CN202887214U - Human identity recognizing device based on face recognition - Google Patents
Human identity recognizing device based on face recognition Download PDFInfo
- Publication number
- CN202887214U CN202887214U CN 201220595895 CN201220595895U CN202887214U CN 202887214 U CN202887214 U CN 202887214U CN 201220595895 CN201220595895 CN 201220595895 CN 201220595895 U CN201220595895 U CN 201220595895U CN 202887214 U CN202887214 U CN 202887214U
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- infrared
- recognizing device
- device based
- 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
Abstract
The utility model discloses a human identity recognizing device based on face recognition and relates to a human identity recognizing device. The human identity recognizing device comprises an image acquisition system, wherein the image acquisition system comprises an infrared CCD (Charge Coupled Device) camera and an infrared initiative light source arranged beside the infrared CCD camera; a lens of the infrared CCD camera is provided with a band-pass filter; the output end of the infrared CCD camera is connected with the input end of a PCI (Peripheral Component Interconnect) image acquisition card; and the output end of the PCI image acquisition card is connected with a computer. The human identity recognizing device disclosed by the utility model has high environment applicability, can recognize people in a medium range (within 0m-5m) in all weather conditions without being influenced by gesture and illumination condition, increases the recognition rate and the application scenarios of the face recognition, and has remarkable practicability.
Description
Technical field
The utility model relates to a kind of human body identity recognition device, relates in particular to a kind of human body identity recognition device based on recognition of face.
Background technology
Identification is almost omnipresent in the human society daily life with checking, and people have a mind to or by mistake will make differentiation to the identity of surrounding population every day, or proves the identity of oneself by variety of way and means.Need swipe the card and input password, move in the hotel and need show I.D. etc. such as handle financial business at ATM.Obviously, we in most cases still depend on traditional authentication means, comprise certificate card (such as I.D., employee's card etc.), key (PIN code or personal identification number).But all there is certain drawback in these means, easily forget or are stolen by premeditated such as password: I.D. (card) carries inconvenience or is forged etc.: these shortcomings cause traditional authentication means more and more to be not suitable with the demand of information society high speed development.Especially after U.S.'s September 11 attacks, safety problem becomes the hot issue that people pay close attention to more, and people are badly in need of a kind of highly reliable, high safety and are laid flexibly novel identity identifying technology.And biometrics identification technology is considered to the ultimate settling mode of these demands.Be subject to people's favor with the advantages such as high acceptability under its natural way as the Automatic face recognition of biometrics identification technology.
In the world the research of people's face and people's face section Expression Recognition become the scientific research focus now gradually.The developed countries such as the U.S., Japan, Britain, Germany, Holland, France and developing country such as India, Singapore have the particular study group to carry out the research of this respect.Wherein the contribution of MIT, CMU, Maryland university, Standford university, the strange university in Japanese city, Tokyo University, ATR research institute is particularly outstanding.Subject matter has focused on illumination, attitude for the impact of recognition of face core algorithm performance.The representative algorithm and model that proposes has illumination cone model, 3D transform model, reaches the design that support vector machine is applied to the recognition of face sorter, has also released some Automatic face recognition business systems.The corresponding further standard of face identification system performance evaluating standard has been summed up the current situation of face recognition technology and has further been pointed out the deficiency that present face recognition algorithms exists.
A large amount of significant work have been done at the detection of people's face, people's face spatial modeling and the aspects such as feature extraction and face recognition algorithms by these seminar of research that domestic Tsing-Hua University, Harbin Institute of Technology, the Chinese Academy of Sciences, Chinese University of Science and Technology, Institutes Of Technology Of Nanjing, Northern Transportation University etc. have personnel to be engaged in people's face and human face expression identification, have also accumulated rich experience.The physiological characteristic of human body mainly comprises people's face, fingerprint, palmmprint, palm shape, iris, retina, vein, DNA, skull etc., because recognition of face is without invasive and, the most intuitively mode the most natural to the user, makes recognition of face become the easiest received living things feature recognition mode; But because face recognition technology is subjected to the impact of the conditions such as distance, attitude and illumination of people's face, the accuracy of recognition of face will be lower than the identification of iris, fingerprint, has directly affected its practicality.
