CN202815870U - Certificate photograph and face automatic identification system - Google Patents
Certificate photograph and face automatic identification system Download PDFInfo
- Publication number
- CN202815870U CN202815870U CN 201220488096 CN201220488096U CN202815870U CN 202815870 U CN202815870 U CN 202815870U CN 201220488096 CN201220488096 CN 201220488096 CN 201220488096 U CN201220488096 U CN 201220488096U CN 202815870 U CN202815870 U CN 202815870U
- Authority
- CN
- China
- Prior art keywords
- face
- people
- subsystem
- information
- certificate photograph
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The utility model provides a certificate photograph and face automatic identification system which includes an information acquisition subsystem and a data analysis subsystem. The data analysis subsystem is provided with a face verification module which is composed of a local characteristic judgment unit and an overall characteristic judgment unit which are connected in order. The local characteristic judgment unit compares the acquired face information with a certificate photograph on the aspect of the local characteristic, and the overall characteristic judgment unit compares the acquired face information with the certificate photograph information on the aspect of the overall characteristic, when both of the local characteristic judgment unit and the overall characteristic judgment unit consider that the face accords with the photograph, the system can finally make the result that the face accords with the certificate photograph. The certificate photograph and face automatic identification system can effectively prevent a person to illegally using or borrowing other people's certificate and solve the trouble that a worker has to carry out the repeated naked eye comparison to a certificate holder, so the working efficiency of a real name system is improved.
Description
Technical field
The utility model belongs to the recognition of face field, the system that particularly directly certificate photograph and people's face is identified automatically.
Background technology
Existing face identification method, particularly some business softwares, very high to the sharpness requirement of a human face photo of identifying, comparing, the distance between two is greater than 80 pixels in the human face photo such as requiring.And because storage space limitations, the photo sharpness that generally is stored on the I.D. rfid card is relatively poor, and the distance in the human face photo between two is only about 20 pixels.Therefore, existing face identification method can not directly be compared with the on-the-spot human face photo of capturing to the high compression photo that is stored on the I.D. rfid card.Its solution is and public security bureau's I.D. central database networking, obtain and download the original photo of this I.D. in data center of the Ministry of Public Security by ID (identity number) card No., recycle some commercial recognition of face softwares, original photo and the on-the-spot human face photo of capturing of I.D. are compared.Owing to must network with I.D. data center of the Ministry of Public Security, so its range of application is subject to great restriction, and the collection site light condition is required high.
The utility model content
The utility model provides a kind of certificate photograph and automatic human face recognition system, can simply, effectively solve photo and compare problem with the on-the-spot human face photo of capturing.
The utility model comprises following technical characterictic:
A kind of certificate photograph and automatic human face recognition system comprise information acquisition subsystem and data analytics subsystem, and described information acquisition subsystem comprises: camera head, identification card and plug-in reader; Described identification card and plug-in reader coupling, identification card includes the RFID electronic tag for the storage certificate photo; The certificate photograph that people's face information that camera head gathers and plug-in reader gather is the input data analysis subsystem respectively; Described data analytics subsystem comprises: people's face authentication module, and this module is comprised of the local feature judging unit that is linked in sequence and global feature judging unit; The face identification unit of described local feature judging unit for based on local binary people's face information and the certificate photograph of collection being compared at local feature; The face identification unit of described global feature judging unit for based on eigenface people's face information and the certificate photograph information of collection being compared at global feature.
Recognition system of the present utility model is with the certificate photograph and the people's face information input data analyzing subsystem that gather, successively judge respectively by local feature judging unit and global feature judging unit, only have when local feature judging unit is all thought situation about conforming to the global feature judging unit under, just export the recognition result that people's face conforms to certificate photograph.Local feature judging unit and global feature judging unit are to utilize local binary method (LBP) and utilize eigenface method (PCA) to realize recognition of face; these two kinds of methods all are existing algorithms; it or not the claimed improvement of the utility model; improvement of the present utility model is to select this two unit; and utilize the sequencing of these two unit to connect; people's face local feature is judged and global feature is judged successively to carry out; the annexation of this module can directly compare the certificate photograph of storing in the identification card and people's face of taking in real time; provide powerful technical support for implementing " system of real name " system; save the staff certificate and holder are carried out naked eyes repeatedly than reciprocity link, increase work efficiency.
Further, the utility model is especially for the small photo of high compression, such as the certificate photograph of storing among the I.D. RFID, and in the photo two eye distances of people's face from the certificate photograph about 20 pixels.
