CN106997465A - Multi-functional dynamic and intelligent identity card identification verification method and verification machine - Google Patents

Multi-functional dynamic and intelligent identity card identification verification method and verification machine Download PDF

Info

Publication number
CN106997465A
CN106997465A CN201710228036.9A CN201710228036A CN106997465A CN 106997465 A CN106997465 A CN 106997465A CN 201710228036 A CN201710228036 A CN 201710228036A CN 106997465 A CN106997465 A CN 106997465A
Authority
CN
China
Prior art keywords
portrait
photograph
identity card
people
certified
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.)
Pending
Application number
CN201710228036.9A
Other languages
Chinese (zh)
Inventor
吴建忠
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.)
Guangdong Golden Hang Polytron Technologies Inc
Original Assignee
Guangdong Golden Hang Polytron Technologies Inc
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 Guangdong Golden Hang Polytron Technologies Inc filed Critical Guangdong Golden Hang Polytron Technologies Inc
Priority to CN201710228036.9A priority Critical patent/CN106997465A/en
Publication of CN106997465A publication Critical patent/CN106997465A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses a kind of multi-functional dynamic and intelligent identity card identification verification method and verification machine, on the one hand, the invention provides a kind of multi-functional dynamic and intelligent identity card identification verification method, the perfect instrument that people is certified by reading obtains and is certified the essential information and source photograph of people, and gathers and be certified the image of people and set up transient target portrait storehouse;This method also includes following process step:Step 1:The source photograph of reading is compared by dynamic and intelligent portrait algorithm with transient target portrait storehouse, and draws similarity score highest and meets the photograph of preset requirement;Step 2:The comparison result of display source photograph and similarity score highest photograph, and display are certified the essential information of people;Step 3:Source photograph and transient target portrait storehouse are carried out associated and recorded and be certified the identity card phase storehouse of people.On the other hand, the invention provides a kind of multi-functional dynamic and intelligent identity card identification verification machine.The present invention can effectively improve discrimination and authentication efficiency.

