CN108269333A - Face identification method, application server and computer readable storage medium - Google Patents
Face identification method, application server and computer readable storage medium Download PDFInfo
- Publication number
- CN108269333A CN108269333A CN201810014831.2A CN201810014831A CN108269333A CN 108269333 A CN108269333 A CN 108269333A CN 201810014831 A CN201810014831 A CN 201810014831A CN 108269333 A CN108269333 A CN 108269333A
- Authority
- CN
- China
- Prior art keywords
- moving object
- face
- video
- image
- facial image
- 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
- 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
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- 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
Abstract
The invention discloses a kind of face identification method, this method includes:Extract the moving object video of at least one camera acquisition;The moving object video is converted as facial image frame;The facial image frame is compared with the sample in server, to determine whether effective image;If so, identification passes through, gate inhibition is opened;And if it is not, then identification failure.The present invention also provides a kind of application server and computer readable storage mediums.The moving object video that camera acquires by execute server can be parsed and be converted to facial image by face identification method provided by the invention, application server and computer readable storage medium, it is compared again with sample data, real-time capture, the efficiency for improving man face image acquiring are accomplished, attendance is completed in a state that employee does not discover, embodies humanized design and impression.
Description
Technical field
The present invention relates to a kind of technical field of face recognition more particularly to face identification method, application server and calculating
Machine readable storage medium storing program for executing.
Background technology
Face recognition technology is a kind of biological identification technology that the facial feature information based on people carries out identification, mainly
Including Face datection and recognition of face two parts.In face area of pattern recognition, face recognition technology development is more rapid,
There is corresponding practical application, such as the access control system based on recognition of face, attendance recorder, face log in.The standard of recognition of face at present
True rate can reach more than 90%.
At present, it is much to fix face location by fixing camera to acquire face in the attendance based on recognition of face
The way of picture, but in existing face attendance technology, it is desirable that employee can acquire people in designated position with specified posture
Face image, this results in customer experience very poor, and the recognition efficiency of face and accuracy are nor very high.
Invention content
In view of this, the present invention proposes a kind of face identification method, application server and computer readable storage medium, with
It solves the problems, such as the poor customer experience that existing face recognition technology occurs, discrimination and accuracy rate is low and shortcoming is intelligentized.
First, to achieve the above object, the present invention proposes a kind of face identification method, and the method comprising the steps of:
Extract the moving object video of at least one camera acquisition;
The moving object video is converted as facial image frame;
The facial image frame is compared with the sample in server, to determine whether effective image;
If so, identification passes through, gate inhibition is opened;And
If it is not, then identification fails.
Optionally, the step of moving object video of at least one camera acquisition of the extraction, specifically includes:
Detect the moving object occurred in the monitoring range of camera;
Obtain the video of the moving object of camera acquisition.
Optionally, the moving object video is converted as facial image frame, is specifically included:
By the Video Quality Metric of the moving object into video frame;
Identify the face in the video frame;
Obtain coordinate range of the face in the video frame;
Intercept the image of the coordinate range.
Optionally, the moving object video and the conversion moving object video of at least one camera acquisition of the extraction
It the step of for facial image frame, specifically includes:
Detect the moving object occurred in the monitoring range of camera;
Judge whether the camera navigates to the face of the moving object;
If so, shooting one or multiple described facial images;
If it is not, then obtain the whole video of the moving object of camera acquisition;
By the whole Video Quality Metric of the moving object into the general image of the moving object;
Facial image is identified from the general image of the moving object.
Optionally, identify that facial image specifically includes from the general image of the moving object:
Identify the face in the general image of the moving object;
Obtain coordinate range of the face in the general image;
Intercept the image of the coordinate range.
Optionally, the facial image frame is compared with the sample in server, to determine whether effective image,
It specifically includes:
The picture similarity of facial image frame and the sample image of the pre-stored user is compared, judges picture similarity
Whether preset threshold value is more than.
Optionally, this method passes through in identification, after opening gate inhibition, further includes step:
By the corresponding employee information typing attendance server of the effective image;
The attendance information of employee is shown by display.
Optionally, this method further includes step after identification failure:
Judge whether the number of recognition failures reaches preset frequency threshold value;
If it is not, then extract the moving object video of at least one camera acquisition.
If so, alarm is generated, to prompt for non-our company employee.
In addition, to achieve the above object, the present invention also provides a kind of application servers, described including memory, processor
The face identification system that can be run on the processor is stored on memory, the face identification system is by the processor
The step of face identification method as described above is realized during execution.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
Readable storage medium storing program for executing is stored with face identification system, and the face identification system can be performed by least one processor, so that institute
State the step of at least one processor performs face identification method as described above.
Compared to the prior art, face identification method proposed by the invention, application server and computer-readable storage
Medium can extract the moving object video of at least one camera acquisition, convert the moving object video as facial image
Frame, and the facial image frame is compared with the sample in server, to determine whether effective image, if so, body
Part is identified by, and opens gate inhibition, if it is not, then identification fails.The face identification method of the application is to pass through execute server
The moving object video that camera acquires is parsed and is converted to facial image frame, then be compared with sample data,
Real-time capture, the efficiency for improving man face image acquiring are accomplished, have completed attendance in a state that employee does not discover, embody
Humanized design and impression.