So identification card can be Chinese second generation identity card, plug-in reader can be card reader of ID card.Certainly, identification card can for two eye distances of the certificate photograph of the identification card of any existing internal memory certificate photograph, particularly internal memory when being the 15-25 pixel.Yet the size of photo pixel does not consist of the restriction of the utility model protection domain; can not be interpreted as that the utility model can only be applied to the identification of small pixel photo; and be construed as under the situation of small pixel photo array, the utility model still can obtain higher discrimination.Why in small pixel photo occasion, still can keep higher discrimination, be because the utility model has merged whole (PCA) recognition methods and part (LBP) recognition methods, by local feature judging unit and global feature judging unit optimization realization.
Further, described data analytics subsystem also comprises the people's face detection module before people's face authentication module, and this people's face detection module is used for extracting people's face feature.Described people's face detection module is based on Face Detection and determines human face region, and extracts the detection module of people's facial feature points by class Haar feature and Adaboost algorithm.Described data analytics subsystem also comprises the picture processing module for gray-scale map conversion, image normalization and illumination equilibrium treatment.Face detection module and picture processing module can Effective Raise recognition efficiency and recognition success rates.
Further, connect the above data analytics subsystem at hardware and be located at host computer, camera head is connected with host computer, and plug-in reader is connected with the host computer serial mode.
Further, this system also comprises storage subsystem and monitoring management subsystem, described storage subsystem comprises face template training storehouse and recognition result thesaurus, described face template training storehouse is by local feature judging unit and the access of global feature judging unit, and described recognition result thesaurus is accessed by the monitoring management subsystem.Described monitoring management subsystem is by inquiry mode access recognition result thesaurus.Described information acquisition subsystem gathers people's face information from the video image of camera.
Above face template training storehouse is used for guaranteeing that identifying calls the face characteristic that face template training storehouse includes people's face original image and extracts from the original image training to people's face data.The recognition result database, other data and other information that are used for storage in the record identification card, ID such as the people, name, photo, charge time, whether can be identified as I etc. information, certificate photograph is preserved with JEPG or PNG fileinfo, identify management if particularly this system is used for the gate inhibition, then recognition result can be used as gate inhibition's record and is stored.Native system also comprises the monitoring management subsystem, by the monitoring management subsystem recognition result thesaurus is accessed, can inquire different information, as according to time inquiring, the identity identification information in the special time period can be inquired, according to the ID inquiry, all identifying informations corresponding to specific user ID can be inquired, also can according to the record content search, can check all recognition system records.
Further, described information acquisition subsystem is used for gathering people's face information from video file, and this is conducive to gather identification in the occasion of the monitoring of maintaining secrecy in the mode of secret monitoring.
Description of drawings
Fig. 1 is hardware connection layout of the present utility model;
Fig. 2 is the utility model internal module connection layout.
Embodiment
Below with reference to Figure of description 1-2, embodiment of the present utility model is explained.
As shown in Figure 1, comprise camera head 1, identification card 2 and plug-in reader 3 on the utility model hardware; Described identification card 2 and plug-in reader 3 couplings, identification card 2 includes the RFID electronic tag for the storage certificate photo; The certificate photograph that people's face information that camera head 1 gathers and plug-in reader 3 gather, respectively input data analysis subsystem 4.Data analytics subsystem 4 is located at host computer, and camera head 1 is connected with host computer, and plug-in reader 3 is connected with the host computer serial ports.
The control section of whole utility model comprises input data analysis subsystem 4, storage subsystem 5 and monitoring management subsystem 6.
Picture processing module 41, people's face detection module 42 and people's face authentication module 43 are drawn together in data analysis and identification that input data analysis subsystem 4 is used for input.Described picture processing module 41 is used for gray-scale map conversion, image normalization and illumination equilibrium treatment.People's face detection module 42 skin color baseds detect determines human face region, and extracts people's facial feature points by class Haar feature and Adaboost algorithm.People's face authentication module 43 is comprised of the local feature judging unit 43a that is linked in sequence and global feature judging unit 43b; Local feature judging unit 43a is used for the people's face information and the certificate photograph that gather are compared at local feature, and global feature judging unit 43b is used for the people's face information and the certificate photograph information that gather are compared at global feature; Under local feature judging unit 43a and global feature judging unit 43b all think situation about conforming to, the recognition result that system's output people face conforms to certificate photograph.
Described storage subsystem 5 comprises face template training storehouse 51 and recognition result thesaurus 52, described face template training storehouse 51 is by local feature judging unit 43a and global feature judging unit 43b access, and described recognition result thesaurus 52 is by 6 access of monitoring management subsystem.
Described monitoring management subsystem 6 is by inquiry mode access recognition result thesaurus 52.