The utility model content
Problem for above-mentioned prior art existence, the utility model provides a kind of human body identity recognition device based on recognition of face, strong to ambient adaptability, can realize identifications round-the-clock, middle distance (5 meters scopes are interior) personnel, be not subjected to the impact of posture, illuminating position, improve the application scenarios of discrimination and recognition of face, had good practicality.
The technical solution of the utility model is: a kind of human body identity recognition device based on recognition of face, comprise image capturing system, described image capturing system comprises infrared C CD video camera and is arranged at the other infrared ray active light source of infrared C CD camera lens, is provided with bandpass filter on the camera lens of described infrared C CD video camera; The output terminal of infrared C CD video camera is connected with the input end of PCI image pick-up card, and the output terminal of PCI image pick-up card is connected with computing machine.
As preferably, the centre wavelength of described infrared ray active light source is 940nm, and the centre wavelength of described bandpass filter is 940nm, and half-band width is 10nm.
As preferably, described computing machine comprises the Adaboost detection module that detects for people's face and the PCA identification module that is used for recognition of face.
The beneficial effects of the utility model are: the utility model is finished personnel identity identification by image capturing system, has without invasive with to user's nature, characteristics intuitively.Adopt the method for infrared ray active illumination, can effectively eliminate extraneous various light and disturb, and can obtain in medium and long distance the image of inclination.The method that the utility model adopts the Adaboost detection module to detect as people's face, in moderate distance (in 5 meters), from various visual angles, many illumination, has a good detection effect in the situations such as complex background, quick and precisely, stably follow the tracks of a plurality of people's faces, and can be at the side face, back side of head state keeps following the tracks of, and algorithm is reached advanced world standards.The interface of adopting international standards can the existing security system of seamless access; Support the multitype database system, can set up efficient index mechanism and realize fast query.The modularization networking mode, set TCP/IP and RS232 bus transfer advantage are fit to the application of various forms or scale.The logical combination computing of the technology such as support and other password/living things feature recognitions realizes stricter safety management, has good practicality.
Description of drawings
Fig. 1 is structured flowchart of the present utility model;
Fig. 2 is the process flow diagram of the utility model condition discrimination.
Embodiment
As a kind of embodiment of the present utility model, as depicted in figs. 1 and 2, a kind of human body identity recognition device based on recognition of face, comprise image capturing system, described image capturing system comprises infrared C CD video camera 1 and is arranged at the other infrared ray active light source 2 of infrared C CD video camera 1 camera lens, is provided with bandpass filter on the camera lens of described infrared C CD video camera 1; The output terminal of infrared C CD video camera is connected with the input end of PCI image pick-up card 3, and the output terminal of PCI image pick-up card 3 is connected with computing machine 4.
In the present embodiment, as preferably, the centre wavelength of described infrared ray active light source 2 is 940nm, and the centre wavelength of described bandpass filter is 940nm, and half-band width is 10nm.
In the present embodiment, as preferably, described computing machine 4 comprises the Adaboost detection module that detects for people's face and the PCA identification module that is used for recognition of face.
Principle of work of the present utility model is: the facial illumination of the 2 couples of tested personnel of infrared ray active light source, illumination intensity is regulated automatically according to the contrast of imaging, reduce ambient lighting and change the impact that causes, bandpass filter 1 filtering most of external interference light.Infrared C CD video camera 1 Real-time Collection tested personnel's face image signal, this video signal is by PCI image pick-up card 3, image is sent into computing machine 4, then process accordingly according to the function needs: begin pre-service by the identification system software that operates on the computing machine 4, carry out after people Lian Jian Ce ﹑ cuts apart, adopt the PCA identification module to carry out recognition of face, thereby realize the human body authentication.System mainly contains three major functions, is respectively: user management, identification, video management.The user management menu is used for the user in the database is managed operation.Can realize adding the functions such as user, cancellation interpolation, deletion user, user list, sample training.Identification is used for unknown images is identified, and is divided into camera identification and two parts of picture recognition.The former is by camera motion capture people face and identification, and latter is identified a width of cloth still image (supporting BMP, JPG and GIF form).Video management then is used for camera is arranged, and comprises the opening/closing camera, the parameter of camera is suitably adjusted.
