reference Data set, door access machine can be concentrated in reference data and be obtained and set of characteristic points based on the set of characteristic points of the facial image The registered images matched determine people when the similarity between the facial image of employee A and registered images is greater than third predetermined threshold value The matching result for the data that face image and reference data are concentrated meets preset condition.
Optionally, in some embodiments, the reference data obtaining mode of door access machine is local mode, please refers to Fig. 2 c, Door access machine can read data as reference data set, in addition, when door access machine reference data obtains mould from the database of door access machine When formula is local mode, matched method is carried out according to the data that authentication mode concentrates facial image and reference data It is similar with preceding embodiment, preceding embodiment is please referred to, details are not described herein.
In order to guarantee door access machine database data accuracy, which can also include:
Door access machine can receive the data that network data base periodically issues and update packet, and door access machine updates packet pair according to data The database of door access machine is updated；Alternatively, door access machine is monitored the data in network data base according to predetermined period, door When monitoring that data change, door access machine is updated the database of door access machine according to the data of variation taboo machine.
Wherein, predetermined period can be pre-set by operation maintenance personnel, for example, can set predetermined period to 30 points Clock, 40 minutes or 180 minutes etc., with specific reference to actual conditions, details are not described herein.
206, door access machine determines that the authentication of user passes through, and allows user current.
Door access machine of the embodiment of the present invention acquires network environment information and user in the authentication request for detecting user Facial image, then, door access machine obtains corresponding with network environment information authentication mode and reference data obtaining mode, Door access machine reads data as reference data set, then, door further according to reference data obtaining mode from the database of door access machine Taboo machine is matched according to the data that authentication mode concentrates facial image and reference data, is preset if matching result meets Condition, door access machine then determines that the authentication of user passes through, and allows user current.Relative to existing face verification scheme and Speech can carry out face verification according to current network environment, can when the connection between server end and client will appear exception To read data from the database of door access machine, and body is carried out to user according to the data read from the database of door access machine Part verifying, is not in face verification the problem of the time is longer and face verification fails, it is thus possible to improve face verification Efficiency and validity.
For convenient for better implementation auth method provided in an embodiment of the present invention, the embodiment of the present invention also provides one kind Based on above-mentioned authentication means (referred to as verifying device).Wherein the meaning of noun is identical with auth method, specific real Existing details can be with reference to the explanation in embodiment of the method.
Fig. 3 a is please referred to, Fig. 3 a is the structural schematic diagram of authentication means provided in an embodiment of the present invention, and wherein this is tested Card device may include acquisition module 301, obtain module 302, read module 303, matching module 304 and determining module 305, Specifically it can be such that
Acquisition module 301, for acquiring the network environment information of door access machine and the facial image of user.
It is asked for example, acquisition module 301 can receive user by authentication transmitted by triggering authentication triggering key It asks, for example, user can click or slide the triggering keys such as " unlock " or " verifying " to trigger the authentication request, etc..So Afterwards, the facial image of current network environment information and user is acquired according to authentication request.Wherein, network environment information It may include network connection mode and network insertion type.Network connection mode may include online mode and offline mode, Network insertion type may include data access and wireless access.Wherein, data access may include local area network or mobile network, Wireless access may include WiMAX.In addition, it is necessary to which explanation is led to due to noise, illumination or equipment itself The quality of the original image often obtained is not very high, therefore is pre-processed to image, so that image is apparent, characteristics of image is more Obviously, convenient for further image is identified and analyzed.To image carry out pretreated method include color space variation and Denoising.In the present embodiment, the variation that color space is mainly carried out to the original image of acquisition, obtains facial image
Module 302 is obtained, obtains mould for obtaining authentication mode corresponding with network environment information and reference data Formula.
