CN202433920U - Multi-angle human face recognizing system - Google Patents
Multi-angle human face recognizing system Download PDFInfo
- Publication number
- CN202433920U CN202433920U CN2012200553792U CN201220055379U CN202433920U CN 202433920 U CN202433920 U CN 202433920U CN 2012200553792 U CN2012200553792 U CN 2012200553792U CN 201220055379 U CN201220055379 U CN 201220055379U CN 202433920 U CN202433920 U CN 202433920U
- Authority
- CN
- China
- Prior art keywords
- face
- angle
- human face
- video camera
- face identification
- 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 relates to a multi-angle human face recognizing system. The multi-angle human face recognizing system comprises a plurality of cameras for acquiring a video stream of a human face, a human face recognizing device and display equipment, wherein the plurality of cameras are used for acquiring video streams of a human face; the distances between all the cameras to the shot human face are equal; the included angle between the cameras is 20-50 degrees; the human face recognizing device is connected with the cameras and is used for acquiring the video streams of all the cameras and selecting an optimal human face picture from the video streams; and the display equipment is connected with the human face recognizing device and is used for outputting and displaying the optimal human face picture which is recognized by the human face recognizing device. The multi-angle human face recognizing system can perform multi-angle human face acquisition on an acquired object, without perception and matching of a human person, and can improve the success rate of frontal human face acquisition under the condition that the arbitrariness of a human face posture is relatively large.
Description
Technical field
The utility model belongs to the face identification system field, particularly a kind of multi-angle face identification system.
Background technology
Now, face recognition technology is applied in the video safety defense monitoring system gradually, and it uses prerequisite is the collection of people's face.Collecting front face is the application foundation of face recognition technology, but in reality, people's attitude has very big randomness; Can also force by the attitude of acquisition target in occasions such as safety check, entry and exit, but in the public cultural facilities place, for example museum, the Art Museum, library etc.; Can't force spectators to cooperate collection; And in the practical application of video safety defense monitoring system, implement hidden collection often, not perception of acquisition target, so the attitude of acquisition target is uncontrollable.Present people's face acquisition method often is difficult to collect front face in this case, and it is very high to show that mainly present face recognition technology requires the collection front face, and the face rotating range of asking for help is little; Often acquisition camera visual field central axis about [15 °; + 15 °], left rotation and right rotation [20 ° ,+20 °]; And actual persons face or human body attitude scope all exceed this scope, in case exceed then can't collect front face.Owing to people's attitude is random, the installation site of acquisition camera often is difficult to accurately location, and aligning the collection of dough figurine face influences bigger.Present acquisition method often requires to be met the requirement of front face acquisition range by the acquisition target human face posture, needs acquisition target to cooperate, and acquisition target cooperates and hidden collection situation front face acquisition rate is not high for need not.
The multiple attitude recognition of face that discloses like the Chinese patent CN10045650.7 system and method for deploying to ensure effective monitoring and control of illegal activities, though its can know others face rotating range be about [30 ° ,+30 °]; [30 ° of left rotation and right rotation; + 30 °], in case but the rotation of people's face exceeds above scope, still can't realize effective collection.And under the ill-matched situation of not perception of acquisition target, human face posture often all can exceed above scope.
The utility model content
The purpose of the utility model is to provide a kind of multi-angle face identification system, realizes the people's face multi-angle collection to being need not to cooperate by the acquisition target unaware, improves front face collection success ratio under the bigger situation of human face posture randomness.
For addressing the above problem, the utility model relates to a kind of multi-angle face identification system, comprising:
Be used to gather some video cameras of the video flowing of people's face, every said video camera to the distance of being taken the photograph people's face equate and said video camera between angle be 20 to 50 degree;
Be connected and from the video flowing of gathering, select the face identification device of beautiful woman's face picture with said video camera;
Link to each other with said face identification device and export the display device that shows said beautiful woman's face picture.
Further, said video camera is three.
Further, be that angle between the said video camera in center is 40 degree to take the photograph people's face.
Further, the left rotation and right rotation angle of said video camera is respectively 20 degree, and the anglec of rotation is respectively 15 degree up and down.
Further, the setting height(from bottom) of said video camera is in 2000mm.
Further, said face identification device comprises:
Be connected with said video camera and with the recognition of face equipment of the video flowing reduction framing picture of gathering;
Be connected and store the memory device of said frame picture with said recognition of face equipment;
Be connected with said memory device and the front face picture from said frame picture in choose beautiful woman's face picture attitude differentiate compare facilities;
Be connected the also synchronous generator of the video flowing rise time of its collection of mark with said video camera.Further, said recognition of face equipment is the TMSDM6437DSP processor.
Further, said memory device is EPROM.
Further, said attitude differentiation compare facilities is a Dragonball MX1 chip.