Description

Multi-functional dynamic and intelligent identity card identification verification method and verification machine
Technical field
Field, more particularly to a kind of multi-functional dynamic and intelligent identity card identification checking are verified the present invention relates to identity card identification Method, further relates to a kind of multi-functional dynamic and intelligent identity card identification verification machine.
Background technology
In recent years, security protection industry has started the upsurge of a ripple Identification of Images, and numerous manufacturers are proposed Related product, made one after another Obtaining Identification of Images becomes the hot spot technology direction in industry.
Although existing portrait recognition technology function is huge, in actual applications, we, which remain unchanged, can run into many problems.Its In, influence of the portrait image quality to discrimination is higher, and poor image quality, identification is low, and validity feature seldom, is used sometimes Naked eyes also are difficult to confirm identity.Picture quality is again affected by many factors, such as illumination, posture, expression, portrait size, definition Deng.Contrasted by picture of the same person under different illumination, it is possible to find out that picture of the same person under different illumination is used Naked eyes also are difficult to distinguish.Thus, current face recognition system can only be carried out in the environment of some are compared with specification, and such as light is equal Even, portrait needs to face video camera, and guarantor in picture as there is certain pixel wide.But in actual security protection Monitor in occasion, these restrictive conditions are difficult to meet one by one.At present, the portrait verification machine clearance time needs 5-6 seconds time, big The exhibitions of flow of the people, airport, railway station, bus station carry out authentication efficiency far and do not reach actual requirement.Other portrait is calculated Method requirement is carried out in the environment of some are compared with specification, and discrimination much can not meet the market demand than relatively low.
The content of the invention
The purpose of the present invention one is to provide a kind of multi-functional dynamic and intelligent identity card identification verification method, can effectively improve Discrimination and authentication efficiency.
The purpose of the present invention two is to provide a kind of verification machine for realizing this method.
To realize the purpose one there is provided a kind of multi-functional dynamic and intelligent identity card identification verification method, this method passes through The perfect instrument that reading is certified people obtains the essential information and source photograph for being certified people, and the image of people is also certified by collection Set up transient target portrait storehouse;
This method also includes following process step:
Step 1:The source photograph of reading is compared by dynamic and intelligent portrait algorithm with transient target portrait storehouse, and Go out similarity score highest and meet the photograph of preset requirement;
Step 2:The comparison result of display source photograph and similarity score highest photograph, and display are certified the base of people This information;
Step 3:Source photograph and transient target portrait storehouse are carried out associated and recorded and be certified the identity card phase of people Storehouse.
Preferably, dynamic and intelligent portrait algorithm includes some sub-steps, and each sub-step is carried out at pictorial information simultaneously Reason, source photograph is compared with transient target portrait storehouse simultaneously for each sub-step, if can draw similarity score highest and meet The photograph of preset requirement, then remove the transient target portrait storehouse and characteristic point nullified in internal memory;If similarity can not be drawn Fraction highest and the photograph for meeting preset requirement, then supplement collection are certified the picture of people and are stored in transient target portrait storehouse, Sub-step is compared with transient target portrait storehouse again.
Preferably, in dynamic and intelligent portrait algorithm, each sub-step includes input picture step, portrait detection successively Step, characteristic extraction step, Identification of Images step and output result step.
Preferably, the input picture step is to be used as the incoming dynamic and intelligent portrait of parameter to calculate in picture in binary form In method.
Preferably, the portrait detecting step is the position that portrait is found in the picture after input picture step process Coordinate is put and then resettled, portrait is then positioned by portrait position's coordinate.
Preferably, the characteristic extraction step is, after the processing of portrait detecting step, to pass through portrait picture and portrait Position coordinates obtains the feature in the middle of the eyes and mouth and both of the portrait.
Preferably, the Identification of Images step is first registers portrait into the group specified, then by specified portrait come It is identified, identification process is as, as being compared, similarity score being obtained, if highest with the owner in group by nominator Fraction is more than the threshold value of setting, then it is assumed that recognizes successfully, and draws similarity score highest photograph, otherwise it is assumed that the portrait Not in group.
To realize purpose two there is provided a kind of multi-functional dynamic and intelligent identity card identification verification machine, including casing, in addition to Camera, the card reading unit of human image collecting rifle, processing and display unit located at cabinet sides, one and the above, the portrait Collection rifle, card reading unit and camera are connected with processing and display unit.
Preferably, the camera is two.
Compared with prior art, its advantage is the present invention:
The present invention is contrasted by quickly setting up transient target portrait storehouse with being certified the source photograph of people, can be effectively improved Discrimination and authentication efficiency.The verification machine of the present invention has recognition accuracy high simultaneously, and acquisition rate is high, to the anti-interference strong of light Ability;Personnel identity identification is carried out by the verification machine of the present invention, the accurate of the efficiency passed through and identification can be greatly lifted Degree, people's information is certified while can also be collected into.Real-time human image collecting has in the present invention is verified speed, people faster As pulldown shifts to an earlier date pre- crawl and detection, it is compared simultaneously in brush identity card so that individual compares passage time less than 1s.
Brief description of the drawings
Fig. 1 is flow chart of the invention;
Fig. 2 is the flow chart of dynamic and intelligent portrait algorithm in the present invention;
Fig. 3 is the structural representation of verification machine in the present invention.
Embodiment
With reference to embodiment, the invention will be further described, but does not constitute any limitation of the invention, any The modification of the limited number of time made in scope of the invention as claimed, still in scope of the presently claimed invention.
As shown in figure 1, the invention provides a kind of multi-functional dynamic and intelligent identity card identification verification method, by reading quilt The perfect instrument of certification people obtains the essential information and source photograph for being certified people, and collection is certified the image foundation of people temporarily Target person is as storehouse;This method also includes following process step:
Step 1:The source photograph of reading is compared by dynamic and intelligent portrait algorithm with transient target portrait storehouse, and Go out similarity score highest and meet the photograph of preset requirement;
Step 2:The comparison result of display source photograph and similarity score highest photograph, and display are certified the base of people This information;
Step 3:Source photograph and transient target portrait storehouse are carried out associated and recorded and be certified the identity card phase of people Storehouse.