Wherein it is possible to corresponding verification mode be obtained according to network environment information, for example, can be according to network connection mode Obtain corresponding verification mode.For another example, phase can also be obtained according to the security level and current network state of actual scene The verification mode answered.In some embodiments, obtain module 302 can specifically include: determination unit, the first selection unit and Second selection unit.Wherein it is determined that unit is used to determine current network state and current safety etc. according to network environment information Grade, the first selection unit are used to choose authentication mode corresponding with current safety grade in default verification mode set, And determining that reference data obtaining mode is network mode, the second selection unit is for choosing and working as in default verification mode set The corresponding authentication mode of preceding security level, and determine that reference data obtaining mode is local mode.
Read module 303, for according to reference data obtaining mode, reading data from the database of door access machine as ginseng Examine data set.
Reference data obtaining mode may include network mode and local mode, if reference data obtaining mode is network mould When formula, and network data library can be carried out more there are when data update by database of the updated data to door access machine Newly, then, data are read then from updated database as reference data set, and pass through the reference data set to user into Row authentication, it is thus possible to improve the reliability of authentication；If reference data obtaining mode is local mode, from door The database of taboo machine reads data as reference data set, and the reference data set obtained by the database in door access machine to Family carries out authentication, and the efficiency of authentication can be improved, that is, in some embodiments, if read module 303 is specifically used for Reference data obtaining mode is that network mode passes through current network then when determining data of the network data base there are update Data after updating are obtained, the database of door access machine are updated according to data after the update got, from reading in database after update Data are as reference data set；If reference data obtaining mode is local mode, data are read from the database of door access machine and are made For reference data set.
Matching module 304, data for being concentrated according to authentication mode to the facial image and reference data into Row matching.
What authentication mode can be determined according to current safety grade, the data that reference data is concentrated may include registration Image and related information.
Optionally, in some embodiments of the invention, matching module specifically can be used for: calculate facial image and reference The similarity of registered images in data set, if similarity is greater than the first preset threshold, it is determined that facial image and reference data set In the matching results of data meet preset condition.
Optionally, in some embodiments of the invention, matching module specifically can be also used for: calculate facial image and ginseng The similarity of registered images in data set is examined, the identity information that similarity is greater than the registered images of the second preset threshold is obtained, if Reference data concentration is stored with related information corresponding to the identity information, it is determined that the data of facial image and reference data concentration Matching result meet preset condition.
In addition, it is necessary to explanation, which can be is pre-established by operation maintenance personnel, is also possible to door access machine It pre-establishes, depending on actual conditions.That is, it is optional, in some embodiments of the invention, Fig. 3 b is please referred to, Further include relating module 306, relating module is specifically used for: the identity information of each registered images in the database of door access machine be set, The registered images with the associated object of identity information are obtained, affiliated partner image is obtained, establishes identity information and affiliated partner figure The incidence relation of picture, obtains related information, the related information is stored in the database of the door access machine.
Optionally, in some embodiments of the invention, matching module specifically can be also used for: detect the spy of facial image Point set is levied, when set of characteristic points determine the face deflection angle of the facial image less than predetermined angle threshold value, is being referred to Acquisition and the matched registered images of set of characteristic points, obtain target image set in data set, calculate facial image and the target The similarity of registered images in image set, if similarity is greater than third predetermined threshold value, it is determined that facial image and reference data set In the matching results of data meet preset condition.
Determining module 305 determines user's when the matching result for obtaining in matching module 304 meets preset condition Authentication passes through, and access control machine allows user current.
It should be noted that can carry out In vivo detection in order to improve the accuracy of authentication to face, please refer to figure 3c further includes optionally In vivo detection module 307 in some embodiments of the invention, In vivo detection module can specifically be used In: the caloric information of facial image is obtained, In vivo detection is carried out to user according to caloric information.Obtaining module 302 can also use In when In vivo detection result instruction user is living body, authentication mode corresponding with network environment information and reference number are obtained According to obtaining mode.
