CN202472689U - Face posture detection system - Google Patents
Face posture detection system Download PDFInfo
- Publication number
- CN202472689U CN202472689U CN2012200820740U CN201220082074U CN202472689U CN 202472689 U CN202472689 U CN 202472689U CN 2012200820740 U CN2012200820740 U CN 2012200820740U CN 201220082074 U CN201220082074 U CN 201220082074U CN 202472689 U CN202472689 U CN 202472689U
- Authority
- CN
- China
- Prior art keywords
- face
- image
- detection system
- human
- communication unit
- 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 - Lifetime
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The utility model discloses a face posture detection system. The face posture detection system comprises an image and video shooting unit, a face detector and a server, wherein the image and video shooting unit is used for shooting images and/or videos; the face detector is used for detecting the images and/or videos shot by the image and video shooting unit and acquiring and selecting face images from the images and/or videos; and the server is used for storing information of the selected face images. The face detector comprises a processor, a storage and a communication unit, wherein the processor is respectively connected with the storage and the communication unit. The face posture detection system disclosed by the utility model can acquire face images with high quality, guarantees the acquired face images to satisfy with corresponding face image acquisition standards, and automatically detects optimal faces, so that the degree of manual intervention is greatly reduced, and meanwhile, the efficiency of face image acquisition is increased. The face posture detection system has one standard on all face image acquisition systems, thus providing great help on the accuracy of a face recognition system which is used in the future as required.
Description
Technical field
The utility model belongs to the face recognition technology field, relates to a kind of attitude detection system, relates in particular to a kind of human face posture detection system.
Background technology
In present human face image information process field; Include a plurality of research directions such as recognition of face, face tracking, attitude detection, Expression Recognition; Yet; All these research directions all relate to the problem that people's face is represented and located, and promptly must know position and the size of people's face in image---and people's face detects.Therefore, for complete, automatic people's face information analysis system, people's face optimum attitude detection algorithm is absolutely necessary.This algorithm can be used in the various application scenarioss of photograph acquisition.For the accuracy of face recognition algorithms provides a very well condition precedent.
, some are starved of the analytical equipment that can detect optimum attitude automatically in need gathering the application scenarios of some key population people faces, such as: video tracking, break laws and commit crime personal information, the portrait collection of going into the personnel of institute, people stayed temporarily and inward and outward personnel and storage and figure and features characteristic key aspect.The optimum attitude pick-up unit has been arranged, can be the effective figure information of face identification system collection from now on, the accuracy of recognition of face is improved be very helpful.
The utility model content
The utility model technical matters to be solved is: a kind of human face posture detection system is provided, can gathers high-quality facial image.
For solving the problems of the technologies described above, the utility model adopts following technical scheme:
A kind of human face posture detection system, said system comprises:
Image/video is taken the unit, in order to photographic images or/and video;
Human-face detector connects said image/video and takes the unit, in order to detecting image that said image/video takes unit photographs or/and video, and gathers and chooses the facial image in image or the video;
Server connects said human-face detector, the human face image information of choosing in order to storage.
As a kind of preferred version of the utility model, said human-face detector comprises processor, storer, communication unit, and processor is connected storage, communication unit respectively.
As a kind of preferred version of the utility model, said communication unit is a radio communication unit.
As a kind of preferred version of the utility model, said server comprises second communication unit, is connected with human-face detector through second communication unit.
As a kind of preferred version of the utility model, said image/video is taken the unit and is comprised the 3rd communication unit, is connected with human-face detector through the 3rd communication unit.
As a kind of preferred version of the utility model, said the 3rd communication unit is a radio communication unit.
As a kind of preferred version of the utility model, said human-face detector also comprises the human face posture detecting device, in order to gather the optimum attitude facial image.
As a kind of preferred version of the utility model, it is video camera that said image/video is taken the unit.
The beneficial effect of the utility model is: the human face posture detection system that the utility model proposes, can gather high-quality facial image; Guarantee that the portrait of gathering meets corresponding portrait and gathers standard, detect optimum people's face automatically, significantly reduced the manual intervention degree, improved the efficient that portrait is gathered simultaneously.The utility model has a standard to all portrait acquisition systems, to be very helpful like the degree of accuracy that need use face identification system in the future.
The utility model also has than higher extendability; The correlation technique of the utility model research and development can also be applied to bank easily; Security fields such as public security (like auxiliary monitoring and pursue and capture an escaped prisoner etc.), even can be applied in the break in traffic rules and regulations monitoring, extremely strong expandability therefore had.
Description of drawings
Fig. 1 is the composition synoptic diagram of the utility model human face posture detection system.
Embodiment
Specify the preferred embodiment of the utility model below in conjunction with accompanying drawing.