System has following characteristics: image capturing system adopts the Active Imaging technology of infrared illumination, the high-quality image of round-the-clock acquisition; And adopt image pre-processing method to improve image quality.Adopt the Adaboost detection module to carry out people's face and detect, calculate simply, discrimination is high.Use the PCA identification module that the variation of the factors such as human face posture, illumination, expression, jewelry, background, time span in the image is had preferably robustness.Software system function is more comprehensive, can immediately obtain image through camera, also can identify static images.Software can be trained input picture immediately, also can directly use the sample data that trains.
Duty of the present utility model is differentiated workflow:
(1) Image Acquisition and enhancing
The facial image data source comprises motion image sequence (video flowing) and rest image.Mainly can pass through scanner, digital camera, the first-class digital input equipment of making a video recording obtains.The image pre-service: pretreated Main Function is as much as possible so that facial image is in same yardstick and standard, finally provides high-quality input picture for subsequent treatment.Usually this part need to finish the functions such as yardstick normalization to abstract image, gray scale normalization, noise reduction, the photograph that delusters, white balance.
(2) people's face detection and location: this module is used for analyzing the image of input, judges whether people's face is wherein arranged, if having, then finds out the position of people's face, and facial image is separated from background image.
At first pretreated facial image is extracted for the feature of identifying according to certain strategy, original face spatial mappings is arrived the New Characteristics space.In this step, not only pay attention to how extracting the characteristic with good separation performance, must consider that also the robustness of total algorithm and treatment effeciency etc. use index.
Then carry out the design of sorter, this process mainly generates the parameter that can be used for identifying.Usually, determine certain decision rule on existing sample training collection basis, so that maximum to being identified the classify error recognition rate minimum or the outcome expectancy that cause of object by this rule.
Carry out at last face extraction, finish classification and the differentiation of people's face by comparing the unknown human face parameter that obtains and the parameter of training gained, provide recognition result.
(3) by the recognition of face of PCA identification module
The application of complete PCA identification module comprises several steps: the facial image pre-service; Read in face database, training forms proper subspace; Training image and test pattern are projected on the subspace that obtains in the previous step; Select certain distance function to identify.
In this device, mainly in computing machine 4 operations, the main interface of function is divided into four sub-windows to the human body identity recognition function.
Form one shows for camera.After camera was opened, the user can see the picture that real-time camera photographs in this form.In addition, when people's face measuring ability was opened, the people's face that detects can dynamically be used red box indicating out.
Form two is the subscriber data district.The name of all users in the current database, sex, identity and grade all here show.The user also can add, delete the operations such as user here by right-click menu.
Form three is control panel.Be handled easily, the button of some common functions is provided here.
Form four is watched the district for user images.After the some users in the subscriber data district are double-clicked, can show the head portrait data of this user in the database here, for watching.
The above only is a kind of embodiment of the present utility model; not in order to limit the utility model; all any modifications of within spirit of the present utility model and principle, doing, be equal to and replace and obvious mode of texturing etc., all should be included within the protection domain of the present utility model.
Claims (3)
1. human body identity recognition device based on recognition of face, comprise image capturing system, it is characterized in that: described image capturing system comprises infrared C CD video camera and is arranged at the other infrared ray active light source of infrared C CD camera lens, is provided with bandpass filter on the camera lens of described infrared C CD video camera; The output terminal of infrared C CD video camera is connected with the input end of PCI image pick-up card, and the output terminal of PCI image pick-up card is connected with computing machine.
2. the human body identity recognition device based on recognition of face according to claim 1, it is characterized in that: the centre wavelength of described infrared ray active light source is 940nm, and the centre wavelength of described bandpass filter is 940nm, and half-band width is 10nm.
3. the human body identity recognition device based on recognition of face according to claim 1 and 2 is characterized in that: described computing machine comprises the Adaboost detection module that detects for people's face and the PCA identification module that is used for recognition of face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220595895 CN202887214U (en) | 2012-11-13 | 2012-11-13 | Human identity recognizing device based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220595895 CN202887214U (en) | 2012-11-13 | 2012-11-13 | Human identity recognizing device based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202887214U true CN202887214U (en) | 2013-04-17 |
Family
ID=48078618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201220595895 Expired - Fee Related CN202887214U (en) | 2012-11-13 | 2012-11-13 | Human identity recognizing device based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202887214U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646203A (en) * | 2013-12-20 | 2014-03-19 | 中晟国计科技有限公司 | Computer safety system with human body biological characteristic recognition |
| CN103927351A (en) * | 2014-04-10 | 2014-07-16 | 清华大学 | Posture correcting based fingerprint retrieval method and system |
| CN108197609A (en) * | 2018-02-02 | 2018-06-22 | 梁纳星 | A kind of accurate people face identifying system |
| CN108566777A (en) * | 2018-04-18 | 2018-09-21 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
| CN110489952A (en) * | 2014-09-30 | 2019-11-22 | 华为技术有限公司 | Identity authentication method, device and user equipment |
-
2012
- 2012-11-13 CN CN 201220595895 patent/CN202887214U/en not_active Expired - Fee Related
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646203A (en) * | 2013-12-20 | 2014-03-19 | 中晟国计科技有限公司 | Computer safety system with human body biological characteristic recognition |
| CN103927351A (en) * | 2014-04-10 | 2014-07-16 | 清华大学 | Posture correcting based fingerprint retrieval method and system |
| CN103927351B (en) * | 2014-04-10 | 2017-06-06 | 清华大学 | Fingerprint retrieval method and system based on attitude updating |
| CN110489952A (en) * | 2014-09-30 | 2019-11-22 | 华为技术有限公司 | Identity authentication method, device and user equipment |
| US11038879B2 (en) | 2014-09-30 | 2021-06-15 | Huawei Technologies Co., Ltd. | Identity authentication method and apparatus, and user equipment |
| CN108197609A (en) * | 2018-02-02 | 2018-06-22 | 梁纳星 | A kind of accurate people face identifying system |
| CN108566777A (en) * | 2018-04-18 | 2018-09-21 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Del Rio et al. | Automated border control e-gates and facial recognition systems | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| Fathy et al. | Face-based active authentication on mobile devices | |
| Derawi et al. | Fingerprint recognition with embedded cameras on mobile phones | |
| CN109086739A (en) | A kind of face identification method and system of no human face data training | |
| Tao et al. | Biometric authentication system on mobile personal devices | |
| KR100944247B1 (en) | System and method for face recognition | |
| CN202887214U (en) | Human identity recognizing device based on face recognition | |
| CN103678984A (en) | Method for achieving user authentication by utilizing camera | |
| CN105427421A (en) | Entrance guard control method based on face recognition | |
| CN101027678A (en) | Single image based multi-biometric system and method | |
| CN101404060A (en) | Human face recognition method based on visible light and near-infrared Gabor information amalgamation | |
| CN106203391A (en) | Face identification method based on intelligent glasses | |
| CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
| CN103530659A (en) | Face recognition method and attendance system combining original and symmetrical face facial images | |
| CN111259757B (en) | Living body identification method, device and equipment based on image | |
| CN202815870U (en) | Certificate photograph and face automatic identification system | |
| Wasnik et al. | Presentation attack detection for smartphone based fingerphoto recognition using second order local structures | |
| CN108648312A (en) | Recognition of face Intelligent greeting method and system | |
| Suhr et al. | Recognizability assessment of facial images for automated teller machine applications | |
| CN204143555U (en) | The Certificate of House Property printing terminal of identification self-aided terminal and correspondence | |
| Galbally et al. | Study on face identification technology for its implementation in the Schengen information system | |
| CN205644823U (en) | Social security self -service terminal device | |
| Lee et al. | Distinction Between Real Faces and Photos by Analysis of Face Data. | |
| Carney et al. | A multi-finger touchless fingerprinting system: Mobile fingerphoto and legacy database interoperability |
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 |
Granted publication date: 20130417 Termination date: 20141113 |
|
| EXPY | Termination of patent right or utility model |