CN108960216A - A kind of detection of dynamic human face and recognition methods - Google Patents
A kind of detection of dynamic human face and recognition methods Download PDFInfo
- Publication number
- CN108960216A CN108960216A CN201811105143.3A CN201811105143A CN108960216A CN 108960216 A CN108960216 A CN 108960216A CN 201811105143 A CN201811105143 A CN 201811105143A CN 108960216 A CN108960216 A CN 108960216A
- Authority
- CN
- China
- Prior art keywords
- face
- detection
- frame
- score
- recognition methods
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of detection of dynamic human face and recognition methods, camera by being placed in foreground obtains video frame images in real time, most advanced pedestrian's body attitude detection, posture normally carries out subsequent Face datection and identification, service is targetedly provided according to final recognition result, posture exception judges whether continuously to occur multiframe exception, if continuous abnormal frame number is higher than the threshold value of setting, blows a whistle to alarm and show associated picture and check from the background convenient for backstage personnel.The present invention realizes intelligent recognition and the corresponding management and service of specific aim offer that personnel are entered and left to company by the monitoring to foreground place.
Description
[technical field]
The present invention relates to intelligent foreground[background fields, more particularly to a kind of detection of dynamic human face and recognition methods.
[background technique]
With the development of economy, the first link that company foreground is linked up as the necessary place of employee and visitor and company,
There is important roles in business administration.Traditional company foreground be mainly responsible for visitor reception, by artificial mode identify come
Visit person simultaneously receives according to visitor's identity, and due to the limitation of human brain memory, staff can not identify visitor in time
It is client or stranger, and artificial cognition excessively relies on staff, once staff job changes, is easy to visit company
Visitor's reception related work impacts.
[summary of the invention]
The object of the present invention is to provide a kind of detection of dynamic human face and recognition methods, by the monitoring to foreground place,
Intelligent recognition and the corresponding management and service of specific aim offer that personnel are entered and left to company are provided.
The present invention is solved the above problems using following technical scheme:
A kind of detection of dynamic human face and recognition methods, comprising the following steps:
Step 1: disposing camera on company foreground, obtain a series of video frame images, the detection of real-time perfoming human body attitude;
Step 2: if human body attitude is normal, jumping to step 3;If human body attitude is abnormal, step 6 is jumped to;
Step 3: carrying out Face datection, definition detects that the frame of face is face detection frame, and n frame followed by is face
Tracking frame;
Step 4: to Face datection frame defined in step 3 and face tracking frame progress face critical point detection, and according to
Corresponding video frame images and face key point carry out face quality evaluation, choose and save the highest facial image of quality;
Step 5: by the face in the highest facial image of the quality saved in step 4 and face database compare one by one into
Row recognition of face register according to recognition result and checks card or provide the prompting that welcomes the coming guests;
Step 6: if the abnormal frame number continuously occurred is higher than threshold value L, blowing a whistle and alarm and show associated picture on backstage
Convenient for backstage, personnel are checked, otherwise jump procedure 1 carries out the human body attitude detection of next video frame images.
Further, in step 2, the behaviors such as the human body exception posture is including bowing, bending over, left and right is hovered;
Further, in step 4, the face key point includes but is not limited to eye, mouth, nose, ear;According to the people detected
Calculated for pixel values evaluation index (the brightness score A 1 of face, articulation score A2, right and left eyes of face key point and video frame images
Eye opening score A 3, score A of shutting up 4, positive face score A 5 and illumination symmetrically divide A6) score value, by evaluation index choose close
Suitable weight calculation goes out face quality and divides Q, then chooses in corresponding several Q values in every group of Face datection frame and face tracking frame
The highest face of Q value saves, and wherein the score range of A1~A6 and Q is 0~100;
Further, in step 5, recognition of face obtains likelihood value after comparing, and likelihood value and threshold k are compared
Compared with if highest likelihood higher than K, determines that identified face to have personnel in face database, register checking card;If most
High likelihood is not higher than K, then determines identified face for stranger, provide voice reminder " welcoming the coming guests ".
In conclusion the beneficial effects of the present invention are provide a kind of detection of dynamic human face and recognition methods, by real-time
Monitoring enters and leaves population, and intelligent distinguishing goes out personnel's classification and targetedly provides management and service, solves traditional artificial foreground
It can not accurately and timely be distinguished caused by recognition efficiency is low and staff is flowed and service not in place etc. ask caused by relative clients
Topic.