In the present embodiment, being certified the perfect instrument of people includes identity card chip card;Essential information includes name, property Not, the relevant personal information such as certificate number, nationality and photograph.It is to be certified in people's identity card phase storehouse to be certified the source photograph of people Photograph.In step 1, meet preset requirement to meet effective portrait standard.In step 2, while showing source photograph, similarity Fraction highest and both comparison results, and, it is certified the essential information of people.In step 3, by source photograph and transient target Portrait storehouse carry out it is associated and recorded be certified the identity card phase storehouse of people after can enrich the effective comparison for being certified people Image library, provide more comparison chart pictures for certification next time so that certification speed faster.
In step 1, dynamic and intelligent portrait algorithm includes some sub-steps, and each sub-step carries out pictorial information simultaneously Processing, source photograph is compared with transient target portrait storehouse simultaneously for each sub-step, if similarity score highest and symbol can be drawn The photograph of preset requirement is closed, then removes the transient target portrait storehouse and characteristic point is nullified in internal memory;If can not draw similar Degree fraction highest and the photograph for meeting preset requirement, then supplement collection are certified the picture of people and are stored in transient target portrait Storehouse, sub-step is compared with transient target portrait storehouse again.
In the present embodiment, processing speed can effectively be improved by the processing of progress simultaneously of some sub-steps.Temporarily Target person is to be certified the portrait storehouse that people sets up in certification advance Mobile state human image collecting as storehouse, and wherein portrait storehouse can include Source photograph, is compared, draws phase by the transient target portrait storehouse of different people with transient target portrait storehouse simultaneously in each sub-step After degree fraction highest photograph, then it will be certified the corresponding transient target portrait storehouse of people and removed from portrait storehouse.
As shown in Fig. 2 in dynamic and intelligent portrait algorithm, each sub-step includes input picture step, portrait detection successively Step, characteristic extraction step, Identification of Images step and the several steps of output result step.It is with binary system shape to input picture step Formula is using picture as in the incoming dynamic and intelligent portrait algorithm of parameter.Portrait detecting step is after input picture step process Picture in find portrait position then resettle coordinate, portrait is then positioned by portrait position's coordinate.Feature extraction Step is, after the processing of portrait detecting step, the eyes and mouth of the portrait to be obtained by portrait picture and portrait position's coordinate And the feature in the middle of both.Identification of Images step for first portrait is registered into the group specified, then by specified portrait come It is identified, identification process is as, as being compared, similarity score being obtained, if highest with the owner in group by nominator Fraction is more than the 90% of setting, then it is assumed that recognizes successfully, and draws similarity score highest photograph, otherwise it is assumed that the portrait Not in group.
In addition, similarity score setting or 80% or 85% or 95%.
In the present embodiment, portrait position's coordinate is to be built according to the position of portrait eyes in the picture in portrait detecting step Vertical coordinate.In characteristic extraction step, the feature extracted includes nose for the feature in the middle of the eyes and mouth and both of portrait With the feature of face, and some characteristic points are obtained, then set up the coordinate of each characteristic point, e.g., nose or a mole on the face, Then using the mole is as a characteristic point and sets up coordinate.Effective portrait is carried out according to effective portrait standard to be judged as to see double On the premise of eyes, the angle that definition size and portrait are captured is obtained according to picture pixels, such as the angle of eyes can be being seen In the range of, effective portrait judgement is carried out to picture.
In the present embodiment, dynamic and intelligent portrait algorithm is different from existing static person as algorithm, and static person will as algorithm Ask picture limpider, light can not be excessive than more uniform, angle.The dynamic and intelligent portrait algorithm of the present invention, which has, focuses on big rule Mould dynamic Identification of Images, the analysis of large-scale crowd behavioural characteristic and early warning, vehicle attribute analysis are retrieved, and the core such as image retrieval is closed Key technology.The present invention proposes double-deck isomery deep neural network theoretical frame, and under this framework, research nonlinear images are empty Between mapping method, by the adaptive fusion of many deep neural networks, same figure will be mapped to across scene, non-homogeneous portrait image Image space;Research level feature learning method, to extract many portrait areas, the stratification feature with identification;Research is non- Linear character space mapping method, by the smaller space of difference in Feature Mapping to class inherited bigger, class.In real scene prison On control video test prove the algorithm of the present invention to changeable illumination, multi-angle, block, obscure, the complex situations such as age range With good robustness.So that the dynamic and intelligent portrait algorithm of the present invention can greatly reduce to environmental requirement, simultaneously Can individual machine to multiple portrait algorithm services carry out computing, greatly improve verification efficiency.
As shown in figure 3, present invention also offers a kind of multi-functional dynamic and intelligent identity card identification verification machine, including casing 1, It is characterized in that:Also include human image collecting rifle 2, processing and display unit 3 located at the side of casing 1, the shooting of one and the above First 4, card reading unit 5, human image collecting rifle 2, card reading unit 5 and camera 4 are connected with processing and display unit 3.
Camera 4 is two.In addition, camera 4 can also be one or three.
In the present embodiment, verification machine of the invention has broken tradition 1:1 portrait Validation Mode, high speed human image collecting rifle 2 Terminal machine hardware requirement is substantially reduced, while also providing portrait data output for the collection of Identification of Images various dimensions.Camera 4 is solved Certainly in portrait filling mining function, dual camera provides double shield for verification machine.Processing and display unit 3 are computer.
The course of work of the present invention:When carrying out portrait certification, people is certified before brush identity card, verification machine passes through portrait 2 pairs of rifle of collection is certified people and carries out IMAQ, is set up in processing and display unit 3 and sets up transient target portrait storehouse, handles And in display unit 3 some sub-steps are set up by dynamic and intelligent portrait algorithm at the same be certified the source photograph of people with it is interim Target person draws similarity score highest photograph as the comparison in storehouse, if can not draw, camera 4 is opened to being certified people Carry out IMAQ and the image collected being saved in into transient target portrait storehouse, then be compared, reach and set until drawing Determine the photograph of similarity score;Remove the transient target portrait storehouse and characteristic point is nullified in internal memory;By handling and showing Show that unit 3 shows source photograph, similarity score highest photograph and comparison result and the essential information for being certified people;The present invention Also source photograph and similarity score highest photograph are carried out associated and recorded and be certified the identity card phase storehouse of people.
Discrimination and authentication efficiency can be effectively improved by the present invention.The present invention has recognition accuracy high, and acquisition rate is high, To the anti-interference strong ability of light;Personnel identity identification is carried out by the verification machine of the present invention, the effect passed through can be greatly lifted Rate and the degree of accuracy of identification, people's information is certified while can also be collected into.
It the above is only the preferred embodiment of the present invention, it should be pointed out that for those skilled in the art, do not taking off On the premise of from structure of the present invention, several modifications and improvements can also be made, these effects implemented all without the influence present invention And practical applicability.