Description of the drawings
Fig. 1 is the schematic diagram of application server one of the present invention optionally hardware structure;
Fig. 2 is the program module schematic diagram of face identification system first embodiment of the present invention;
Fig. 3 is the program module schematic diagram of face identification system second embodiment of the present invention;
Fig. 4 is the flow diagram of the present inventor's face recognition method first embodiment;
Fig. 5 is that step S400 refines flow diagram in Fig. 4;
Fig. 6 is the flow diagram of the present inventor's face recognition method second embodiment;
Fig. 7 is the flow diagram of the present inventor's face recognition method 3rd embodiment;
Fig. 8 is the flow diagram of the present inventor's face recognition method fourth embodiment;
Fig. 9 is the flow diagram of the 5th embodiment of the present inventor's face recognition method.
Reference numeral:
Application server | 2 |
Memory | 11 |
Processor | 12 |
Network interface | 13 |
Face identification system | 200 |
Extraction module | 201 |
Modular converter | 202 |
Judgment module | 203 |
Alarm modules | 301 |
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before creative work is made
All other embodiments obtained are put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is only used for description purpose, and cannot
It is interpreted as indicating or implies its relative importance or imply the quantity of the technical characteristic indicated by indicating.Define as a result, " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present with reference to there is conflicting or can not realize when, also not the present invention claims
Protection domain within.
As shown in fig.1, it is the schematic diagram of application server 2 one of the present invention optionally hardware structure.
In the present embodiment, the application server 2 may include, but be not limited only to, and company can be in communication with each other by system bus
Connect memory 11, processor 12, network interface 13.It should be pointed out that Fig. 1 illustrates only the application clothes with component 11-13
It is engaged in device 2, it should be understood that be not required for implementing all components shown, the implementation that can be substituted is more or less
Component.
Wherein, the application server 2 can be rack-mount server, blade server, tower server or cabinet
The computing devices such as formula server, which can be independent server or multiple servers are formed
Server cluster.
The memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), static random are visited
It asks memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), may be programmed read-only deposit
Reservoir (PROM), magnetic storage, disk, CD etc..In some embodiments, the memory 11 can be the application clothes
The internal storage unit of business device 2, such as the hard disk or memory of the application server 2.In further embodiments, the memory
11 can also be the plug-in type hard disk being equipped on the External memory equipment of the application server 2, such as the application server 2,
Intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash
Card) etc..Certainly, the memory 11 can also both include the internal storage unit of the application server 2 or including outside it
Portion's storage device.In the present embodiment, the memory 11 is installed on the operating system of the application server 2 commonly used in storage
With types of applications software, such as program code of face identification system 200 etc..In addition, the memory 11 can be also used for temporarily
When store the Various types of data that has exported or will export.
The processor 12 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 12 is answered commonly used in control is described
With the overall operation of server 2.In the present embodiment, the processor 12 is used to run the program stored in the memory 11
Code or processing data, such as run described face identification system 200 etc..
The network interface 13 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established between the application server 2 and other electronic equipments.
So far, oneself is through describing the hardware configuration and function of relevant device of the present invention in detail.In the following, above-mentioned introduction will be based on
It is proposed each embodiment of the present invention.
First, the present invention proposes a kind of face identification system 200.
As shown in fig.2, it is the Program modual graph of 200 first embodiment of face identification system of the present invention.
In the present embodiment, the face identification system 200 includes a series of computer journey being stored on memory 11
Sequence instructs, and when the computer program instructions are performed by processor 12, can realize the recognition of face behaviour of various embodiments of the present invention
Make.In some embodiments, the specific operation realized based on the computer program instructions each section, face identification system
200 can be divided into one or more modules.For example, in fig. 2, the face identification system 200, which can be divided into, to be carried
Modulus block 201, modular converter 202 and judgment module 203.Wherein:
The extraction module 201, for extracting the moving object video of at least one camera acquisition.
The modular converter 202, for converting the moving object video as facial image frame.
Specifically, extraction module 201 includes:Detection unit 2011, acquiring unit 2012, judging unit 2013 and bat
Take the photograph unit 2014 and recognition unit 2015.Wherein:
The detection unit 2011, for detecting the moving object occurred in the monitoring range of camera;
Acquiring unit 2012, for obtaining the video identification unit 2014 of the moving object of camera acquisition.
That is, when detection unit 2011 detect there is moving object in the monitoring range of camera when, by obtaining
Unit 2012 is taken to obtain the video of camera acquisition moving object, server obtains the video of the moving object from camera,
2014 modular converter 202 of recognition unit is by moving object Video Quality Metric facial image frame.
Judging unit 2013, for judging whether the camera navigates to the face of the moving object;If so, it claps
Unit 2014 is taken the photograph, for shooting one or multiple described facial images;If it is not, then acquiring unit 2012, image for obtaining
The whole video of the moving object of head acquisition;
Modular converter 202 is additionally operable to the overall diagram into the moving object by the whole Video Quality Metric of the moving object
Picture;
Recognition unit 2015, for identifying facial image from the general image of the moving object.
