CN110110593A - Face Work attendance method, device, equipment and storage medium based on self study - Google Patents
Face Work attendance method, device, equipment and storage medium based on self study Download PDFInfo
- Publication number
- CN110110593A CN110110593A CN201910239165.7A CN201910239165A CN110110593A CN 110110593 A CN110110593 A CN 110110593A CN 201910239165 A CN201910239165 A CN 201910239165A CN 110110593 A CN110110593 A CN 110110593A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- identified
- facial image
- attendance
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face Work attendance method, device, equipment and computer readable storage medium based on self study, this method is by carrying out quality of human face image analysis to continuous frame number image data, obtain multiframe facial image to be identified, positioning feature point is carried out to facial image to be identified, and by preset convolutional neural networks model, extracts the face feature vector in every frame facial image to be identified and save to face characteristic list；Face characteristic list is clustered, face characteristic matrix is obtained；The matching analysis is carried out using face feature vector of the KNN model constructed in advance to every a line in face characteristic matrix, obtain the matching result of each face feature vector in every a line and is saved into identification similarity matrix；According to identification similarity matrix, face checking-in result is obtained, recognition of face is carried out using image of the image quality analysis method combination face characteristic clustering method to more people's multiframes, the precision of recognition of face during face attendance can be effectively improved.
Description
Technical field
The present invention relates to Computer Image Processing field more particularly to a kind of face Work attendance methods based on self study, dress
It sets, equipment and computer readable storage medium.
Background technique
Traditional attendance mode is checked card for fingerprint, and fingerprint, which is checked card, undoubtedly can cause congestion because of queuing in working peak period,
As artificial intelligence technology constantly promotes, face attendance has become reality.The important technology that face attendance is related to is face figure
As matching.
Currently, often more people appear in camera simultaneously and camera can obtain during using common camera attendance
It takes by attendance person from entering to all frame numbers to disappear from camera, can be turned one's head and be led because bowing during attendance by attendance person
Cause has multiple recognition results, and wearing spectacles cap is replaced additionally, due to Changes in weather, by attendance person will lead to discrimination reduction, knows
Other result diversification.Therefore, the precision for how improving recognition of face during common camera attendance becomes face field of attendance
Technical problem urgently to be resolved.
Summary of the invention
In view of the above-mentioned problems, the face Work attendance method that the purpose of the present invention is to provide a kind of based on self study, device, setting
Standby and storage medium can effectively improve the precision of recognition of face during face attendance, O&M cost in conjunction with picture quality
It is low.
In a first aspect, the embodiment of the invention provides a kind of face Work attendance method based on self study, comprising the following steps:
Quality of human face image analysis is carried out to the continuous frame number image data received, obtains multiframe face figure to be identified
Picture；
The facial image progress positioning feature point to be identified described in multiframe, and pass through preset convolutional neural networks model,
Extract the face feature vector in every frame facial image to be identified；
The corresponding face feature vector of facial image to be identified described in multiframe is saved to preset face characteristic list；
The face characteristic list is clustered, face characteristic matrix is obtained；Wherein, every in the face characteristic matrix
The corresponding face feature vector of facial image to be identified of the different frame numbers of the same people of one behavior；
Face feature vector progress using the KNN model constructed in advance to every a line in the face characteristic matrix
With analysis, the matching result of each face feature vector in every a line is obtained, and the matching result is saved to preparatory building
Identification similarity matrix in；
According to the identification similarity matrix, face checking-in result is obtained.
Preferably, the matching result includes name information, similarity, face characteristic information.
Preferably, described according to the identification similarity matrix, face checking-in result is obtained, is specifically included:
According to the similarity of every a line in the identification similarity matrix, to every a line in the identification similarity matrix
Matching result is ranked up, and obtains the corresponding matching result of similarity maximum value；
Using the name information in the corresponding matching result of similarity maximum value as target attendance pair, query history casting note
Record；
When the target attendance object is not broadcasted, the attendance of target attendance object is recorded and by the target attendance object
Corresponding matching result is sent to voice broadcast module and is broadcasted, sends the corresponding matching result of the target attendance object
It is shown to display module；
When the target attendance object has been broadcasted, and the difference for broadcasting time and current time is greater than preset time threshold
When, it records the attendance of target attendance object and the corresponding matching result of the target attendance object is sent to voice broadcast module
It broadcasted, the corresponding matching result of the target attendance object is sent to display module shows；
When the target attendance object has been broadcasted, and the difference for broadcasting time and current time is less than preset time threshold
When, analysis is ranked up to the similarity of next line in the identification similarity matrix.