Claims (9)

1. a kind of multi-functional dynamic and intelligent identity card identification verification method, it is characterised in that this method is certified people by reading Perfect instrument obtain and be certified the essential information and source photograph of people, the image for being also certified people by collection sets up transient target Portrait storehouse;
This method also includes following process step:
Step 1:The source photograph of reading is compared by dynamic and intelligent portrait algorithm with transient target portrait storehouse, drawn similar Degree fraction highest and the photograph for meeting preset requirement;
Step 2:The comparison result of display source photograph and similarity score highest photograph, and display are certified the basic letter of people Breath;
Step 3:Source photograph and transient target portrait storehouse are carried out associated and recorded and be certified the identity card phase storehouse of people.
2. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 1, it is characterised in that:
In step 1, dynamic and intelligent portrait algorithm includes some sub-steps, and each sub-step is carried out at pictorial information simultaneously Reason, source photograph is compared with transient target portrait storehouse simultaneously for each sub-step, if can draw similarity score highest and meet The photograph of preset requirement, then remove the transient target portrait storehouse and characteristic point nullified in internal memory;If similarity can not be drawn Fraction highest and the photograph for meeting preset requirement, then supplement collection are certified the picture of people and are stored in transient target portrait storehouse, Sub-step is compared with transient target portrait storehouse again.
3. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 2, it is characterised in that:Dynamic In state intelligence portrait algorithm, each sub-step include successively input picture step, portrait detecting step, characteristic extraction step, Identification of Images step and output result step.
4. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 3, it is characterised in that:It is described Picture step is inputted in binary form using picture as in the incoming dynamic and intelligent portrait algorithm of parameter.
5. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 3, it is characterised in that:It is described Portrait detecting step is that the position of portrait is found in the picture after input picture step process and then coordinate is resettled, so Portrait is positioned by portrait position's coordinate afterwards.
6. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 3 or 5, it is characterised in that: The characteristic extraction step is, after the processing of portrait detecting step, the people to be obtained by portrait picture and portrait position's coordinate Feature in the middle of the eyes and mouth and both of picture.
7. a kind of multi-functional dynamic and intelligent identity card identification verification method according to claim 3, it is characterised in that:It is described Then Identification of Images step is identified, identification process is first to register portrait into the group specified by specified portrait By nominator as, as being compared, obtaining similarity score with the owner in group, if highest score is more than the threshold value of setting, Then think to recognize successfully, and draw similarity score highest photograph, otherwise it is assumed that the portrait is not in group.
8. a kind of multi-functional dynamic and intelligent identity card identification verification machine according to any one of claim 1 to 7 methods described, including Casing (1), it is characterised in that:Also include the human image collecting rifle (2) located at casing (1) side, handle and display unit (3), one Individual and the above camera (4), card reading unit (5), the human image collecting rifle (2), card reading unit (5) and camera (4) with Processing and display unit (3) connection.
9. a kind of multi-functional dynamic and intelligent identity card identification verification machine according to claim 8, it is characterised in that:It is described to take the photograph As head (4) is two.
CN201710228036.9A 2017-04-10 2017-04-10 Multi-functional dynamic and intelligent identity card identification verification method and verification machine Pending CN106997465A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710228036.9A CN106997465A (en) 2017-04-10 2017-04-10 Multi-functional dynamic and intelligent identity card identification verification method and verification machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710228036.9A CN106997465A (en) 2017-04-10 2017-04-10 Multi-functional dynamic and intelligent identity card identification verification method and verification machine