The utility model can be converted into gray level image with people's face that capture at the scene, carries out normalization and illumination equilibrium treatment; People's face detects the image that the RFID data are processed and does Face Detection, utilizes the Adaboost algorithm to get rid of unnecessary training data, and key point is placed on the important training data; The checking of people's face utilizes based on dual mode (LBP) method extracts face characteristic, recycles based on eigenface (PCA) method realization recognition of face, and finally reaches China second-generation identity card RFID photo and the automatic effect of identifying of the on-the-spot people of candid photograph face.
In an embodiment who specifically is applied to examinee's identification, whole system comprises camera, identification card and RFID plug-in reader three parts.Wherein, camera is used for the collection of video image, and video stream data is sent to the computing machine that data are processed; Identification card includes the identity informations such as licensee's name, photo, but identification be stuck in the RFID plug-in reader Read Range, will include data and send to the RFID plug-in reader; The RFID plug-in reader links to each other by serial ports with computing machine, after receiving RFID electronic tag inner storag information, information is sent to computing machine.
Input data analysis subsystem 4 is cores of the present utility model, relate to the information processing in the RFID identification card, the detection of front face position in the video image, the extraction of face characteristic, the synchronous and mutual exclusion control between the checking of people's face and each functional module.
Storage subsystem 5 comprises people's face module database, gate inhibition's database of record and forwarding server.People's face module database comprises people's face original image, and trains the face characteristic that extracts from original image; Holder ID in the gate inhibition's database of record intelligent identity identification system record rfid card, name, photo, charge time, whether by gate control system etc.; Forwarding server is responsible for the information transmission between monitor message and mobile phone.Be responsible for to take the view data of holding and be forwarded to corresponding mobile phone terminal.
Monitoring management subsystem 6 and storage subsystem 5 link to each other by database.The querying condition of system's support has according to time inquiring, according to the ID inquiry with according to the record content search.
Claims (10)
1. a certificate photograph and automatic human face recognition system comprise information acquisition subsystem and data analytics subsystem, it is characterized in that:
Described information acquisition subsystem comprises:
Camera head, identification card and plug-in reader; Described identification card and plug-in reader coupling, identification card includes the RFID electronic tag for the storage certificate photo; The certificate photograph that people's face information that camera head gathers and plug-in reader gather is the input data analysis subsystem respectively;
Described data analytics subsystem comprises:
People's face authentication module, this module is comprised of the local feature judging unit that is linked in sequence and global feature judging unit; The face identification unit of described local feature judging unit for based on local binary people's face information and the certificate photograph of collection being compared at local feature; The face identification unit of described global feature judging unit for based on eigenface people's face information and the certificate photograph information of collection being compared at global feature.
2. automatic recognition system according to claim 1 is characterized in that, described identification card is Chinese second generation identity card, and plug-in reader is card reader of ID card.
3. automatic recognition system according to claim 1 is characterized in that, described identification card internal memory two eye distances are from the certificate photograph that is the 15-25 pixel.
4. automatic recognition system according to claim 1 is characterized in that, described data analytics subsystem also comprises the people's face detection module before people's face authentication module.
5. automatic recognition system according to claim 4 is characterized in that, described people's face detection module is based on Face Detection and determines human face region, and extracts the detection module of people's facial feature points by class Haar feature and Adaboost algorithm.
6. automatic recognition system according to claim 5 is characterized in that, described data analytics subsystem also comprises the picture processing module for gray-scale map conversion, image normalization and illumination equilibrium treatment.
7. according to claim 1 to 6 each described automatic recognition systems, described data analytics subsystem is located at host computer, and camera head is connected with host computer, and plug-in reader is connected with the host computer serial mode.
8. automatic recognition system according to claim 1, it is characterized in that, also comprise storage subsystem and monitoring management subsystem, described storage subsystem comprises face template training storehouse and recognition result thesaurus, described face template training storehouse is by local feature judging unit and the access of global feature judging unit, and described recognition result thesaurus is accessed by the monitoring management subsystem.
9. automatic recognition system according to claim 8 is characterized in that, described monitoring management subsystem is by inquiry mode access recognition result thesaurus.