Preferably, the method also includes:
Similarity threshold is preset when the similarity in the matching result is less than, and image quality value is greater than preset quality value
When, the corresponding facial image to be identified of the matching result is added to face characteristic training set；
Updated face characteristic training set is input to the KNN model constructed in advance and carries out model training.
Preferably, the described pair of continuous frame number image data received carries out quality of human face image analysis, obtains multiframe and waits for
It identifies facial image, specifically includes:
The continuous frame number image data is grouped in order；Wherein, every group of image data packet includes continuous N frame image, and N >
1；
Quality of human face image analysis is carried out to every group of image data, obtains the corresponding face figure to be identified of every group of image data
Picture.
Preferably, described that quality of human face image analysis is carried out to every group of image data, it is corresponding to obtain every group of image data
Facial image to be identified, specifically includes:
Calculate the face swing, facial image clarity of each frame image, facial image brightness in every group of image data
And facial image sizes values；
According to the face swing, facial image clarity of each frame image in preset weight and every group of image data,
Facial image brightness and facial image sizes values calculate the image quality value of each frame image in every group of image data；
It is corresponding as every group of image data that the corresponding image of image quality value maximum value is obtained from every group of image data
Facial image to be identified.
Preferably, the facial image to be identified described in multiframe carries out positioning feature point, specifically includes:
Using dlib facial feature points detection algorithm facial image progress positioning feature point to be identified described in multiframe.
Second aspect, a kind of face Work attendance device based on self study of the embodiment of the present invention, comprising:
Image quality analysis module, for carrying out quality of human face image analysis to the continuous frame number image data received,
Obtain multiframe facial image to be identified；
Face characteristic extraction module carries out positioning feature point for the facial image to be identified described in multiframe, and by pre-
If convolutional neural networks model, extract the face feature vector in every frame facial image to be identified；
Face characteristic list builder module, for protecting the corresponding face feature vector of facial image to be identified described in multiframe
It deposits to preset face characteristic list；
Face characteristic cluster module obtains face characteristic matrix for clustering to the face characteristic list；Its
In, in the face characteristic matrix the corresponding face characteristic of facial image to be identified of the different frame numbers of each same people of behavior to
Amount；
Face characteristic matching module, for using the KNN model constructed in advance to each in the face characteristic matrix
Capable face feature vector carries out the matching analysis, obtains the matching result of each face feature vector in every a line, and will be described
Matching result is saved into the identification similarity matrix constructed in advance；
Face checking-in result obtains module, for obtaining face checking-in result according to the identification similarity matrix.
The third aspect, a kind of face Time Attendance Device based on self study of the embodiment of the present invention, including processor, memory
And the computer program executed by the processor is stored in the memory and is configured as, the processor executes institute
The face Work attendance method based on self study as described in relation to the first aspect is realized when stating computer program.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Medium includes the computer program of storage, wherein controls the computer-readable storage medium in computer program operation
Equipment executes the face Work attendance method based on self study as described in relation to the first aspect where matter.
Above embodiments have the following beneficial effects:
By carrying out quality of human face image analysis to the continuous frame number image data received, multiframe face to be identified is obtained
Image, realize the image that high quality is obtained from continuous frame number image data as facial image to be identified, can accurately from
The image with clear face image is extracted in continuous frame number image data；The facial image progress to be identified described in multiframe is special
Levy point location, and by preset convolutional neural networks model, extract face characteristic in every frame facial image to be identified to
Amount；The corresponding face feature vector of facial image to be identified described in multiframe is saved to preset face characteristic list；To described
Face characteristic list is clustered, and face characteristic matrix is obtained；Wherein, each same people of behavior in the face characteristic matrix
The corresponding face feature vector of facial image to be identified of different frame numbers, recorded in a manner of face characteristic list different people
Face feature vector in different frame facial image to be identified is simultaneously clustered, and face characteristic matrix is finally obtained, and the face is special
The corresponding face feature vector of facial image to be identified of the different frame numbers of each same people of behavior in matrix is levied, it can be right simultaneously
Multiple people carry out recognition of face simultaneously, realize more people's multiframe recognitions of face；It is special to the face using the KNN model constructed in advance
The face feature vector for levying every a line in matrix carries out the matching analysis, obtains the matching of each face feature vector in every a line
As a result, and the matching result is saved into the identification similarity matrix constructed in advance；According to the identification similarity matrix,
Face checking-in result is obtained, is carried out using image of the image quality analysis method combination face characteristic clustering method to more people's multiframes
Recognition of face, can effectively improve the precision of recognition of face during face attendance, while greatly improve the effect of face attendance
Rate, O&M cost are low.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, attached drawing needed in embodiment will be made below
Simply introduce, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram for the face Work attendance method based on self study that first embodiment of the invention provides.