Further, said synchronous generator is Tektronix SPG422.
Compared with prior art; Some video cameras of the video flowing of the utility model through being provided for gathering people's face; Every said video camera to the distance of being taken the photograph people's face equate and said video camera between angle be 20 to 50 degree; And setting is connected with said video camera, is used to obtain the video flowing of every video camera, and from video flowing, chooses the face identification device of beautiful woman's face picture; Be provided with in addition with said face identification device and link to each other; Be used for beautiful woman's face picture of the identification of said face identification device is exported the display device of demonstration, realize people's face multi-angle collection, improve under the bigger situation of human face posture randomness front face and gather success ratio being need not to cooperate by the acquisition target unaware.
Description of drawings
Fig. 1 is the connection layout of the multi-angle face identification system of the utility model;
Fig. 2 is the installation diagram of the video camera seat in the plane of the utility model one embodiment;
Fig. 3 is the face identification device structural map of the utility model one embodiment;
Fig. 4 is the concrete structural map of Fig. 3 face identification device.
Embodiment
Below in conjunction with the accompanying drawing among the utility model embodiment, the technical scheme among the utility model embodiment is carried out clear, intactly description, obviously, described embodiment only is the utility model part embodiment, rather than whole embodiment.Based on the embodiment in the utility model, those of ordinary skills are not making the every other embodiment that is obtained under the creative work prerequisite, all belong to the scope of the utility model protection.
Fig. 1 is the connection layout of the multi-angle face identification system of the utility model.
Multi-angle face identification system as shown in Figure 1, that the utility model provides specifically comprises: some video cameras 1, face identification device 2 and display devices 3, wherein,
Said some shooting 1 machines are used to gather the video flowing of people's face, and the angle between the equal and said video camera 1 is 20 to 50 to spend to the distance of being taken the photograph people's face for every said video camera 1.
Said face identification device 2 is connected with said video camera 1, is used to obtain the video flowing of every video camera 1, and from video flowing, chooses beautiful woman's face picture.
Said display device 3 links to each other with said face identification device, is used for beautiful woman's face picture of the identification of said face identification device 2 is exported demonstration, and said display device 3 can be PC.
Fig. 2 is the installation diagram of the video camera seat in the plane of the utility model one embodiment.
In the present embodiment, as shown in Figure 2, said video camera 1 is three, and with by to be taken the photograph people's face 4 be rotation center, every video camera 1 is 20 degree around the left rotation and right rotation angle of being taken the photograph people's face 4, and the anglec of rotation is 15 degree up and down, and the angle between two adjacent camera 1 is 40 to spend.The selection of every video camera 1 seat in the plane needs according to current recognition of face characteristics, and promptly can to discern the attitude scope be left rotation and right rotation [20 ° ,+20 °] to people from system face; [15 ° of last lower angles; + 15 °], setting height(from bottom) is controlled in the 2000mm, and the collecting efficiency of every digital camera was 25 frame/seconds.
Fig. 3 is the face identification device structural map of the utility model one embodiment.
In the present embodiment, as shown in Figure 3, said face identification device 2 comprises: recognition of face equipment 21, memory device 22, attitude are differentiated compare facilities 23 and synchronous generator 24, wherein,
Recognition of face equipment 21 is connected with said video camera 1, is used to obtain the video flowing of every video camera 1, and with said video flowing reduction framing picture.
Memory device 22 is connected with said recognition of face equipment 21, is used to store said frame picture.
Attitude is differentiated compare facilities 23 and is connected with said memory device 22, is used for obtaining the front face picture from the frame picture, and from said front face picture, chooses beautiful woman's face picture.
Synchronous generator 24 is connected with said video camera 1, is used for the time of the video flowing generation of mark video camera.
Wherein, In the multi-angle face identification system of the utility model; Every video camera 1 can connect a recognition of face equipment 21, memory device 22, a synchronous generator 24 successively, also can many or all video cameras 1 connect a recognition of face equipment 21, memory device 22, a synchronous generator 24 jointly successively.In the present embodiment, every video camera 1 connects a recognition of face equipment 21 and a memory device 22 respectively successively, and connects a synchronous generator 24 jointly, and attitude of every memory device 22 common connections is differentiated compare facilities 23 then.
Multi-angle face identification system basic functional principle is following: the video flowing that collects for some video cameras 1 carries out pre-service with 24 pairs of video flowings of a synchronous generator; Promptly confirm a people, some video cameras are marked as synchronization to every two field picture that a fixed position collects in the contemporaneity, have made things convenient for multi-angle people face information process (look into anharmonic ratio to) like this; Through synchronous generator 24; Some video cameras 1 collect people's face information, can accurately judge whether it is a people's photo, and people's face information processing process can have more determinacy like this; Thereby the photo origin that guarantees comparison belongs to same individual; Can not increase calculated amount, and the accuracy that information is judged can improve, can realize well that like this everyone goes out the target of a positive face image under the multi-angle collection.