In addition, it should also be noted that, gate inhibition when door access machine and server exist and be connected to the network, on door access machine The database of machine can be updated by the network data base on server, please refer to Fig. 3 d, optionally, of the invention one In a little embodiments, further include update module 308, update module specifically can be used for: receiving network data library is periodically issued Data update packet, update packet according to data and are updated to the database of door access machine, alternatively, according to predetermined period to network data Data in library are monitored, and when monitoring that data change, are carried out according to database of the data of variation to door access machine It updates.
Acquisition module of the embodiment of the present invention 301 acquires the network of door access machine in the authentication request for detecting user Then the facial image of environmental information and user obtains module 302 and obtains authentication mode corresponding with network environment information With reference data obtaining mode, read module 303 reads number from the database of door access machine further according to reference data obtaining mode According to as reference data set, then, matching module 304 is according to authentication mode to the number of facial image and reference data concentration According to being matched, if matching result meets preset condition, determining module 305 determines that the authentication of user passes through, and controls Door access machine allows user current.For the scheme of existing face verification, face can be carried out according to current network environment Verifying can read data when the connection between server end and client will appear exception from the database of door access machine, and According to the data read from the database of door access machine to user carry out authentication, be not in face verification time compared with The problem of long and face verification fails, it is thus possible to improve the efficiency and validity of face verification.
Further, for the ease of the understanding to auth method provided in an embodiment of the present invention, Fig. 3 e is please referred to, with Authentication means are integrated in for door access machine, and user can be in advance in corresponding small routine or the cell phone software typing user Image, obtain registered images, and the registered images are uploaded in the network data base of server side.Then, authentication The database of the door access machine of device pulls the registered images being stored in network data base.When user enters the area for having the door access machine When domain, door access machine can capture the facial image of the user first, meanwhile, door access machine can also detect the working condition such as net of its own Whether network there is exception and whether data transmission exception etc. occurs, also, door access machine is gone back in the case where there is network connection Whether can change according to the data in predetermined period detection network data base, if so, by the data of variation to gate inhibition The database of machine is updated.Then, door access machine can also carry out In vivo detection to the facial image of user, when user is living body When, then carry out face matching, that is, judge whether the facial image of the user is stored with registration figure in the database of door access machine Picture, if so, the identification success of the user, and the permission based on the user, determine the region that the user can enter.
Correspondingly, the embodiment of the present invention also provides a kind of terminal, as shown in figure 4, the terminal may include radio frequency (RF, Radio Frequency) circuit 401, the memory 402, defeated that includes one or more computer readable storage medium Enter unit 403, display unit 404, sensor 405, voicefrequency circuit 406, Wireless Fidelity (WiFi, Wireless Fidelity) The components such as module 407, the processor 408 for including one or more than one processing core and power supply 409.This field skill Art personnel are appreciated that the restriction of the not structure paired terminal of terminal structure shown in Fig. 4, may include more or more than illustrating Few component perhaps combines certain components or different component layouts.Wherein:
RF circuit 401 can be used for receiving and sending messages or communication process in, signal sends and receivees, particularly, by base station After downlink information receives, one or the processing of more than one processor 408 are transferred to；In addition, the data for being related to uplink are sent to Base station.In general, RF circuit 401 includes but is not limited to antenna, at least one amplifier, tuner, one or more oscillators, uses Family identity module (SIM, Subscriber Identity Module) card, transceiver, coupler, low-noise amplifier (LNA, Low Noise Amplifier), duplexer etc..In addition, RF circuit 401 can also by wireless communication with network and its He communicates equipment.Any communication standard or agreement, including but not limited to global system for mobile telecommunications system can be used in the wireless communication Unite (GSM, Global System of Mobile communication), general packet radio service (GPRS, General Packet Radio Service), CDMA (CDMA, Code Division Multiple Access), wideband code division it is more Location (WCDMA, Wideband Code Division Multiple Access), long term evolution (LTE, Long Term Evolution), Email, short message service (SMS, Short Messaging Service) etc..