Fig. 2 is the overall flow schematic diagram of face Work attendance method provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of face attendance checking system provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram for the face Work attendance device based on self study that second embodiment of the invention provides；
Fig. 5 is the structural schematic diagram for the face Time Attendance Device based on self study that third embodiment of the invention provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig.1 and 2, wherein, Fig. 1 is the face Work attendance method provided in an embodiment of the present invention based on self study
Flow diagram, Fig. 2 are the overall flow schematic diagrams of face Work attendance method provided in an embodiment of the present invention.The present invention first is implemented
Example provide a kind of face Work attendance method based on self study, can by being executed based on the face Time Attendance Device of self study, and
The following steps are included:
S11: quality of human face image analysis is carried out to the continuous frame number image data received, obtains multiframe face to be identified
Image.
In embodiments of the present invention, the face Time Attendance Device based on self study can for computer, mobile phone, tablet computer,
Access control equipment, laptop or server etc. calculate equipment, and the face Work attendance method based on self study can be used as it
In functional module it is integrated on the face Time Attendance Device based on self study, by the face attendance based on self study
Equipment executes.
In embodiments of the present invention, the face Time Attendance Device based on self study receives continuous frame number image data, needs
It is noted that the embodiment of the present invention does not do any restrictions for the acquisition modes of the target facial image, such as can lead to
It crosses the included video camera that office population place is arranged in of the face Time Attendance Device based on self study to be obtained, Huo Zhetong
Cross wired mode or wireless mode from network, the camera in office population place is set or other equipment receive the company
Continuous frame number image data.The embodiment of the present invention is analyzed by quality of human face image, is capable of the searching of quick lock in key frame images
Speed, carry out face matching by all frame number images of the attendance person from entering disappearing from camera compared to existing obtain
Process, invention significantly improves the precision that program overall operation efficiency and key images identify.
S12: the facial image progress positioning feature point to be identified described in multiframe, and pass through preset convolutional neural networks mould
Type extracts the face feature vector in every frame facial image to be identified.
It should be noted that the embodiment of the present invention for the facial image to be identified positioning feature point mode not
Any restrictions are done, such as ASM (Active Shape Model) algorithm, AAM (Active Appreance can be passed through
Model) algorithm or human face characteristic point (eyes, eyebrow in facial image to be identified are determined based on dlib Face datection algorithm
Hair, nose, mouth, face's outer profile) position, and establish face characteristic training set.The face characteristic training set is input to
Convolutional neural networks model (CNN model) is trained, and obtains the face feature vector in every frame facial image to be identified.
S13: the corresponding face feature vector of facial image to be identified described in multiframe is saved to preset face characteristic and is arranged
Table.
S14: the face characteristic list is clustered, face characteristic matrix is obtained；Wherein, the face characteristic matrix
In each same people of behavior different frame numbers the corresponding face feature vector of facial image to be identified.
In embodiments of the present invention, using CW clustering algorithm (Chinese_Whisper) in the face characteristic list
The face feature vector of every a line is clustered.CW clustering algorithm is by building non-directed graph, by each face as in non-directed graph
A node, the similarity between face passes through the corresponding similarity of one node of iterative search as the side between node
Weight is cumulative and to search classification and be clustered.The embodiment of the present invention recorded in a manner of face characteristic list different people
Face feature vector in different frame facial image to be identified is simultaneously clustered, by different frame numbers, the face characteristic of different people
Vector assigns to two-dimensional face characteristic matrix (face_matric), the difference of each same people of behavior in the face eigenmatrix
The corresponding face feature vector of facial image to be identified of frame number, then do not go together in the face eigenmatrix indicate it is to be identified not
With attendance object, recognition of face can be carried out simultaneously to multiple people simultaneously, realize more people's multiframe recognitions of face.