That is, when detection unit 2011 detect there is moving object in the monitoring range of camera when, by taking the photograph
As the face of head tracing movement object, and face range is accurately positioned, can directly acquire a facial image or continuously adopts
Collect multiple facial images.If tracking, less than face, the entirety that acquiring unit 2012 obtains moving object by camera regards
Frequently, modular converter 202 knows the integral image of whole Video Quality Metric of moving object, recognition unit 2014 from general image again
Others' face image, and then identify the face of moving object.
Optionally, if identifying facial image from the video of moving object, modular converter 202 is specifically used for:
By the Video Quality Metric of the moving object into video frame;
Identify the face in the video frame;
Obtain coordinate range of the face in the video frame;
Intercept the image of the coordinate range.
Optionally, if identifying facial image from the general image of moving object, recognition unit 2015 is specifically used for:
Identify the face in the general image of the moving object;
Obtain coordinate range of the face in the general image;
Intercept the image of the coordinate range.
In the present embodiment, when recognizing face to the image collected, it is by the image tagged with the face
Facial image.Acquisition facial image is based on Face datection algorithm, and wherein Face datection refers to the frame obtained in video camera
Face is found in picture, and obtains the rectangular coordinates range of face.
Face datection algorithm includes at least conventional machines learning algorithm (such as SURF Cascade etc.) and based on depth
The algorithm (such as Faster RCNN, MTCNN etc.) of study.
When the face scanned is converted to facial image, based on the rectangular coordinates model that face is obtained when detecting face
It encloses, facial image is can obtain according to coordinate range interception rectangular area from the video frame of camera.
Optionally, the multiple cameras of carry on server, these cameras can be at the gate inhibition to enter or go out
At the gate inhibition of door, these cameras can be located at different floors, and the application is not specifically limited herein.
Optionally, server is also connect with attendance server, by the attendance number in attendance data typing attendance server
According in library.Store the samples pictures of each employee in attendance data library, the quantity of samples pictures can be one or
Multiple, multiple samples pictures can record the face image feature of each expression of employee.
Optionally, server is also connect with display screen, with real-time display attendance information etc., if staff attendance success, goes back
Show the samples pictures of employee.
Optionally, during the video of camera acquisition moving object, illumination brightness is needed to cannot be below preset threshold value, also
It is to say, needs face in uniform light, and facial contour and face can be recognized by camera.
Optionally, when multiple cameras collect the video of moving object simultaneously, the actuator processing on server is every
The video of camera all the way is that can be correctly obtained the sequence for intercepting facial image inside each actuator.
Optionally, the acquisition range of camera can be able to be that the full frame of video camera or part are drawn by parameter setting
Face, picture coverage area is by conditional decisions such as the focal length of camera lens, resolution ratio, illumination, as long as employee enters into camera
Acquisition range, it is possible to recorded video, expression, action without limiting employee etc..In addition, the application does not also limit camera
Angle, that is to say, that in the moving object video for obtaining camera acquisition constantly, video can be obtained from different directions, from
Front, left side side or right side side of moving object etc., to obtain front face image, left side facial image or right side dough figurine
Face image.
Judgment module 203, for the facial image frame to be compared with the sample in server, to determine whether
Effective image.If so, identification passes through, gate inhibition is opened, if it is not, then identification fails.
Specifically, server interception facial image frame is compared with the samples pictures in attendance data library, mainly compares
To the picture similarity of facial image frame and the sample image of the pre-stored user, it is pre- to judge whether picture similarity is more than
If threshold value, if it is, determining that the facial image frame is effective image, i.e. identification passes through, and opens gate inhibition, on the contrary,
It is invalid image then to determine the facial image frame, i.e. identification fails.
When determining server interception facial image is effective image, then illustrate that facial image is identified, using the application,
Recognition of face can generally be completed within 1 second, so the influence to employee attendance's time is very small.
It captures the picture frame of mobile network camera and verifies sample to compare sample database and the facial image of interception
Whether library is closed comprising the face and then progress identification that grab and access control system.Got remotely deploy to ensure effective monitoring and control of illegal activities, resource has
Effect utilizes, the gate identification system service of efficient stable.Quality and the double targets promoted of extension are reached.
Optionally, when identification by when, by the corresponding employee information typing attendance server of the effective image, member
Work information includes:Employee name, attendance time, date, employee department.
It is alternatively possible to the attendance information of employee is shown by display.
Optionally, while attendance information is shown, also attendance information is preserved, and is connect with attendance checking system, with
Import attendance data.
The attendance time can refer to work hours, quitting time, lunch break, overtime of employee etc..
Optionally, using the time being correctly validated as the attendance time of employee.
Optionally, when multiple cameras collect the video or image of same moving object (employee), then first to know
Do not go out facial image be effective image time as the attendance time.
When determining server interception facial image is invalid image, then illustrate not identify facial image, then attendance
Failure.
Application server provided in this embodiment extracts the movement of at least one camera acquisition by extraction module 201
Object video, 202 converting motion object video of modular converter are facial image frame, and judgment module 203 is by the facial image frame
It is compared with the sample in server, to determine whether effective image, if so, identification passes through, opens gate inhibition, if
No, then identification fails.The moving object video that camera acquires is parsed and is converted by the application server of the application
For facial image, then be compared with sample data, accomplish real-time capture, the efficiency for improving man face image acquiring,
Employee completes attendance in the state of not discovering, and embodies humanized design and impression.