[Detailed description of the invention]
Fig. 1 is the overview flow chart of the embodiment of the present invention 1
[specific embodiment]
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Real-time example 1
As shown in Figure 1, a kind of dynamic human face detection and recognition methods, comprise the following steps:
(1) camera for being placed in company foreground is opened, a series of video frame images are obtained by function call-back manner;
(2) human body attitude detection is carried out frame by frame step (3) are jumped to, if currently if the human body attitude of present frame is normal
When the human body attitude of frame has the behaviors such as bow, bend over, left and right is hovered, then step (6) are jumped to;
(3) Face datection is carried out frame by frame since present frame, definition detects that the frame of face is face detection frame, follows it closely
10 frames afterwards are face tracking frame;
(4) face critical point detection is carried out to all face detection frames and face tracking frame, wherein key point includes but not
It is limited to eye, mouth, nose, ear, according to the bright of the calculated for pixel values face of the video frame images of the face key point and acquisition that detect
Degree score A 1, articulation score A2, the eye opening score A 3 of right and left eyes, score A of shutting up 4, positive face score A 5 and illumination symmetrically divide A6,
Finally divide the calculation formula of Q according to face quality: Q=0.1A1+0.2A2+0.1A3+0.1A4+0.4A5+0.1A6 is calculated
Q value, wherein the score range of A1~A6 and Q is 0~100.The corresponding number in every group of Face datection frame and face tracking frame
It is chosen in a Q value and saves the highest facial image of Q value;
(5) face picture pre-saved in the highest facial image of Q value in step (4) and face database is carried out one
One comparison obtains likelihood value, and highest likelihood value and threshold value 0.7 are compared, if highest likelihood is higher than 0.7, determines
Identified face is to have personnel in face database to be employee or client and make sign-desk to when recognizing employee for the first time
Otherwise reason determines that identified face is stranger, provides voice reminder " welcoming the coming guests ";
(6) if the abnormal frame number continuously occurred is not more than 15, step (2) are jumped to, if the abnormal frame number continuously occurred
Greater than 15, then alarms and show associated picture and checked on backstage convenient for backstage personnel.
Claims (4)
1. a kind of dynamic human face detection and recognition methods, which comprises the following steps:
Step 1: disposing camera on company foreground, obtain a series of video frame images, the detection of real-time perfoming human body attitude;
Step 2: if human body attitude is normal, jumping to step 3;If human body attitude is abnormal, step 6 is jumped to;
Step 3: carrying out Face datection, definition detects that the frame of face is face detection frame, and n frame followed by is face tracking
Frame;
Step 4: face critical point detection being carried out to Face datection frame defined in step 3 and face tracking frame, and according to correspondence
Video frame images and face key point carry out face quality evaluation, choose save the highest facial image of quality;
Step 5: the face in the highest facial image of the quality saved in step 4 and face database being compared one by one and carries out people
Face identification, register according to recognition result and checks card or provide the prompting that welcomes the coming guests;
Step 6: if the abnormal frame number continuously occurred is higher than threshold value L, blowing a whistle to alarm and show associated picture and be convenient for from the background
Backstage personnel check that otherwise jump procedure 1 carries out the human body attitude detection of next video frame images.
2. a kind of dynamic human face detection as described in claim 1 and recognition methods, which is characterized in that human body in the step 2
Abnormal posture is including bowing, bending over, left and right is hovered.
3. a kind of dynamic human face detection as described in claim 1 and recognition methods, which is characterized in that in the step 4, face
Key point includes but is not limited to eye, mouth, nose, ear;According to the calculated for pixel values of the face key point and video frame images that detect
Evaluation index (brightness score A 1, articulation score A2, the eye opening score A 3 of right and left eyes, score A of shutting up 4, the positive face score of face
A5 and illumination symmetrically divide A6) score value, go out face quality by choosing suitable weight calculation to evaluation index and divide Q, then every
The highest face of Q value is chosen in group Face datection frame and face tracking frame in corresponding several Q values to save.