Publications (1)

Publication Number Publication Date
CN106997465A true CN106997465A (en) 2017-08-01

Family

ID=59434297

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710228036.9A Pending CN106997465A (en) 2017-04-10 2017-04-10 Multi-functional dynamic and intelligent identity card identification verification method and verification machine

Country Status (1)

Country Link
CN (1) CN106997465A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2540519A1 (en) * 2011-06-27 2013-01-02 Oberthur Technologies A data carrier and a method of personalizing a data carrier
CN103971043A (en) * 2014-05-28 2014-08-06 李雪 Identity authentication method and authentication information acquisition method
CN104240349A (en) * 2014-09-12 2014-12-24 宝鸡市交通信息工程研究所 Method for quickly confirming real name identity in important place and human image and identity comparison safety inspection system
CN104965235A (en) * 2015-06-12 2015-10-07 同方威视技术股份有限公司 Security check system and method
CN105631430A (en) * 2015-12-30 2016-06-01 浙江宇视科技有限公司 Matching method and apparatus for face image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2540519A1 (en) * 2011-06-27 2013-01-02 Oberthur Technologies A data carrier and a method of personalizing a data carrier
CN103971043A (en) * 2014-05-28 2014-08-06 李雪 Identity authentication method and authentication information acquisition method
CN104240349A (en) * 2014-09-12 2014-12-24 宝鸡市交通信息工程研究所 Method for quickly confirming real name identity in important place and human image and identity comparison safety inspection system
CN104965235A (en) * 2015-06-12 2015-10-07 同方威视技术股份有限公司 Security check system and method
CN105631430A (en) * 2015-12-30 2016-06-01 浙江宇视科技有限公司 Matching method and apparatus for face image

Similar Documents

Publication Publication Date Title
CN109858371B (en) Face recognition method and device
CN109697416B (en) Video data processing method and related device
US10650261B2 (en) System and method for identifying re-photographed images
CN104933414B (en) A kind of living body faces detection method based on WLD-TOP
WO2021139324A1 (en) Image recognition method and apparatus, computer-readable storage medium and electronic device
CN103914686B (en) A kind of face alignment authentication method and system shone based on certificate photo with collection
KR101781358B1 (en) Personal Identification System And Method By Face Recognition In Digital Image
Deb et al. Look locally infer globally: A generalizable face anti-spoofing approach
CN107169458B (en) Data processing method, device and storage medium
CN111241975B (en) Face recognition detection method and system based on mobile terminal edge calculation
CN106056083B (en) A kind of information processing method and terminal
Wang et al. A benchmark for clothes variation in person re‐identification
CN108108711B (en) Face control method, electronic device and storage medium
Smith-Creasey et al. Continuous face authentication scheme for mobile devices with tracking and liveness detection
WO2021082692A1 (en) Pedestrian picture labeling method and device, storage medium, and intelligent apparatus
CN112364827A (en) Face recognition method and device, computer equipment and storage medium
Ayyappan et al. Criminals and missing children identification using face recognition and web scrapping
CN109657627A (en) Auth method, device and electronic equipment
Lin et al. Convolutional neural networks for face anti-spoofing and liveness detection
CN114218543A (en) Encryption and unlocking system and method based on multi-scene expression recognition
CN112560683A (en) Method and device for identifying copied image, computer equipment and storage medium
CN114861241A (en) Anti-peeping screen method based on intelligent detection and related equipment thereof
CN106980818B (en) Personalized preprocessing method, system and terminal for face image
CN111091089B (en) Face image processing method and device, electronic equipment and storage medium
Ma et al. Multi-perspective dynamic features for cross-database face presentation attack detection

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20170801

RJ01 Rejection of invention patent application after publication