Memory 402 can be used for storing software program and module, and processor 408 is stored in memory 402 by operation Software program and module, thereby executing various function application and data processing.Memory 402 can mainly include storage journey Sequence area and storage data area, wherein storing program area can the (ratio of application program needed for storage program area, at least one function Such as sound-playing function, image player function) etc.；Storage data area, which can be stored, uses created data according to terminal (such as audio data, phone directory etc.) etc..In addition, memory 402 may include high-speed random access memory, can also include Nonvolatile memory, for example, at least a disk memory, flush memory device or other volatile solid-state parts.Phase Ying Di, memory 402 can also include Memory Controller, to provide processor 408 and input unit 403 to memory 402 Access.
Input unit 403 can be used for receiving the number or character information of input, and generate and user setting and function Control related keyboard, mouse, operating stick, optics or trackball signal input.Specifically, in a specific embodiment In, input unit 403 may include touch sensitive surface and other input equipments.Touch sensitive surface, also referred to as touch display screen or touching Control plate, collect user on it or nearby touch operation (such as user using any suitable object such as finger, stylus or Operation of the attachment on touch sensitive surface or near touch sensitive surface), and corresponding connection dress is driven according to preset formula It sets.Optionally, touch sensitive surface may include both touch detecting apparatus and touch controller.Wherein, touch detecting apparatus is examined The touch orientation of user is surveyed, and detects touch operation bring signal, transmits a signal to touch controller；Touch controller from Touch information is received on touch detecting apparatus, and is converted into contact coordinate, then gives processor 408, and can reception processing Order that device 408 is sent simultaneously is executed.Furthermore, it is possible to a variety of using resistance-type, condenser type, infrared ray and surface acoustic wave etc. Type realizes touch sensitive surface.In addition to touch sensitive surface, input unit 403 can also include other input equipments.Specifically, other are defeated Entering equipment can include but is not limited to physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse One of mark, operating stick etc. are a variety of.
Display unit 404 can be used for showing information input by user or be supplied to user information and terminal it is various Graphical user interface, these graphical user interface can be made of figure, text, icon, video and any combination thereof.Display Unit 404 may include display panel, optionally, can using liquid crystal display (LCD, Liquid Crystal Display), The forms such as Organic Light Emitting Diode (OLED, Organic Light-Emitting Diode) configure display panel.Further , touch sensitive surface can cover display panel, after touch sensitive surface detects touch operation on it or nearby, send processing to Device 408 is followed by subsequent processing device 408 and is provided on a display panel accordingly according to the type of touch event to determine the type of touch event Visual output.Although touch sensitive surface and display panel are to realize input and input as two independent components in Fig. 4 Function, but in some embodiments it is possible to touch sensitive surface and display panel are integrated and realizes and outputs and inputs function.
Terminal may also include at least one sensor 405, such as optical sensor, motion sensor and other sensors. Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to ambient light Light and shade adjust the brightness of display panel, proximity sensor can close display panel and/or back when terminal is moved in one's ear Light.As a kind of motion sensor, gravity accelerometer can detect (generally three axis) acceleration in all directions Size can detect that size and the direction of gravity when static, can be used to identify mobile phone posture application (such as horizontal/vertical screen switching, Dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；It can also configure as terminal The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
Voicefrequency circuit 406, loudspeaker, microphone can provide the audio interface between user and terminal.Voicefrequency circuit 406 can By the electric signal after the audio data received conversion, it is transferred to loudspeaker, voice signal output is converted to by loudspeaker；It is another The voice signal of collection is converted to electric signal by aspect, microphone, is converted to audio data after being received by voicefrequency circuit 406, then After the processing of audio data output processor 408, it is sent to such as another terminal through RF circuit 401, or by audio data Output is further processed to memory 402.Voicefrequency circuit 406 is also possible that earphone jack, with provide peripheral hardware earphone with The communication of terminal.
WiFi belongs to short range wireless transmission technology, and terminal can help user's transceiver electronics postal by WiFi module 407 Part, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 4 is shown WiFi module 407, but it is understood that, and it is not belonging to must be configured into for terminal, it can according to need do not changing completely Become in the range of the essence of invention and omits.