As shown in Figure 4; In the present embodiment; Said recognition of face equipment 21 is TMSDM6437 DSP (TMS320DM6437) processor, and TMS320DM6437 is that TI company releases, is high-performance, exploitation, dominant frequency 600MHz, 32 processor familys that fixed DSP Leonardo da Vinci is technological of low-cost Video Applications specially, and TMSDM6437 DSP can obtain the video flowing of each digital camera output; Secondly video flowing is carried out the reduction of frame picture; Restore every video camera per second 25 frame pictures, in the frame picture, carry out people's face subsequently and detect, detect the people of point range intercepting according to pixels face picture and name behind people's face; Name needs sequence number, the synchronous sequence time according to the Image Acquisition video camera, with the picture-storage that obtains in memory device 22 separately.
Please continue with reference to figure 4, in the present embodiment, said memory device 22 is EPROM; It is Dragonball MX1 chip that said attitude is differentiated compare facilities 23; Dragonball MX1 is a imperial pearl chip that Motorola releases; Characteristics are low-power consumption, low frequency, good stability; Dragonball MX1 can differentiate human face posture; From three EPROM 22, obtain with people's face picture constantly by the image file naming order, the people's face picture that gets access to is extracted eigenwert carry out the attitude differentiation relatively, the front face picture of selecting a best outputs on the PC with this picture characteristic of correspondence value coding.
Please continue with reference to figure 4, in the present embodiment, said synchronous generator 24 is Tektronix SPG422; The digital camera that Tektronix SPG422 synchronous digital signal generator 24 can gathered for front end; Use synchronous generator, whenever send out a pulse signal, through this pulse signal at a distance from a break time; Come mark front-end collection image, make that the time mark of every frame picture that synchronization restores through three dsp chips is consistent.
In sum; Some video cameras of the video flowing of the utility model through being provided for gathering people's face; Every said video camera to the distance of being taken the photograph people's face equate and said video camera between angle be 20 to 50 degree; And setting is connected with said video camera, is used to obtain the video flowing of every video camera, and from video flowing, chooses the face identification device of beautiful woman's face picture; Be provided with in addition with said face identification device and link to each other; Be used for beautiful woman's face picture of the identification of said face identification device is exported the display device of demonstration, realize people's face multi-angle collection, improve under the bigger situation of human face posture randomness front face and gather success ratio being need not to cooperate by the acquisition target unaware.
Obviously, those skilled in the art can carry out various changes and modification to utility model and not break away from the spirit and the scope of the utility model.Like this, if these of the utility model are revised and modification belongs within the scope of the utility model claim and equivalent technologies thereof, then the utility model also is intended to comprise these change and modification.
Claims (10)
1. a multi-angle face identification system is characterized in that, comprising:
Be used to gather some video cameras of the video flowing of people's face, every said video camera to the distance of being taken the photograph people's face equate and said video camera between angle be 20 to 50 degree;
Be connected and from the video flowing of gathering, select the face identification device of beautiful woman's face picture with said video camera;
Link to each other with said face identification device and export the display device that shows said beautiful woman's face picture.
2. multi-angle face identification system as claimed in claim 1 is characterized in that, said video camera is three.
3. multi-angle face identification system as claimed in claim 2 is characterized in that, is that angle between the said video camera in center is 40 degree to take the photograph people's face.
4. multi-angle face identification system as claimed in claim 3 is characterized in that, the left rotation and right rotation angle of said video camera is respectively 20 degree, and the anglec of rotation is respectively 15 degree up and down.
5. multi-angle face identification system as claimed in claim 3 is characterized in that the setting height(from bottom) of said video camera is in 2000mm.
6. like each described multi-angle face identification system of claim 1 to 5, it is characterized in that said face identification device comprises:
Be connected with said video camera and with the recognition of face equipment of the video flowing reduction framing picture of gathering;
Be connected and store the memory device of said frame picture with said recognition of face equipment;
Be connected with said memory device and the front face picture from said frame picture in choose beautiful woman's face picture attitude differentiate compare facilities;
Be connected the also synchronous generator of the video flowing rise time of its collection of mark with said video camera.
7. multi-angle face identification system as claimed in claim 6 is characterized in that, said recognition of face equipment is the TMSDM6437DSP processor.
8. multi-angle face identification system as claimed in claim 7 is characterized in that, said memory device is EPROM.
9. multi-angle face identification system as claimed in claim 8 is characterized in that, it is Dragonball MX1 chip that said attitude is differentiated compare facilities.