4. a kind of dynamic human face detection as described in claim 1 and recognition methods, which is characterized in that in the step 5, face
Identification obtains likelihood value after comparing, and likelihood value is compared with threshold k, if highest likelihood is higher than K, determines to be known
Others' face is to have personnel in face database, register checking card, if highest likelihood is not higher than K, determines identified people
Face is stranger, provides the voice reminder to welcome the coming guests.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811105143.3A CN108960216A (en) | 2018-09-21 | 2018-09-21 | A kind of detection of dynamic human face and recognition methods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811105143.3A CN108960216A (en) | 2018-09-21 | 2018-09-21 | A kind of detection of dynamic human face and recognition methods |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108960216A true CN108960216A (en) | 2018-12-07 |
Family
ID=64471992
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811105143.3A Pending CN108960216A (en) | 2018-09-21 | 2018-09-21 | A kind of detection of dynamic human face and recognition methods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108960216A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753262A (en) * | 2019-01-04 | 2019-05-14 | Oppo广东移动通信有限公司 | frame display processing method, device, terminal device and storage medium |
CN109948890A (en) * | 2019-01-30 | 2019-06-28 | 红云红河烟草(集团)有限责任公司 | Behavior evaluation method and system for workshop machine station operators |
CN111726528A (en) * | 2020-06-24 | 2020-09-29 | Oppo广东移动通信有限公司 | Camera switching method, device, terminal and computer storage medium |
CN112818913A (en) * | 2021-02-24 | 2021-05-18 | 西南石油大学 | Real-time smoking calling identification method |
CN113852653A (en) * | 2020-06-28 | 2021-12-28 | 北京三快在线科技有限公司 | Sign-in method, device, system, storage medium and electronic equipment |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010031073A1 (en) * | 2000-03-31 | 2001-10-18 | Johji Tajima | Face recognition method, recording medium thereof and face recognition device |
CN101847279A (en) * | 2010-05-20 | 2010-09-29 | 上海洪剑智能科技有限公司 | Network human face recognition system with intelligent management system and recognition method thereof |
CN104239851A (en) * | 2014-07-25 | 2014-12-24 | 重庆科技学院 | Intelligent cell inspection system based on behavior analysis and control method thereof |
CN105225394A (en) * | 2015-11-10 | 2016-01-06 | 苏州海而仕信息科技有限公司 | A kind of intelligent building method for supervising based on recognition of face |
CN205356524U (en) * | 2015-12-31 | 2016-06-29 | 3M创新有限公司 | Intelligence electron cat eye system based on identification |
CN205594741U (en) * | 2015-12-31 | 2016-09-21 | 3M创新有限公司 | Intelligent access control system based on identification |
CN106373240A (en) * | 2016-09-14 | 2017-02-01 | 浙江维融电子科技股份有限公司 | Intelligent monitoring system of self-service bank and monitoring method thereof |
CN107292240A (en) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | It is a kind of that people's method and system are looked for based on face and human bioequivalence |
CN107393073A (en) * | 2017-07-20 | 2017-11-24 | 克立司帝控制***(上海)有限公司 | Gate inhibition's monitoring control system and method based on image recognition technology |
CN107679504A (en) * | 2017-10-13 | 2018-02-09 | 北京奇虎科技有限公司 | Face identification method, device, equipment and storage medium based on camera scene |
CN107992739A (en) * | 2017-11-30 | 2018-05-04 | 北京旷视科技有限公司 | User authentication method, apparatus and system |
CN207440785U (en) * | 2017-06-28 | 2018-06-01 | 北京深度未来科技有限公司 | Recognition of face all-in-one machine and face identification system |
CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
-
2018
- 2018-09-21 CN CN201811105143.3A patent/CN108960216A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010031073A1 (en) * | 2000-03-31 | 2001-10-18 | Johji Tajima | Face recognition method, recording medium thereof and face recognition device |
CN101847279A (en) * | 2010-05-20 | 2010-09-29 | 上海洪剑智能科技有限公司 | Network human face recognition system with intelligent management system and recognition method thereof |
CN104239851A (en) * | 2014-07-25 | 2014-12-24 | 重庆科技学院 | Intelligent cell inspection system based on behavior analysis and control method thereof |
CN105225394A (en) * | 2015-11-10 | 2016-01-06 | 苏州海而仕信息科技有限公司 | A kind of intelligent building method for supervising based on recognition of face |