Processor 408 is the control centre of terminal, using the various pieces of various interfaces and connection whole mobile phone, is led to It crosses operation or executes the software program and/or module being stored in memory 402, and call and be stored in memory 402 Data execute the various functions and processing data of terminal, to carry out integral monitoring to mobile phone.Optionally, processor 408 can wrap Include one or more processing cores；Preferably, processor 408 can integrate application processor and modem processor, wherein answer With the main processing operation system of processor, user interface and application program etc., modem processor mainly handles wireless communication. It is understood that above-mentioned modem processor can not also be integrated into processor 408.
Terminal further includes the power supply 409 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply pipe Reason system and processor 408 are logically contiguous, to realize management charging, electric discharge and power managed by power-supply management system Etc. functions.Power supply 409 can also include one or more direct current or AC power source, recharging system, power failure inspection The random components such as slowdown monitoring circuit, power adapter or inverter, power supply status indicator.
Although being not shown, terminal can also include camera, bluetooth module etc., and details are not described herein.Specifically in this implementation In example, the processor 408 in terminal can be corresponding by the process of one or more application program according to following instruction Executable file is loaded into memory 402, and the application program being stored in memory 402 is run by processor 408, from And realize various functions:
In the authentication request for detecting user, acquire network environment information and user facial image, obtain with The corresponding authentication mode of network environment information and reference data obtaining mode, then according to reference data obtaining mode, from Data are read in the database of door access machine as reference data set, finally according to authentication mode to facial image and reference number It is matched according to the data of concentration, if matching result meets preset condition, it is determined that the authentication of user passes through.
The embodiment of the present invention acquires the face of network environment information and user in the authentication request for detecting user Then image obtains authentication mode corresponding with network environment information and reference data obtaining mode, further according to reference number According to obtaining mode, data are read from the database of door access machine as reference data set, then, according to authentication mode to people The data that face image and reference data are concentrated are matched, if matching result meets preset condition, it is determined that the identity of user is tested Card passes through, and access control machine allows user current.It, can be according to current network for the scheme of existing face verification Environment carries out face verification, can be from the database of door access machine when the connection between server end and client will appear exception Middle reading data, and authentication is carried out to user according to the data read from the database of door access machine, it is not in people The problem of time of face verifying is longer and face verification fails, it is thus possible to improve the efficiency and validity of face verification.
Embodiment five,
It will appreciated by the skilled person that all or part of the steps in the various methods of above-described embodiment can be with It is completed by instructing, or relevant hardware is controlled by instruction to complete, which can store computer-readable deposits in one In storage media, and is loaded and executed by processor.
For this purpose, the embodiment of the present invention provides a kind of storage medium, wherein being stored with a plurality of instruction, which can be processed Device is loaded, to execute the step in any auth method provided by the embodiment of the present invention.For example, the instruction can To execute following steps:
In the authentication request for detecting user, acquire network environment information and user facial image, obtain with The corresponding authentication mode of network environment information and reference data obtaining mode, then according to reference data obtaining mode, from Data are read in the database of door access machine as reference data set, finally according to authentication mode to facial image and reference number It is matched according to the data of concentration, if matching result meets preset condition, it is determined that the authentication of user passes through, and controls door Taboo machine allows user current.
The specific implementation of above each operation can be found in the embodiment of front, and details are not described herein.
Wherein, which may include: read-only memory (ROM, Read Only Memory), random access memory Body (RAM, Random Access Memory), disk or CD etc..
By the instruction stored in the storage medium, any identity provided by the embodiment of the present invention can be executed and tested Step in card method, it is thereby achieved that achieved by any auth method provided by the embodiment of the present invention Beneficial effect is detailed in the embodiment of front, and details are not described herein.
A kind of auth method, device, terminal and storage medium is provided for the embodiments of the invention above to carry out It is discussed in detail, used herein a specific example illustrates the principle and implementation of the invention, above embodiments Explanation be merely used to help understand method and its core concept of the invention；Meanwhile for those skilled in the art, foundation Thought of the invention, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification is not It is interpreted as limitation of the present invention.