10. automatic recognition system according to claim 1 is characterized in that, described information acquisition subsystem is used for gathering people's face information from video file.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201220488096 CN202815870U (en) | 2012-04-28 | 2012-09-20 | Certificate photograph and face automatic identification system |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201220194230.2 | 2012-04-28 | ||
CN201220194230 | 2012-04-28 | ||
CN 201220488096 CN202815870U (en) | 2012-04-28 | 2012-09-20 | Certificate photograph and face automatic identification system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN202815870U true CN202815870U (en) | 2013-03-20 |
Family
ID=47874718
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201220488096 Expired - Fee Related CN202815870U (en) | 2012-04-28 | 2012-09-20 | Certificate photograph and face automatic identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN202815870U (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846625A (en) * | 2017-02-08 | 2017-06-13 | 艾伯资讯(深圳)有限公司 | Identity information recognition process unit |
CN109447029A (en) * | 2018-11-12 | 2019-03-08 | 公安部第三研究所 | Electronic identity license generates system and method |
CN110210424A (en) * | 2019-06-05 | 2019-09-06 | 重庆两江新区管理委员会 | A kind of worker's identity information acquisition system and method based on recognition of face |
CN111553251A (en) * | 2020-04-24 | 2020-08-18 | 平安科技(深圳)有限公司 | Certificate four-corner incomplete detection method, device, equipment and storage medium |
CN113408360A (en) * | 2021-05-25 | 2021-09-17 | 常熟市百创网络科技有限公司 | AI information identification system |
CN114120386A (en) * | 2020-08-31 | 2022-03-01 | 腾讯科技(深圳)有限公司 | Face recognition method, device, equipment and storage medium |
-
2012
- 2012-09-20 CN CN 201220488096 patent/CN202815870U/en not_active Expired - Fee Related
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846625A (en) * | 2017-02-08 | 2017-06-13 | 艾伯资讯(深圳)有限公司 | Identity information recognition process unit |
CN109447029A (en) * | 2018-11-12 | 2019-03-08 | 公安部第三研究所 | Electronic identity license generates system and method |
CN110210424A (en) * | 2019-06-05 | 2019-09-06 | 重庆两江新区管理委员会 | A kind of worker's identity information acquisition system and method based on recognition of face |
CN111553251A (en) * | 2020-04-24 | 2020-08-18 | 平安科技(深圳)有限公司 | Certificate four-corner incomplete detection method, device, equipment and storage medium |
WO2021212873A1 (en) * | 2020-04-24 | 2021-10-28 | 平安科技(深圳)有限公司 | Defect detection method and apparatus for four corners of certificate, and device and storage medium |
CN111553251B (en) * | 2020-04-24 | 2024-05-07 | 平安科技(深圳)有限公司 | Certificate four-corner defect detection method, device, equipment and storage medium |
CN114120386A (en) * | 2020-08-31 | 2022-03-01 | 腾讯科技(深圳)有限公司 | Face recognition method, device, equipment and storage medium |
CN113408360A (en) * | 2021-05-25 | 2021-09-17 | 常熟市百创网络科技有限公司 | AI information identification system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN202815870U (en) | Certificate photograph and face automatic identification system | |
CN204155327U (en) | A kind of visiting personnel based on recognition of face register checking device | |
US10943095B2 (en) | Methods and systems for matching extracted feature descriptors for enhanced face recognition | |
CN204155293U (en) | A kind of demo plant based on recognition of face and verification system | |
CN107680294A (en) | House property information querying method, system, terminal device and storage medium | |
CN102800017A (en) | Identity verification system based on face recognition | |
CN106803301A (en) | A kind of recognition of face guard method and system based on deep learning | |
CN104182671A (en) | Method and device for protecting privacy information of browser | |
CN102799821A (en) | Method for checking intelligent card and identity of card holder, and face identification identity checking device | |
CN102497531A (en) | Human face recognition wireless video monitoring system based on cloud computing platform | |
CN105427421A (en) | Entrance guard control method based on face recognition | |
CN105930709A (en) | Method and apparatus for applying human face identification technology to witness testimony consistency check | |
CN105551104A (en) | Monitoring-image-seat-discrimination-based middle and primary school classroom automatic attendance system | |
CN103914686A (en) | Face comparison authentication method and system based on identification photo and collected photo | |
CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
CN101976356A (en) | Face identification method for surfing identification policy, and identification system thereof | |
CN101751562B (en) | Bank transaction image forensic acquiring method based on face recognition | |
CN101739742A (en) | Networking type multi-channel access control and attendance system | |
CN103324911A (en) | Anti-cheating system based on face recognition | |
CN202771514U (en) | Face recognition access control attendance system | |
CN109800638A (en) | A kind of emphasis people's monitoring method based on face recognition technology | |
CN201134110Y (en) | Human face recognition system | |
CN104217503A (en) | Self-service terminal identity identification method and corresponding house property certificate printing method | |
CN202887214U (en) | Human identity recognizing device based on face recognition | |
CN104217504A (en) | Identity recognition self-service terminal and corresponding certificate of house property printing terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130320 Termination date: 20160920 |