CN205356524U (en) * | 2015-12-31 | 2016-06-29 | 3M创新有限公司 | Intelligence electron cat eye system based on identification |
CN205594741U (en) * | 2015-12-31 | 2016-09-21 | 3M创新有限公司 | Intelligent access control system based on identification |
CN106373240A (en) * | 2016-09-14 | 2017-02-01 | 浙江维融电子科技股份有限公司 | Intelligent monitoring system of self-service bank and monitoring method thereof |
CN107292240A (en) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | It is a kind of that people's method and system are looked for based on face and human bioequivalence |
CN207440785U (en) * | 2017-06-28 | 2018-06-01 | 北京深度未来科技有限公司 | Recognition of face all-in-one machine and face identification system |
CN107393073A (en) * | 2017-07-20 | 2017-11-24 | 克立司帝控制***(上海)有限公司 | Gate inhibition's monitoring control system and method based on image recognition technology |
CN107679504A (en) * | 2017-10-13 | 2018-02-09 | 北京奇虎科技有限公司 | Face identification method, device, equipment and storage medium based on camera scene |
CN107992739A (en) * | 2017-11-30 | 2018-05-04 | 北京旷视科技有限公司 | User authentication method, apparatus and system |
CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753262A (en) * | 2019-01-04 | 2019-05-14 | Oppo广东移动通信有限公司 | frame display processing method, device, terminal device and storage medium |
CN109753262B (en) * | 2019-01-04 | 2022-06-28 | Oppo广东移动通信有限公司 | Frame display processing method and device, terminal equipment and storage medium |
CN109948890A (en) * | 2019-01-30 | 2019-06-28 | 红云红河烟草(集团)有限责任公司 | Behavior evaluation method and system for workshop machine station operators |
CN111726528A (en) * | 2020-06-24 | 2020-09-29 | Oppo广东移动通信有限公司 | Camera switching method, device, terminal and computer storage medium |
CN113852653A (en) * | 2020-06-28 | 2021-12-28 | 北京三快在线科技有限公司 | Sign-in method, device, system, storage medium and electronic equipment |
CN112818913A (en) * | 2021-02-24 | 2021-05-18 | 西南石油大学 | Real-time smoking calling identification method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108960216A (en) | A kind of detection of dynamic human face and recognition methods | |
CN107480658B (en) | Face recognition device and method based on multi-angle video | |
CN108549854B (en) | A kind of human face in-vivo detection method | |
CN202130312U (en) | Driver fatigue driving monitoring device | |
CN109299690B (en) | Method capable of improving video real-time face recognition precision | |
CN202257856U (en) | Driver fatigue-driving monitoring device | |
CN108009482A (en) | One kind improves recognition of face efficiency method | |
CN109409297B (en) | Identity recognition method based on dual-channel convolutional neural network | |
CN107967458A (en) | A kind of face identification method | |
CN105787472B (en) | A kind of anomaly detection method based on the study of space-time laplacian eigenmaps | |
CN110119656A (en) | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations | |
CN106250825A (en) | A kind of at the medical insurance adaptive face identification system of applications fields scape | |
CN107392112A (en) | A kind of facial expression recognizing method and its intelligent lock system of application | |
CN108294759A (en) | A kind of Driver Fatigue Detection based on CNN Eye state recognitions | |
CN106250821A (en) | The face identification method that a kind of cluster is classified again | |
CN104992148A (en) | ATM terminal human face key points partially shielding detection method based on random forest | |
CN104851140A (en) | Face recognition-based attendance access control system | |
CN107085715A (en) | A kind of television set intelligently detects the dormant system and method for user | |
CN106295474B (en) | Fatigue detection method, system and the server of deck officer | |
CN109034134A (en) | Abnormal driving behavioral value method based on multitask depth convolutional neural networks | |
CN112466024B (en) | Intelligent epidemic prevention system | |
CN109902560A (en) | A kind of fatigue driving method for early warning based on deep learning | |
CN102024145A (en) | Layered recognition method and system for disguised face | |
CN102902967A (en) | Method for positioning iris and pupil based on eye structure classification | |
CN103077378B (en) | Contactless face recognition algorithms based on extension eight neighborhood Local textural feature and system of registering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181207 |
|
WD01 | Invention patent application deemed withdrawn after publication |