As shown in fig.3, it is the Program modual graph of 200 second embodiment of face identification system of the present invention.In the present embodiment,
The face system 200 is in addition to including the extraction module 201 in first embodiment, modular converter 202 and judging mould
Except block 203, alarm modules 301 are further included.
In a second embodiment, judgment module 203, are additionally operable to judge whether the number of recognition failures reaches preset number
Threshold value.If it is not, the moving object video that extraction module 201 extracts at least one camera acquisition is then triggered, if so, touching
Activating alarm module 301, for generating alarm, to prompt for non-our company employee.
Specifically, may be to be if judgment module 203 is judged in preset frequency threshold value to employee's recognition failures
It unites failure or since the reason of video capture angle leads to the recognition failures with samples pictures, and then extracts the fortune again
The video of animal body, then facial image is obtained, and be compared with sample image.If judgment module 203 judges to be more than preset
Frequency threshold value, still to employee's recognition failures, then illustrate the employee be not our company worker possibility it is very high, then generate police
Report, causes the attention of relevant departments.
Application server in the present embodiment, when the number for judging recognition failures does not reach preset frequency threshold value, then
Again the moving object video of at least one camera acquisition is extracted, otherwise, alarm is generated, is taken with further application
Business device identification facial image.
In addition, the present invention also proposes a kind of face identification method.
As shown in fig.4, it is the flow diagram of the present inventor's face recognition method first embodiment.In the present embodiment,
According to different demands, the execution sequence of the step in flow chart shown in Fig. 4 can change, and certain steps can be omitted.
Step S400 extracts the moving object video of at least one camera acquisition.
Step S402 converts the moving object video as facial image frame.
Specifically, as shown in figure 5, step S400 further comprises:
S501 detects the moving object occurred in the monitoring range of camera;
S502 obtains the video of the moving object of camera acquisition.
That is, when detection moving object occurs in the monitoring range of camera, acquired and moved by camera
The video of object, server obtain the video of the moving object from camera, and by moving object Video Quality Metric facial image
Frame.
As shown in fig. 6, step S400 can also include:
S601 detects the moving object occurred in the monitoring range of camera;
S602, judges whether the camera navigates to the face of the moving object;If so, into S603, if
It is no, then into S604;
S603 shoots one or multiple described facial images;
S604 obtains the whole video of the moving object of camera acquisition;
S605, by the whole Video Quality Metric of the moving object into the general image of the moving object;
S606 identifies facial image from the general image of the moving object.
That is, when detection moving object occurs in the monitoring range of camera, pass through camera tracing movement
The face of object, and face range is accurately positioned can directly acquire a facial image or continuous acquisition multiple face figures
Picture.If tracking obtains the whole video of moving object by camera, by the whole Video Quality Metric of moving object less than face
Integral image, then facial image is identified from general image, and then identify the face of moving object.
If as shown in fig. 7, identifying facial image from the video of moving object, process is as follows:
S701, by the Video Quality Metric of the moving object into video frame;
S702 identifies the face in the video frame;
S703 obtains coordinate range of the face in the video frame;
S704 intercepts the image of the coordinate range.
If as shown in figure 8, identifying facial image from the general image of moving object, process is as follows:
S801 identifies the face in the general image of the moving object;
S802 obtains coordinate range of the face in the general image;
S803 intercepts the image of the coordinate range.
In the present embodiment, when recognizing face to the image collected, it is by the image tagged with the face
Facial image.Acquisition facial image is based on Face datection algorithm, and wherein Face datection refers to the frame obtained in video camera
Face is found in picture, and obtains the rectangular coordinates range of face.
Face datection algorithm includes at least conventional machines learning algorithm (such as SURF Cascade etc.) and based on depth
The algorithm (such as Faster RCNN, MTCNN etc.) of study.
When the face scanned is converted to facial image, based on the rectangular coordinates model that face is obtained when detecting face
It encloses, facial image is can obtain according to coordinate range interception rectangular area from the video frame of camera.
Optionally, the multiple cameras of carry on server, these cameras can be at the gate inhibition to enter or go out
At the gate inhibition of door, these cameras can be located at different floors, and the application is not specifically limited herein.
Optionally, server is also connect with attendance server, by the attendance number in attendance data typing attendance server
According in library.Store the samples pictures of each employee in attendance data library, the quantity of samples pictures can be one or
Multiple, multiple samples pictures can record the face image feature of each expression of employee.
Optionally, server is also connect with display screen, with real-time display attendance information etc., if staff attendance success, goes back
Show the samples pictures of employee.
Optionally, during the video of camera acquisition moving object, illumination brightness is needed to cannot be below preset threshold value, also
It is to say, needs face in uniform light, and facial contour and face can be recognized by camera.
Optionally, when multiple cameras collect the video of moving object simultaneously, the actuator processing on server is every
The video of camera all the way is that can be correctly obtained the sequence for intercepting facial image inside each actuator.