Embodiment one
See also Fig. 1, the utility model has disclosed a kind of human face posture detection system, and said system comprises: image/video is taken unit 20, human-face detector 10, server 30; Human-face detector 10 is taken unit 20 with image/video respectively, server 30 is connected.
Image/video take unit 20 in order to photographic images or/and video.As, said image/video is taken unit 20 can be video camera.Said image/video is taken unit 20 and is comprised the 3rd communication unit, is connected with human-face detector 10 through the 3rd communication unit.Said the 3rd communication unit is a radio communication unit.
Human-face detector 10 connects said image/video and takes unit 20,, and gathers and chooses the facial image in image or the video or/and video in order to detect that said image/video is taken the image taken unit 20.
Preferably, said human-face detector also comprises the human face posture detecting device, in order to gather the optimum attitude facial image.
As shown in Figure 1, said human-face detector 10 comprises processor 11, storer 12, communication unit 13, and processor 11 is connected storage 12, communication unit 13 respectively.Said communication unit 13 can be radio communication unit.
The running of the utility model total system realizes through following steps:
When step 1, staff needed register information people's image information through camera acquisition, video camera connected the human face analysis equipment (human-face detector 10) on backstage, and the people's face that collects is carried out analyzing and processing.
Step 2, human face analysis equipment can be handled image automatically, choose wherein optimum attitude and store.
Step 3, with the resulting information stores of step 2 to the data in server storehouse, so that when carrying out authentications such as recognition of face and coupling operation, call; Thereby the collection of underwriter's picture can be used for the people and compares identification.
Embodiment two
Present embodiment discloses the preferred version of a kind of attitude detection of human face posture detection system.In human-face detector 10 recognition and verification video images, these video images carry out optimum attitude and choose through the optimum attitude identification module, confirm client's information simultaneously through the information in the canned data server.
The portrait optimum attitude acquisition methods of a kind of optimum attitude recognition system based on face recognition technology of the utility model comprises the steps:
A obtains needed portrait video information: the user to required registration carries out the portrait video acquisition.
The B pre-service: the original image to input comprises gray processing, the illumination compensation pre-service, and the quality of raising image obtains gray level image;
The C optimum attitude detects: detect people's face automatically, the people's face of focusing automatically detects the anglec of rotation of people's face in pitching, the degree of depth, three dimensions in plane, and points out; Automatically judge whether espressiove of people's face, and point out.
D people's face location: align the dough figurine face and detect in real time, confirm the position of people's face in image; Be included as feature calculation unit and taxon; Described for feature calculation unit is that gray level image to be detected is carried out convergent-divergent, exhaustive search candidate face window, the microstructure features of each window of calculated description, and it is passed to AdaBoost neural network classifier unit adjudicate;
E organ location; The organ location is to confirm the position of people's face in image, comprises eyes, two eyebrows, nose, face, the location of lower jaw; Face shape facility and AdaBoost sorter according to people's face the zone of detected people's face window carry out eyes to C in the step, two eyebrows, and nose, face, the location of lower jaw for potential pseudo-organ, adopts the discrimination principle of maximum a posteriori probability to carry out filtering;
F normalization: according to the positional information of organ, try to achieve normalized gray level image, it is that image is comprised rotation, convergent-divergent, and shearing manipulation makes the eyes level, and the height of lower jaw is certain;
G feature extraction: from whole people's face, extract people's face and lose characteristic, comprise naked eyelid, eyebrow, eyes, nose, mouth face component: utilize principal component method to extract the characteristic of face component;
H people's face information stores: the optimum attitude portrait for collecting is preserved.
In sum, the human face posture detection system that the utility model proposes can be gathered high-quality facial image; Guarantee that the portrait of gathering meets corresponding portrait and gathers standard, detect optimum people's face automatically, significantly reduced the manual intervention degree, improved the efficient that portrait is gathered simultaneously.The utility model has a standard to all portrait acquisition systems, to be very helpful like the degree of accuracy that need use face identification system in the future.
The utility model also has than higher extendability; The correlation technique of the utility model research and development can also be applied to bank easily; Security fields such as public security (like auxiliary monitoring and pursue and capture an escaped prisoner etc.), even can be applied in the break in traffic rules and regulations monitoring, extremely strong expandability therefore had.
Here description of the utility model and application is illustrative, is not to want the scope of the utility model is limited in the above-described embodiments.Here the distortion of the embodiment that is disclosed and change are possible, and the replacement of embodiment is known with the various parts of equivalence for those those of ordinary skill in the art.Those skilled in the art are noted that under the situation of spirit that does not break away from the utility model or essential characteristic, and the utility model can be with other form, structure, layout, ratio, and realize with other assembly, material and parts.Under the situation that does not break away from the utility model scope and spirit, can carry out other distortion and change here to the embodiment that is disclosed.