Claims (12)

1. a kind of auth method characterized by comprising
In the authentication request for detecting user, the network environment information of door access machine and the facial image of user are acquired；
Obtain authentication mode corresponding with the network environment information and reference data obtaining mode；
According to the reference data obtaining mode, data are read from the database of door access machine as reference data set；
It is matched according to the data that the authentication mode concentrates the facial image and reference data；
If matching result meets preset condition, it is determined that the authentication of the user passes through, and access control machine allows user It is current.
2. the method according to claim 1, wherein described obtain identity corresponding with the network environment information Verification mode and reference data obtaining mode, comprising:
Current network state and current safety grade are determined according to the network environment information；
If current network state is presence, body corresponding with current safety grade is chosen in default verification mode set Part verification mode, and determine that reference data obtaining mode is network mode；
If current network state is off-line state, body corresponding with current safety grade is chosen in default verification mode set Part verification mode, and determine that reference data obtaining mode is local mode.
3. according to the method described in claim 2, it is characterized in that, described according to the reference data obtaining mode, from gate inhibition The database of machine reads data as reference data set, comprising:
If the reference data obtaining mode is network mode, when determining data of the network data base there are update, lead to It crosses current network and obtains data after update, the database of door access machine is updated according to data after the update got, the number after update According to reading data in library as reference data set；
If the reference data obtaining mode is local mode, data are read as reference data from the database of door access machine Collection.
4. according to the method described in claim 2, it is characterized in that, the reference data concentrate data include registered images, The data concentrated according to the authentication mode to the facial image and reference data match, comprising:
It calculates the facial image and reference data concentrates the similarity of registered images；
If similarity is greater than the first preset threshold, it is determined that the matching result of the data of the facial image and reference data concentration Meet preset condition.
5. according to the method described in claim 2, it is characterized in that, the reference data concentrate data include registered images and Related information, the data concentrated according to the authentication mode to the facial image and reference data match, Include:
It calculates the facial image and reference data concentrates the similarity of registered images；
Obtain the identity information that similarity is greater than the registered images of the second preset threshold；
If reference data concentration is stored with related information corresponding with the identity information, it is determined that the facial image and reference The matching result of data in data set meets preset condition.
6. according to the method described in claim 5, it is characterized in that, the registration for obtaining similarity and being greater than the second preset threshold Before the identity information of image, further includes:
The identity information of each registered images in the database of door access machine is set；
The registered images with the associated object of the identity information are obtained, affiliated partner image is obtained；
The incidence relation for establishing the identity information Yu the affiliated partner image, obtains related information；
The related information is stored in the database of door access machine.
7. according to the method described in claim 2, it is characterized in that, the reference data concentrate data include registered images, The data concentrated according to the authentication mode to the facial image and reference data match, comprising:
Detect the set of characteristic points of the facial image；
When the set of characteristic points determine the face deflection angle of the facial image less than predetermined angle threshold value, in reference number According to acquisition and the matched registered images of the set of characteristic points are concentrated, target image set is obtained；
It calculates the facial image and the target image concentrates the similarity of registered images；
If similarity is greater than third predetermined threshold value, it is determined that the matching result of the data of the facial image and reference data concentration Meet preset condition.
8. method according to any one of claims 1 to 7, which is characterized in that the acquisition and the network environment information Before corresponding authentication mode and reference data obtaining mode, further includes:
Obtain the caloric information of the facial image；
In vivo detection is carried out to the user according to the caloric information；
It is described to obtain authentication mode corresponding with the network environment information and reference data obtaining mode, comprising: in work When body testing result indicates that the user is living body, authentication mode corresponding with the network environment information and reference are obtained Data acquisition.
9. method according to any one of claims 1 to 7, which is characterized in that further include:
Data that receiving network data library periodically issues update packet, according to the data update packet to the database of door access machine into Row updates；Alternatively,
The data in network data base are monitored according to predetermined period, when monitoring that data change, according to variation Data the database of door access machine is updated.
10. a kind of authentication means characterized by comprising
Acquisition module, in the authentication request for detecting user, acquiring network environment information and the user of door access machine Facial image；
Module is obtained, for obtaining authentication mode corresponding with the network environment information and reference data obtaining mode；
Read module, for according to the reference data obtaining mode, reading data from the database of door access machine as reference Data set；
Matching module, the data progress for being concentrated according to the authentication mode to the facial image and reference data Match；
Determining module when the matching result for obtaining in matching module meets preset condition, determines that the identity of the user is tested Card passes through, and access control machine allows user current.
11. a kind of terminal, which is characterized in that including processor and memory, in the memory storage by least one instruction, At least a Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, code set or instruction set are by institute Processor is stated to load and execute to realize auth method as described in any one of claim 1 to 9.
12. a kind of storage medium, which is characterized in that the storage medium is stored with a plurality of instruction, and described instruction is suitable for processor It is loaded, the step in 1 to 9 described in any item authentications is required with perform claim.
CN201910557166.6A 2019-06-25 2019-06-25 Identity authentication method, device, terminal and storage medium Active CN110335386B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910557166.6A CN110335386B (en) 2019-06-25 2019-06-25 Identity authentication method, device, terminal and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910557166.6A CN110335386B (en) 2019-06-25 2019-06-25 Identity authentication method, device, terminal and storage medium