Optionally, the acquisition range of camera can be able to be that the full frame of video camera or part are drawn by parameter setting
Face, picture coverage area is by conditional decisions such as the focal length of camera lens, resolution ratio, illumination, as long as employee enters into camera
Acquisition range, it is possible to recorded video, expression, action without limiting employee etc..In addition, the application does not also limit camera
Angle, that is to say, that in the moving object video for obtaining camera acquisition constantly, video can be obtained from different directions, from
Front, left side side or right side side of moving object etc., to obtain front face image, left side facial image or right side dough figurine
Face image.
Step S404 the facial image frame is compared with the sample in server, to determine whether effectively figure
Picture.If so, S406 is entered step, if it is not, then entering step 408.
Specifically, server interception facial image frame is compared with the samples pictures in attendance data library, mainly compares
To the picture similarity of facial image frame and the sample image of the pre-stored user, it is pre- to judge whether picture similarity is more than
If threshold value, if it is, determining that the facial image frame is effective image, and enter step 404, on the contrary, it is determined that the people
Face image frame is invalid image, and enters step 406.
Step S404, identification pass through, and open gate inhibition.
Specifically, when determining server interception facial image is effective image, then illustrate that facial image is identified, use
The application, recognition of face can generally be completed within 1 second, so the influence to employee attendance's time is very small.
It captures the picture frame of mobile network camera and verifies sample to compare sample database and the facial image of interception
Whether library is closed comprising the face and then progress identification that grab and access control system.Got remotely deploy to ensure effective monitoring and control of illegal activities, resource has
Effect utilizes, the gate identification system service of efficient stable.Quality and the double targets promoted of extension are reached.
Optionally, when identification by when, by the corresponding employee information typing attendance server of the effective image, member
Work information includes:Employee name, attendance time, date, employee department.
It is alternatively possible to the attendance information of employee is shown by display.
Optionally, while attendance information is shown, also attendance information is preserved, and is connect with attendance checking system, with
Import attendance data.
The attendance time can refer to work hours, quitting time, lunch break, overtime of employee etc..
Optionally, using the time being correctly validated as the attendance time of employee.
Optionally, when multiple cameras collect the video or image of same moving object (employee), then first to know
Do not go out facial image be effective image time as the attendance time.
Step S406, identification failure.
Specifically, when determining server interception facial image is invalid image, then illustrate not identify facial image,
Then attendance fails.
As shown in figure 9, after step 406, the method further includes:
S901, judges whether the number of recognition failures reaches preset frequency threshold value.If it is not, then enter S902, if so,
Into S903.
S902 extracts the moving object video of at least one camera acquisition.
S903 generates alarm, to prompt for non-our company employee.
Specifically, if to employee's recognition failures in preset frequency threshold value, may be the system failure or by
Lead to the recognition failures with samples pictures in the reason of video capture angle, and then extract the video of the moving object again, then
Facial image is obtained, and is compared with sample image.If more than preset frequency threshold value, still to employee's recognition failures, then
Illustrate the employee be not our company worker possibility it is very high, then generate alarm, cause the attention of relevant departments.
Face identification method provided in this embodiment, the moving object video acquired by extracting at least one camera,
Converting motion object video is facial image frame, and the facial image frame is compared with the sample in server, to judge
Whether it is effective image, if so, identification passes through, opens gate inhibition, if it is not, then identification fails.The face of the application
Recognition methods is to parse the moving object video that camera acquires by execute server and be converted to facial image, then
It is compared with sample data, has accomplished real-time capture, the efficiency for improving man face image acquiring, do not discovered in employee
Attendance is completed under state, embodies humanized design and impression.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone, computer,
Server, air conditioner or network equipment etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made directly or indirectly is used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of face identification method, applied to application server, which is characterized in that the method includes the steps:
Extract the moving object video of at least one camera acquisition;
The moving object video is converted as facial image frame;
The facial image frame is compared with the sample in server, to determine whether effective image;
If so, identification passes through, gate inhibition is opened;And
If it is not, then identification fails.
2. face identification method as described in claim 1, which is characterized in that the fortune of at least one camera acquisition of extraction
It the step of animal volumetric video, specifically includes:
Detect the moving object occurred in the monitoring range of camera;
Obtain the video of the moving object of camera acquisition.
3. face identification method as described in claim 1, which is characterized in that convert the moving object video as facial image
Frame specifically includes:
By the Video Quality Metric of the moving object into video frame;
Identify the face in the video frame;
Obtain coordinate range of the face in the video frame;
Intercept the image of the coordinate range.
4. face identification method as described in claim 1, which is characterized in that the fortune of at least one camera acquisition of extraction
It the step of animal volumetric video, specifically includes:
Detect the moving object occurred in the monitoring range of camera;
Judge whether the camera navigates to the face of the moving object;
If so, shooting one or multiple described facial images;
If it is not, then obtain the whole video of the moving object of camera acquisition;
It is described to convert the step of moving object video is facial image frame, it specifically includes:
By the whole Video Quality Metric of the moving object into the general image of the moving object;
Facial image is identified from the general image of the moving object.
5. face identification method as claimed in claim 4, which is characterized in that identified from the general image of the moving object
The step of going out facial image specifically includes:
Identify the face in the general image of the moving object;
Obtain coordinate range of the face in the general image;
Intercept the image of the coordinate range.