10. multi-angle face identification system as claimed in claim 9 is characterized in that, said synchronous generator is Tektronix SPG422.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012200553792U CN202433920U (en) | 2012-02-20 | 2012-02-20 | Multi-angle human face recognizing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012200553792U CN202433920U (en) | 2012-02-20 | 2012-02-20 | Multi-angle human face recognizing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202433920U true CN202433920U (en) | 2012-09-12 |
Family
ID=46783349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012200553792U Expired - Fee Related CN202433920U (en) | 2012-02-20 | 2012-02-20 | Multi-angle human face recognizing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202433920U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091149A (en) * | 2014-06-20 | 2014-10-08 | 中国船舶重工集团公司第七二六研究所 | Face acquisition modeling training system and acquisition modeling training method thereof |
| CN104616375A (en) * | 2014-12-30 | 2015-05-13 | 苏州福丰科技有限公司 | Intelligent three-dimensional face identification lock |
| CN109271923A (en) * | 2018-09-14 | 2019-01-25 | 曜科智能科技（上海）有限公司 | Human face posture detection method, system, electric terminal and storage medium |
| CN109359635A (en) * | 2018-12-14 | 2019-02-19 | 中通服公众信息产业股份有限公司 | A kind of face information acquisition device of multi-angle |
| CN110826367A (en) * | 2018-08-10 | 2020-02-21 | 北京魔门塔科技有限公司 | Human face image acquisition system for data analysis |
-
2012
- 2012-02-20 CN CN2012200553792U patent/CN202433920U/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091149A (en) * | 2014-06-20 | 2014-10-08 | 中国船舶重工集团公司第七二六研究所 | Face acquisition modeling training system and acquisition modeling training method thereof |
| CN104091149B (en) * | 2014-06-20 | 2018-01-26 | 中国船舶重工集团公司第七二六研究所 | The collection modeling training system and its collection modeling training method of face |
| CN104616375A (en) * | 2014-12-30 | 2015-05-13 | 苏州福丰科技有限公司 | Intelligent three-dimensional face identification lock |
| CN110826367A (en) * | 2018-08-10 | 2020-02-21 | 北京魔门塔科技有限公司 | Human face image acquisition system for data analysis |
| CN109271923A (en) * | 2018-09-14 | 2019-01-25 | 曜科智能科技（上海）有限公司 | Human face posture detection method, system, electric terminal and storage medium |
| CN109359635A (en) * | 2018-12-14 | 2019-02-19 | 中通服公众信息产业股份有限公司 | A kind of face information acquisition device of multi-angle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN202443476U (en) | Multiple camera human face recognition system | |
| CN202433920U (en) | Multi-angle human face recognizing system | |
| CN106843460B (en) | Multiple target position capture positioning system and method based on multi-cam | |
| CN103279186B (en) | Merge the multiple goal motion capture system of optical alignment and inertia sensing | |
| ES2704277T3 (en) | Facial recognition with self-learning using depth-based tracking for the generation and updating of databases | |
| CN105931272B (en) | A kind of Moving Objects method for tracing and system | |
| Goh et al. | The CMU face in action (FIA) database | |
| CN106652590B (en) | Teaching method, teaching identifier and tutoring system | |
| CN102063887A (en) | Method for automatically adjusting visual range of display and display thereof | |
| CN102156537A (en) | Equipment and method for detecting head posture | |
| CN105338369A (en) | Method and apparatus for synthetizing animations in videos in real time | |
| CN106775528A (en) | A kind of touring system of virtual reality | |
| CN102553232A (en) | Human posture capture apparatus and implementing method thereof | |
| CN106373142A (en) | Virtual character on-site interaction performance system and method | |
| CN103543827A (en) | Immersive outdoor activity interactive platform implement method based on single camera | |
| CN104952105B (en) | A kind of 3 D human body Attitude estimation method and apparatus | |
| CN107281710A (en) | A kind of method of remedial action error | |
| CN105338370A (en) | Method and apparatus for synthetizing animations in videos in real time | |
| CN108564653A (en) | Human skeleton tracing system and method based on more Kinect | |
| CN110378292A (en) | Three dimension location system and method | |
| CN109806580A (en) | Mixed reality system and method based on wireless transmission | |
| CN203931065U (en) | A kind of electric operating site safety region prior-warning device | |
| CN109445598A (en) | A kind of augmented reality system and device of view-based access control model | |
| CN105208372A (en) | 3D landscape generation system and method with interaction measurable function and reality sense | |
| CN114832349B (en) | Yuanzhou swimming teaching auxiliary system and use method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180613 Address after: No. 345, No. 19, fresh water road, Huangpu District, Shanghai, No. 19 Patentee after: Shanghai Zhongyuan Electron & Engineering Co.,Ltd. Address before: 200135 202, 22 Lane 1446 lane, Yushan Road, Pudong New Area, Shanghai. Patentee before: Hua Jiaobao |
|
| 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: 20120912 Termination date: 20210220 |