Publications (2)

Publication Number Publication Date
CN110335386A true CN110335386A (en) 2019-10-15
CN110335386B CN110335386B (en) 2021-08-03

Family

ID=68142738

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910557166.6A Active CN110335386B (en) 2019-06-25 2019-06-25 Identity authentication method, device, terminal and storage medium

Country Status (1)

Country Link
CN (1) CN110335386B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992554A (en) * 2019-12-10 2020-04-10 温州市美拉五金有限公司 Enterprise access control management method, device, equipment and medium
CN111540105A (en) * 2020-04-09 2020-08-14 北京捷通华声科技股份有限公司 Method, system, equipment and storage medium for controlling access control
CN112749413A (en) * 2020-08-03 2021-05-04 德能森智能科技（成都）有限公司 Authority verification device and method based on intelligent park management
CN115147964A (en) * 2022-06-29 2022-10-04 中铁第四勘察设计院集团有限公司 Multi-information security inspection method and system, computer equipment and readable medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102857637A (en) * 2012-09-03 2013-01-02 北京小米科技有限责任公司 Acquisition method, acquisition system and acquisition device for information of contact person
CN103856568A (en) * 2014-03-25 2014-06-11 深圳市中兴移动通信有限公司 Terminal and system for prompting safety state of user terminal and implementation method
CN104639651A (en) * 2015-03-04 2015-05-20 成都维远艾珏信息技术有限公司 Mobile equipment information transmission method
EP2889812A1 (en) * 2013-12-24 2015-07-01 Pathway IP SARL Room access control system
CN105005779A (en) * 2015-08-25 2015-10-28 湖北文理学院 Face verification anti-counterfeit recognition method and system thereof based on interactive action
CN105338093A (en) * 2015-11-16 2016-02-17 中国建设银行股份有限公司 Data synchronizing method and system
CN106650671A (en) * 2016-12-27 2017-05-10 深圳英飞拓科技股份有限公司 Human face identification method, apparatus and system
CN107292283A (en) * 2017-07-12 2017-10-24 深圳奥比中光科技有限公司 Mix face identification method
CN107735817A (en) * 2015-06-15 2018-02-23 亚萨合莱有限公司 Voucher buffer
CN107944380A (en) * 2017-11-20 2018-04-20 腾讯科技（深圳）有限公司 Personal identification method, device and storage device
CN108038163A (en) * 2017-12-06 2018-05-15 交控科技股份有限公司 Standby control center database synchronous system
CN108629280A (en) * 2018-03-27 2018-10-09 维沃移动通信有限公司 Face identification method and mobile terminal
CN108961520A (en) * 2018-09-21 2018-12-07 深圳市九洲电器有限公司 A kind of face identification method and device