Claims (8)
1. a human face posture detection system is characterized in that, said system comprises:
Image/video is taken the unit, in order to photographic images or/and video;
Human-face detector connects said image/video and takes the unit, in order to detecting image that said image/video takes unit photographs or/and video, and gathers and chooses the facial image in image or the video;
Server connects said human-face detector, the human face image information of choosing in order to storage.
2. human face posture detection system according to claim 1 is characterized in that:
Said human-face detector comprises processor, storer, communication unit, and processor is connected storage, communication unit respectively.
3. human face posture detection system according to claim 2 is characterized in that:
Said communication unit is a radio communication unit.
4. human face posture detection system according to claim 1 is characterized in that:
Said server comprises second communication unit, is connected with human-face detector through second communication unit.
5. human face posture detection system according to claim 1 is characterized in that:
Said image/video is taken the unit and is comprised the 3rd communication unit, is connected with human-face detector through the 3rd communication unit.
6. human face posture detection system according to claim 5 is characterized in that:
Said the 3rd communication unit is a radio communication unit.
7. human face posture detection system according to claim 1 is characterized in that:
Said human-face detector also comprises the human face posture detecting device, in order to gather the optimum attitude facial image.
8. human face posture detection system according to claim 1 is characterized in that:
It is video camera that said image/video is taken the unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012200820740U CN202472689U (en) | 2012-03-06 | 2012-03-06 | Face posture detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012200820740U CN202472689U (en) | 2012-03-06 | 2012-03-06 | Face posture detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202472689U true CN202472689U (en) | 2012-10-03 |
Family
ID=46920833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012200820740U Expired - Lifetime CN202472689U (en) | 2012-03-06 | 2012-03-06 | Face posture detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202472689U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336160A (en) * | 2015-12-02 | 2016-02-17 | 深圳市博远交通设施有限公司 | Pedestrian red light running integrated signal lamp device based on face recognition |
| CN105938603A (en) * | 2016-04-20 | 2016-09-14 | 长沙慧联智能科技有限公司 | Personnel interest degree detection system based on machine vision and personnel interest degree detection method thereof |
-
2012
- 2012-03-06 CN CN2012200820740U patent/CN202472689U/en not_active Expired - Lifetime
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336160A (en) * | 2015-12-02 | 2016-02-17 | 深圳市博远交通设施有限公司 | Pedestrian red light running integrated signal lamp device based on face recognition |
| CN105938603A (en) * | 2016-04-20 | 2016-09-14 | 长沙慧联智能科技有限公司 | Personnel interest degree detection system based on machine vision and personnel interest degree detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109819208B (en) | Intensive population security monitoring management method based on artificial intelligence dynamic monitoring | |
| US10943095B2 (en) | Methods and systems for matching extracted feature descriptors for enhanced face recognition | |
| CN109522853B (en) | Face datection and searching method towards monitor video | |
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| WO2019127273A1 (en) | Multi-person face detection method, apparatus, server, system, and storage medium | |
| CN110598535B (en) | Face recognition analysis method used in monitoring video data | |
| CN103310179A (en) | Method and system for optimal attitude detection based on face recognition technology | |
| CN104751136B (en) | A kind of multi-camera video event back jump tracking method based on recognition of face | |
| CN101587485B (en) | Face information automatic login method based on face recognition technology | |
| CN107977656A (en) | A kind of pedestrian recognition methods and system again | |
| CN102999918A (en) | Multi-target object tracking system of panorama video sequence image | |
| CN111639616A (en) | Heavy identity recognition method based on deep learning | |
| CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
| CN103605971A (en) | Method and device for capturing face images | |
| CN102542246A (en) | Abnormal face detection method for ATM (Automatic Teller Machine) | |
| CN108090428A (en) | A kind of face identification method and its system | |
| CN107516076A (en) | Portrait identification method and device | |
| CN110909612A (en) | Gait recognition method and system based on deep neural network and machine vision | |
| CN202472689U (en) | Face posture detection system | |
| CN105447463A (en) | Camera-crossing automatic tracking system for transformer station based on human body feature recognition | |
| CN110245648A (en) | The alert system of wisdom list based on Identification of Images | |
| CN112711964A (en) | Face tracking monitoring system and method | |
| CN106846527B (en) | A kind of attendance checking system based on recognition of face | |
| CN111277789A (en) | Video-based community security method and device, electronic equipment and storage medium | |
| CN113591619A (en) | Face recognition verification device based on video and verification method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CX01 | Expiry of patent term | ||
| CX01 | Expiry of patent term |
Granted publication date: 20121003 |