6. such as claim 1-5 any one of them face identification methods, which is characterized in that by the facial image frame and service
Sample in device is compared, and to determine whether effective image, specifically includes:
The picture similarity of facial image frame and the sample image of the pre-stored user is compared, whether judges picture similarity
More than preset threshold value.
7. face identification method as claimed in claim 6, which is characterized in that this method passes through in identification, opens gate inhibition
Later, step is further included:
By the corresponding employee information typing attendance server of the effective image;
The attendance information of employee is shown by display.
8. face identification method as claimed in claim 6, which is characterized in that this method further includes after identification failure
Step:
Judge whether the number of recognition failures reaches preset frequency threshold value;
If it is not, then extract the moving object video of at least one camera acquisition.
If so, alarm is generated, to prompt for non-our company employee.
9. a kind of application server, which is characterized in that the application server includes memory, processor, on the memory
The face identification system that can be run on the processor is stored with, it is real when the face identification system is performed by the processor
Now the step of face identification method as described in any one of claim 1-8.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has face identification system, the people
Face identifying system can be performed by least one processor, so that at least one processor is performed as appointed in claim 1-8
The step of face identification method described in one.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810014831.2A CN108269333A (en) | 2018-01-08 | 2018-01-08 | Face identification method, application server and computer readable storage medium |
PCT/CN2018/090908 WO2019134346A1 (en) | 2018-01-08 | 2018-06-12 | Face recognition method, application server, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810014831.2A CN108269333A (en) | 2018-01-08 | 2018-01-08 | Face identification method, application server and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108269333A true CN108269333A (en) | 2018-07-10 |
Family
ID=62773203
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810014831.2A Pending CN108269333A (en) | 2018-01-08 | 2018-01-08 | Face identification method, application server and computer readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108269333A (en) |
WO (1) | WO2019134346A1 (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109064601A (en) * | 2018-07-30 | 2018-12-21 | 深圳招商建筑科技有限公司 | A kind of intelligence gate sentry robot implementation method |
CN109241833A (en) * | 2018-07-26 | 2019-01-18 | 高新兴科技集团股份有限公司 | A kind of method and apparatus of orientation direction |
CN109325436A (en) * | 2018-09-17 | 2019-02-12 | 王虹 | Face identification system and server |
CN109815810A (en) * | 2018-12-20 | 2019-05-28 | 北京以萨技术股份有限公司 | A kind of biopsy method based on single camera |
CN109829418A (en) * | 2019-01-28 | 2019-05-31 | 北京影谱科技股份有限公司 | A kind of punch card method based on figure viewed from behind feature, device and system |
CN109840565A (en) * | 2019-01-31 | 2019-06-04 | 成都大学 | A kind of blink detection method based on eye contour feature point aspect ratio |
CN109919003A (en) * | 2019-01-23 | 2019-06-21 | 平安科技(深圳)有限公司 | Face identification method, terminal device and computer readable storage medium |
CN109948456A (en) * | 2019-02-26 | 2019-06-28 | 北京华夏电通科技有限公司 | Face identification method and device applied to digital court |
CN110032929A (en) * | 2019-03-01 | 2019-07-19 | 广东天波信息技术股份有限公司 | A kind of Work attendance method and device based on image recognition |
CN110458062A (en) * | 2019-07-30 | 2019-11-15 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment and storage medium |
WO2020024354A1 (en) * | 2018-08-02 | 2020-02-06 | 平安科技(深圳)有限公司 | Unmanned warehouse theft prevention method, device, computer device, and storage medium |
CN111161458A (en) * | 2019-12-13 | 2020-05-15 | 上海聪育智能科技有限公司 | Teaching access control management system and method based on portrait recognition |
CN111695445A (en) * | 2020-05-25 | 2020-09-22 | 深圳丽泽智能科技有限公司 | Face recognition method, device, equipment and computer readable storage medium |
CN111860357A (en) * | 2020-07-23 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Attendance calculation method, device, terminal and storage medium based on living body identification |
CN112347832A (en) * | 2020-06-12 | 2021-02-09 | 深圳Tcl新技术有限公司 | Unlocking method, device and equipment based on face recognition and computer storage medium |
CN113095347A (en) * | 2020-01-09 | 2021-07-09 | 舜宇光学(浙江)研究院有限公司 | Deep learning-based mark recognition method and training method, system and electronic equipment thereof |
CN113129492A (en) * | 2021-04-16 | 2021-07-16 | 腾讯科技(深圳)有限公司 | Intelligent access control method and system |
CN113239766A (en) * | 2021-04-30 | 2021-08-10 | 复旦大学 | Behavior recognition method based on deep neural network and intelligent alarm device |