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102857637A (en) * 2012-09-03 2013-01-02 北京小米科技有限责任公司 Acquisition method, acquisition system and acquisition device for information of contact person
EP2889812A1 (en) * 2013-12-24 2015-07-01 Pathway IP SARL Room access control system
CN103856568A (en) * 2014-03-25 2014-06-11 深圳市中兴移动通信有限公司 Terminal and system for prompting safety state of user terminal and implementation method
CN104639651A (en) * 2015-03-04 2015-05-20 成都维远艾珏信息技术有限公司 Mobile equipment information transmission method
CN107735817A (en) * 2015-06-15 2018-02-23 亚萨合莱有限公司 Voucher buffer
CN105005779A (en) * 2015-08-25 2015-10-28 湖北文理学院 Face verification anti-counterfeit recognition method and system thereof based on interactive action
CN105338093A (en) * 2015-11-16 2016-02-17 中国建设银行股份有限公司 Data synchronizing method and system
CN106650671A (en) * 2016-12-27 2017-05-10 深圳英飞拓科技股份有限公司 Human face identification method, apparatus and system
CN107292283A (en) * 2017-07-12 2017-10-24 深圳奥比中光科技有限公司 Mix face identification method
CN107944380A (en) * 2017-11-20 2018-04-20 腾讯科技（深圳）有限公司 Personal identification method, device and storage device
CN108038163A (en) * 2017-12-06 2018-05-15 交控科技股份有限公司 Standby control center database synchronous system
CN108629280A (en) * 2018-03-27 2018-10-09 维沃移动通信有限公司 Face identification method and mobile terminal
CN108961520A (en) * 2018-09-21 2018-12-07 深圳市九洲电器有限公司 A kind of face identification method and device

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992554A (en) * 2019-12-10 2020-04-10 温州市美拉五金有限公司 Enterprise access control management method, device, equipment and medium
CN111540105A (en) * 2020-04-09 2020-08-14 北京捷通华声科技股份有限公司 Method, system, equipment and storage medium for controlling access control
CN112749413A (en) * 2020-08-03 2021-05-04 德能森智能科技（成都）有限公司 Authority verification device and method based on intelligent park management
CN112749413B (en) * 2020-08-03 2023-03-31 德能森智能科技（成都）有限公司 Authority verification device and method based on intelligent park management
CN115147964A (en) * 2022-06-29 2022-10-04 中铁第四勘察设计院集团有限公司 Multi-information security inspection method and system, computer equipment and readable medium
CN115147964B (en) * 2022-06-29 2023-09-26 中铁第四勘察设计院集团有限公司 Multi-element information security inspection method, system, computer equipment and readable medium

Also Published As

Publication number Publication date
CN110335386B (en) 2021-08-03

Similar Documents

Publication Publication Date Title
CN106778585B (en) A kind of face key point-tracking method and device
CN110335386A (en) A kind of auth method, device, terminal and storage medium
CN107992728B (en) Face verification method and device
CN107944380A (en) Personal identification method, device and storage device
CN105956518A (en) Face identification method, device and system
CN108304758A (en) Facial features tracking method and device
CN108108649B (en) Identity verification method and device
CN104143078A (en) Living body face recognition method and device and equipment
CN105847325B (en) The adjustment method and device of applications client
CN105162591B (en) Equipment login method and device
US9940448B2 (en) Unlock processing method and device
CN109165606A (en) A kind of acquisition methods of information of vehicles, device and storage medium
CN111917918B (en) Augmented reality-based event reminder management method and device and storage medium
CN106533917B (en) Relation chain processing method, apparatus and system
CN109451130B (en) Mobile terminal testing method and device, mobile terminal and storage medium
CN104573437B (en) Information authentication method, device and terminal
CN108540482A (en) Account number analysis system, method and device
CN103530624B (en) Information generating method, device and terminal equipment
CN109857297A (en) Information processing method and terminal device
CN109901761A (en) A kind of content display method and mobile terminal
CN105490992B (en) A kind of verification method of two dimensional code, device and system
CN108492837A (en) Detection method, device and the storage medium of audio burst white noise
CN112818733A (en) Information processing method, device, storage medium and terminal
CN110069407A (en) A kind of function test method and device of application program
CN108984231A (en) A kind of login method and mobile terminal of application program account

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant