CN202694370U - Multi-face recognition system based on digital image processing - Google Patents
Multi-face recognition system based on digital image processing Download PDFInfo
- Publication number
- CN202694370U CN202694370U CN 201220308158 CN201220308158U CN202694370U CN 202694370 U CN202694370 U CN 202694370U CN 201220308158 CN201220308158 CN 201220308158 CN 201220308158 U CN201220308158 U CN 201220308158U CN 202694370 U CN202694370 U CN 202694370U
- Authority
- CN
- China
- Prior art keywords
- image processing
- digital image
- recognition system
- system based
- processor
- 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
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The utility model discloses a multi-face recognition system based on digital image processing. The multi-face recognition system comprises a processor, a camera, a display screen, a keyboard and a power source. The multi-face recognition system is simple in structure, low in cost, fast in data processing speed, high in maintainability, stable in work and capable of real-timely and accurately recognizing multiple faces.
Description
Technical field
The utility model relates to the digital image processing field of recognition of face, particularly a kind of plurality of human faces recognition system based on Digital Image Processing.
Background technology
Digital image processing techniques are utilized exactly computing machine or some hardware devices (such as MCU, DSP, PC etc.) that the image information that collects by video capture circuit is carried out series of algorithms and are processed, obtain the series of features parameter of the image that collects, such as geometric properties of object etc., and then satisfy the technology of people's demand.After 9.11 disasters occured, various countries stepped up its investment in anti-terrorism, Homeland Security and social safety field.Identification also more and more obtains the attention of national governments, and recognition of face is an important branch of identity recognizing technology, also is that people are in an emphasis problem of digital image processing field research." the Biometrics Market and Industry Report 2007-2012 " that publish according to American I nternational Biometric Group shows, recognition of face market whole world income in 2007 surpasses more than 200 hundred million Renminbi, and annual more than 40 hundred million Renminbi that increase, reached more than 400 hundred million Renminbi to 2012.At present, Digital Image Processing based on recognition of face obtains good application in all many-sides such as safety monitoring, search and rescue investigations, but still there is a series of problem, mostly be to adopt independent computing machine or calculating unit to operate such as existing system, huge being not easy to of equipment operates, and mostly just the video segment of crossing or the image that collects operated the real-time of forfeiture recognition of face.Although and general embedded system use is extensive, be rarely used in the plurality of human faces identification of single image, just only the individual human face image that gathers is identified, and the algorithm precision is lower.
Summary of the invention
The technical problems to be solved in the utility model is to provide a kind of plurality of human faces recognition system based on Digital Image Processing, should be simple in structure based on the plurality of human faces recognition system of Digital Image Processing, the algorithm precision is higher, and the recognition of face rate is higher, system works is stable, and is maintainable strong.
The technical scheme of utility model is as follows:
A kind of plurality of human faces recognition system based on Digital Image Processing comprises processor, camera, display screen, keyboard and power supply; Camera, display screen, keyboard and power supply all link to each other with processor, and described processor comprises for the first subsystem of management and control and is used for Digital Image Processing and the second subsystem of plurality of human faces identification.
Described the first subsystem is the ARM subsystem; Described the second subsystem is the DSP subsystem.
Described processor is the OMAP3530 processor.
This system comprises the extension storage system that links to each other with processor, and the extension storage system comprises at least a in NAND Flash, NOR Flash and mmc card and the SD card.
Described camera links to each other with processor by modulus conversion chip.
Described camera links to each other by the V4L2 interface with modulus conversion chip.
Beneficial effect
A kind of plurality of human faces recognition system based on Digital Image Processing of the present utility model adopts the Embedded System Design based on OMAP3530, can local control system, improved maintainablely and stable, and embodied the characteristic of system intelligent.Successfully apply in the reality, aspect teaching, improved roll-call efficient, save the time of wasting on class; Aspect commercial, solved the apparatus expensive that in the past adopts fingerprint recognition, the problem of inconvenient operation.Native system is simple in structure, computing velocity was fast when digital picture was processed, and the recognition of face rate is high, and good operability and the advantage of lower cost are arranged, and is convenient to promote.
Description of drawings
Fig. 1 is structural representation of the present utility model;
Fig. 2 is workflow diagram of the present utility model.
Embodiment
Embodiment 1:
As shown in Figure 1, a kind of plurality of human faces recognition system based on Digital Image Processing comprises OMAP3530 processor, camera, display screen, keyboard and power supply; Camera, display screen, keyboard, power supply and extension storage system.
As shown in Figure 2, the plurality of human faces recognition system workflow based on Digital Image Processing comprises system's startup, Image Acquisition, facial image feature extraction and coupling and obtains the identification staff list.
In the classroom, adopt native system to carry out automatic roll-calling, at first start power supply, face characteristic information and the corresponding staff list that obtains in advance is stored in the system, be used for the image information behind acquisition and processing is mated identification; Select camera as image acquisition unit, TVP5146 obtains catching in real time digital picture by the ARM unit controls camera in the OMAP3530 processor after the digital signal as modulus conversion chip.
Data by camera collection are data of yuv space, and are not complete standard pictures.It is handled as follows: after the yuv space data are become the rgb space data through color space conversion, add successively 14 file header and 40 message bit pattern head, finally obtain the image of needed 24 the BMP forms of system.
The image of 24 BMP forms obtaining is carried out human face region cut apart, and the facial image after cutting apart is carried out feature extracting and matching.System will have skin color Image Segmentation Using on every side according to the skin color model principle, and will divide the image and the ellipse that cut off to carry out match, thereby make the facial image that obtains for oval, and system is rotated adjustment according to the angle of ellipse long and short shaft and horizontal and vertical direction to ellipse, draws at last comparatively desirable facial image; Because the resolution of the facial image that collects is lower, adopt the Retinex of color-based Constancy Theory to strengthen algorithm, the facial image that collects is carried out the sharpening of image and process; The facial image that gathers is carried out the operation of binaryzation, through rim detection reentry vertical Gray Projection and the horizontal Gray Projection of bianry image, according to the Gray Projection figure that obtains eyes, nose face are positioned, then according to the position behind the location, extract the individual features value; Use again the PCA algorithm that corresponding facial image feature is carried out people's face matching and recognition.
After successively many facial images that gather being carried out recognition of face, list the identification situation to everyone face figure, draw the staff list in classroom.
Claims (6)
1. the plurality of human faces recognition system based on Digital Image Processing is characterized in that, comprises processor, camera, display screen, keyboard and power supply; Camera, display screen, keyboard and power supply all link to each other with processor, and described processor comprises for the first subsystem of management and control and is used for Digital Image Processing and the second subsystem of plurality of human faces identification.
2. the plurality of human faces recognition system based on Digital Image Processing according to claim 1 is characterized in that, described the first subsystem is the ARM subsystem; Described the second subsystem is the DSP subsystem.
3. the plurality of human faces recognition system based on Digital Image Processing according to claim 2 is characterized in that, described processor is the OMAP3530 processor.
4. the plurality of human faces recognition system based on Digital Image Processing according to claim 1, it is characterized in that, comprise the extension storage system that links to each other with processor, the extension storage system comprises at least a in NAND Flash, NOR Flash and mmc card and the SD card.
5. each described plurality of human faces recognition system based on Digital Image Processing is characterized in that camera links to each other with processor by modulus conversion chip according to claim 1-4.
6. the plurality of human faces recognition system based on Digital Image Processing according to claim 5 is characterized in that, described camera links to each other by the V4L2 interface with modulus conversion chip.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220308158 CN202694370U (en) | 2012-06-28 | 2012-06-28 | Multi-face recognition system based on digital image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220308158 CN202694370U (en) | 2012-06-28 | 2012-06-28 | Multi-face recognition system based on digital image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202694370U true CN202694370U (en) | 2013-01-23 |
Family
ID=47549953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201220308158 Expired - Fee Related CN202694370U (en) | 2012-06-28 | 2012-06-28 | Multi-face recognition system based on digital image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202694370U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732601A (en) * | 2014-11-19 | 2015-06-24 | 东北大学 | Automatic high-recognition-rate attendance checking device and method based on face recognition technology |
| CN108700988A (en) * | 2016-02-15 | 2018-10-23 | 电子湾有限公司 | Digital picture is presented |
| US12008034B2 (en) | 2016-02-15 | 2024-06-11 | Ebay Inc. | Digital image presentation |
-
2012
- 2012-06-28 CN CN 201220308158 patent/CN202694370U/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732601A (en) * | 2014-11-19 | 2015-06-24 | 东北大学 | Automatic high-recognition-rate attendance checking device and method based on face recognition technology |
| CN104732601B (en) * | 2014-11-19 | 2017-05-10 | 东北大学 | Automatic high-recognition-rate attendance checking device and method based on face recognition technology |
| CN108700988A (en) * | 2016-02-15 | 2018-10-23 | 电子湾有限公司 | Digital picture is presented |
| CN108700988B (en) * | 2016-02-15 | 2021-05-25 | 电子湾有限公司 | Digital image presentation |
| US11681745B2 (en) | 2016-02-15 | 2023-06-20 | Ebay Inc. | Digital image presentation |
| US12008034B2 (en) | 2016-02-15 | 2024-06-11 | Ebay Inc. | Digital image presentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN110070033B (en) | Method for detecting wearing state of safety helmet in dangerous working area in power field | |
| WO2020143330A1 (en) | Facial image capturing method, computer-readable storage medium and terminal device | |
| CN101587485B (en) | Face information automatic login method based on face recognition technology | |
| WO2019061658A1 (en) | Method and device for positioning eyeglass, and storage medium | |
| CN104951773A (en) | Real-time face recognizing and monitoring system | |
| CN104361326A (en) | Method for distinguishing living human face | |
| CN102902986A (en) | Automatic gender identification system and method | |
| CN105046219A (en) | Face identification system | |
| CN103985172A (en) | An access control system based on three-dimensional face identification | |
| CN112633111B (en) | Method and device for detecting wearing of safety helmet and storage medium | |
| CN105335691A (en) | Smiling face identification and encouragement system | |
| CN113239739B (en) | Wearing article identification method and device | |
| CN102567716A (en) | Face synthetic system and implementation method | |
| CN103996033A (en) | Human identification method based on tracking of human face five-sense-organ coordinates | |
| CN204143555U (en) | The Certificate of House Property printing terminal of identification self-aided terminal and correspondence | |
| CN202694370U (en) | Multi-face recognition system based on digital image processing | |
| CN103150575A (en) | Real-time three-dimensional unmarked human body gesture recognition method and system | |
| CN112084986A (en) | Real-time safety helmet detection method based on image feature extraction | |
| CN104217503A (en) | Self-service terminal identity identification method and corresponding house property certificate printing method | |
| CN104217504A (en) | Identity recognition self-service terminal and corresponding certificate of house property printing terminal | |
| CN109800701A (en) | A kind of intelligent security protection Verification System based on recognition of face | |
| CN104463143A (en) | Identification system based on image processing | |
| CN103268477A (en) | Three-dimensional face recognition system based on embedded platform | |
| CN103824058A (en) | Face recognition system and method based on locally distributed linear embedding algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130123 Termination date: 20130628 |