CN113359496A (en) * | 2021-06-28 | 2021-09-07 | 平安普惠企业管理有限公司 | Intelligent household data control method, device, equipment and storage medium |
CN114202818A (en) * | 2021-11-12 | 2022-03-18 | 珠海大横琴科技发展有限公司 | Attendance card punching method and device |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111145413A (en) * | 2019-12-26 | 2020-05-12 | 上海电气集团数字科技有限公司 | Intelligent access control system and face recognition method thereof |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020032048A (en) * | 2000-10-25 | 2002-05-03 | 이인동 | Face cognition the preservation a means |
KR100347058B1 (en) * | 1998-11-18 | 2002-08-03 | 주식회사 신테크 | Method for photographing and recognizing a face |
WO2010012215A1 (en) * | 2008-07-28 | 2010-02-04 | 汉王科技股份有限公司 | Dual cameras face recognition device and method |
CN102332185A (en) * | 2011-08-17 | 2012-01-25 | 中国铁道科学研究院电子计算技术研究所 | L-type passage used for security inspection area face recognition |
CN202196458U (en) * | 2011-08-24 | 2012-04-18 | 苏州飞锐智能科技有限公司 | Face recognition system |
CN103226694A (en) * | 2013-03-28 | 2013-07-31 | 赵福辉 | Real-time portrait acquiring, comparing and prewarning surveillance system and using method thereof |
CN103606216A (en) * | 2013-12-11 | 2014-02-26 | 周卫荣 | School entrance guard system |
CN104091176A (en) * | 2014-07-18 | 2014-10-08 | 吴建忠 | Technology for applying figure and head portrait comparison to videos |
CN104794459A (en) * | 2015-05-07 | 2015-07-22 | 北京丰华联合科技有限公司 | Video personnel identification method |
CN106846578A (en) * | 2017-01-20 | 2017-06-13 | 贵州财经大学 | Face identification system and gate control system |
CN107506983A (en) * | 2017-08-31 | 2017-12-22 | 济南浪潮高新科技投资发展有限公司 | A kind of attendance checking system and Work attendance method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100468467C (en) * | 2006-12-01 | 2009-03-11 | 浙江工业大学 | Access control device and check on work attendance tool based on human face identification technique |
CN104463117B (en) * | 2014-12-02 | 2018-07-03 | 苏州科达科技股份有限公司 | A kind of recognition of face sample collection method and system based on video mode |
KR101909326B1 (en) * | 2015-12-08 | 2018-12-19 | 단국대학교 천안캠퍼스 산학협력단 | User interface control method and system using triangular mesh model according to the change in facial motion |
CN107524389A (en) * | 2017-08-19 | 2017-12-29 | 合肥智贤智能化科技有限公司 | A kind of hommization highly effective and safe antitheft door |
CN107506747A (en) * | 2017-09-11 | 2017-12-22 | 重庆大学 | Face identification system and method based on video data characteristic point |
-
2018
- 2018-01-08 CN CN201810014831.2A patent/CN108269333A/en active Pending
- 2018-06-12 WO PCT/CN2018/090908 patent/WO2019134346A1/en active Application Filing
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100347058B1 (en) * | 1998-11-18 | 2002-08-03 | 주식회사 신테크 | Method for photographing and recognizing a face |
KR20020032048A (en) * | 2000-10-25 | 2002-05-03 | 이인동 | Face cognition the preservation a means |
WO2010012215A1 (en) * | 2008-07-28 | 2010-02-04 | 汉王科技股份有限公司 | Dual cameras face recognition device and method |
CN102332185A (en) * | 2011-08-17 | 2012-01-25 | 中国铁道科学研究院电子计算技术研究所 | L-type passage used for security inspection area face recognition |
CN202196458U (en) * | 2011-08-24 | 2012-04-18 | 苏州飞锐智能科技有限公司 | Face recognition system |
CN103226694A (en) * | 2013-03-28 | 2013-07-31 | 赵福辉 | Real-time portrait acquiring, comparing and prewarning surveillance system and using method thereof |
CN103606216A (en) * | 2013-12-11 | 2014-02-26 | 周卫荣 | School entrance guard system |
CN104091176A (en) * | 2014-07-18 | 2014-10-08 | 吴建忠 | Technology for applying figure and head portrait comparison to videos |
CN104794459A (en) * | 2015-05-07 | 2015-07-22 | 北京丰华联合科技有限公司 | Video personnel identification method |
CN106846578A (en) * | 2017-01-20 | 2017-06-13 | 贵州财经大学 | Face identification system and gate control system |
CN107506983A (en) * | 2017-08-31 | 2017-12-22 | 济南浪潮高新科技投资发展有限公司 | A kind of attendance checking system and Work attendance method |
Non-Patent Citations (4)
Title |
---|
严严: "State-of-the-Art on Video-Based Face Recognition%基于视频的人脸识别研究进展", 《计算机学报》 * |
中国科学技术信息研究所: "《中国科学技术信息研究所论文集 2009 上》", 31 January 2013 * |
李敏跃: "人脸识别系统的研究与实现——图像获取、定位、特征提取和特征识别", 《广西科技大学学报》 * |
肖秀春: "人脸检测与面部特征提取技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241833A (en) * | 2018-07-26 | 2019-01-18 | 高新兴科技集团股份有限公司 | A kind of method and apparatus of orientation direction |
CN109064601A (en) * | 2018-07-30 | 2018-12-21 | 深圳招商建筑科技有限公司 | A kind of intelligence gate sentry robot implementation method |
CN109064601B (en) * | 2018-07-30 | 2021-12-07 | 深圳招商建筑科技有限公司 | Intelligent gate sentry robot implementation method |
WO2020024354A1 (en) * | 2018-08-02 | 2020-02-06 | 平安科技(深圳)有限公司 | Unmanned warehouse theft prevention method, device, computer device, and storage medium |
CN109325436A (en) * | 2018-09-17 | 2019-02-12 | 王虹 | Face identification system and server |
CN109815810A (en) * | 2018-12-20 | 2019-05-28 | 北京以萨技术股份有限公司 | A kind of biopsy method based on single camera |
CN109919003A (en) * | 2019-01-23 | 2019-06-21 | 平安科技(深圳)有限公司 | Face identification method, terminal device and computer readable storage medium |
CN109829418A (en) * | 2019-01-28 | 2019-05-31 | 北京影谱科技股份有限公司 | A kind of punch card method based on figure viewed from behind feature, device and system |
CN109829418B (en) * | 2019-01-28 | 2021-01-05 | 北京影谱科技股份有限公司 | Card punching method, device and system based on shadow features |
CN109840565A (en) * | 2019-01-31 | 2019-06-04 | 成都大学 | A kind of blink detection method based on eye contour feature point aspect ratio |
CN109948456A (en) * | 2019-02-26 | 2019-06-28 | 北京华夏电通科技有限公司 | Face identification method and device applied to digital court |
CN110032929A (en) * | 2019-03-01 | 2019-07-19 | 广东天波信息技术股份有限公司 | A kind of Work attendance method and device based on image recognition |
CN110458062A (en) * | 2019-07-30 | 2019-11-15 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment and storage medium |
CN111161458A (en) * | 2019-12-13 | 2020-05-15 | 上海聪育智能科技有限公司 | Teaching access control management system and method based on portrait recognition |
CN113095347A (en) * | 2020-01-09 | 2021-07-09 | 舜宇光学(浙江)研究院有限公司 | Deep learning-based mark recognition method and training method, system and electronic equipment thereof |
CN111695445A (en) * | 2020-05-25 | 2020-09-22 | 深圳丽泽智能科技有限公司 | Face recognition method, device, equipment and computer readable storage medium |
CN112347832A (en) * | 2020-06-12 | 2021-02-09 | 深圳Tcl新技术有限公司 | Unlocking method, device and equipment based on face recognition and computer storage medium |
CN112347832B (en) * | 2020-06-12 | 2024-02-09 | 深圳Tcl新技术有限公司 | Unlocking method, device, equipment and computer storage medium based on face recognition |
CN111860357A (en) * | 2020-07-23 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Attendance calculation method, device, terminal and storage medium based on living body identification |
CN113129492A (en) * | 2021-04-16 | 2021-07-16 | 腾讯科技(深圳)有限公司 | Intelligent access control method and system |
CN113239766A (en) * | 2021-04-30 | 2021-08-10 | 复旦大学 | Behavior recognition method based on deep neural network and intelligent alarm device |
CN113359496A (en) * | 2021-06-28 | 2021-09-07 | 平安普惠企业管理有限公司 | Intelligent household data control method, device, equipment and storage medium |
CN114202818A (en) * | 2021-11-12 | 2022-03-18 | 珠海大横琴科技发展有限公司 | Attendance card punching method and device |
Also Published As
Publication number | Publication date |
---|---|
WO2019134346A1 (en) | 2019-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108269333A (en) | Face identification method, application server and computer readable storage medium | |
CN109858371B (en) | Face recognition method and device | |
CN110659397B (en) | Behavior detection method and device, electronic equipment and storage medium | |
CN109727275B (en) | Object detection method, device, system and computer readable storage medium | |
CN110414376B (en) | Method for updating face recognition model, face recognition camera and server | |
JP2015529354A (en) | Method and apparatus for face recognition | |
CN112052815B (en) | Behavior detection method and device and electronic equipment | |
CN110738178A (en) | Garden construction safety detection method and device, computer equipment and storage medium | |
CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
CN112001230A (en) | Sleeping behavior monitoring method and device, computer equipment and readable storage medium | |
RU2713876C1 (en) | Method and system for detecting alarm events when interacting with self-service device | |
CN110599129A (en) | Campus attendance checking method, device, identification terminal and system based on image tracking | |
CN110674680A (en) | Living body identification method, living body identification device and storage medium | |
CN111263955A (en) | Method and device for determining movement track of target object | |
CN114581998A (en) | Deployment and control method, system, equipment and medium based on target object association feature fusion | |
CN109697389B (en) | Identity recognition method and device | |
CN111178129A (en) | Multi-modal personnel identification method based on face and posture | |
JP6311237B2 (en) | Collation device and collation method, collation system, and computer program | |
CN110688878B (en) | Living body identification detection method, living body identification detection device, living body identification detection medium, and electronic device | |
CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
CN113869115A (en) | Method and system for processing face image | |
CN113869110A (en) | Article detection method, device, terminal and computer readable storage medium | |
CN109448193A (en) | Identity information recognition methods and device | |
CN112183167B (en) | Attendance checking method, authentication method, living body detection method, device and equipment | |
CN109583296A (en) | One kind preventing error detection method, apparatus, system and computer storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180710 |
|
RJ01 | Rejection of invention patent application after publication |