S15: using the KNN model that constructs in advance to the face feature vector of every a line in the face characteristic matrix into
Row the matching analysis obtains the matching result of each face feature vector in every a line, and the matching result is saved to preparatory
In the identification similarity matrix of building.
In embodiments of the present invention, before carrying out face matching further include: acquisition is by the original face figure of attendance object
Picture, and establish face training set, wherein it include the corresponding at least original facial image of same people in the face training set
With personnel's attribute information；Personnel's attribute information includes name information, job information etc..
In embodiments of the present invention, by the KNN model constructed in advance, to by step S13, S14 treated face
Feature training set is trained, wherein KNN model setting, which takes, closes on value K=2, and algorithm (algorith) uses kd tree kd_
Tree (k-dimensional tree), weight (weights) are set as distance distance, and the KNN model after being trained,
And obtain the matching result of each face feature vector in every a line.The face Time Attendance Device based on self study calculates people
The center Euclidean distance of the face feature vector of every a line in face eigenmatrix；According to the center of the face feature vector of every a line
Euclidean distance and the face training set, by nearest neighbor algorithm, face feature vector is iterated matching one by one, with from described
The acquisition of face training set is matched with the original face image set of face feature vector and its corresponding people in face characteristic matrix
Member's attribute information, is gradually reduced the quantity of sample by the Iterative matching to face feature vector as matching result, reduces
Range of search, so that it is determined that being matched with the original face image set of face feature vector in face characteristic matrix.
Further, the matching result includes name information, similarity, face characteristic information.The face characteristic information
Including face feature vector in original facial image and/or face characteristic matrix.
S16: according to the identification similarity matrix, face checking-in result is obtained.
The embodiment of the present invention, using image quality analysis method combination face characteristic clustering method to the image of more people's multiframes
Recognition of face is carried out, the precision of recognition of face during face attendance can be effectively improved, while greatling improve face attendance
Efficiency, O&M cost is low.
In an alternative embodiment, S16: according to the identification similarity matrix, face checking-in result is obtained, specifically
Include:
S161: according to the similarity of every a line in the identification similarity matrix, to every in the identification similarity matrix
The matching result of a line is ranked up, and obtains the corresponding matching result of similarity maximum value；
S162: using the name information in the corresponding matching result of similarity maximum value as target attendance pair, query history is broadcast
Report record；
S163: it when the target attendance object is not broadcasted, records the attendance of target attendance object and examines the target
The corresponding matching result of diligent object is sent to voice broadcast module and is broadcasted, ties the corresponding matching of the target attendance object
Fruit is sent to display module and is shown；
S164: when the target attendance object has been broadcasted, and the difference for broadcasting time and current time is greater than preset time
When threshold value, records the attendance of target attendance object and the corresponding matching result of the target attendance object is sent to voice broadcast
Module, which broadcasted, the corresponding matching result of the target attendance object is sent to display module shows；
S165: when the target attendance object has been broadcasted, and the difference for broadcasting time and current time is less than preset time
When threshold value, analysis is ranked up to the similarity of next line in the identification similarity matrix.
In present example, the preset time threshold is 30s.To every a line in identification similarity matrix with similarity
The size of value sorts from large to small, and taking the maximum matching result of similarity value is final recognition result, when the matching result is corresponding
Attendance object also do not broadcast or broadcast the time greater than 30s, then record attendance and voice broadcast come out, the matching result is simultaneously
It is shown in the display module of web terminal, has broadcasted or broadcasted the time when the corresponding attendance object of the matching result and be less than
30s then skips the image data for analyzing next 10 frame.The schematic block diagram of face attendance checking system is as shown in Figure 2.
In an alternative embodiment, the method also includes:
Similarity threshold is preset when the similarity in the matching result is less than, and image quality value is greater than preset quality value
When, the corresponding facial image to be identified of the matching result is added to face characteristic training set；
Updated face characteristic training set is input to the KNN model constructed in advance and carries out model training.
In embodiments of the present invention, specific limit is not done to the specific value of preset quality value and default similarity threshold
It is fixed, it can be arranged according to the actual situation, such as the value range of default similarity threshold is 80%-90%, preset quality value
Value range is the average value of image quality value summation.Facial image to be identified for identified multiframe of the embodiment of the present invention,
If similarity is less than default similarity threshold and image quality value greater than preset quality value, then by frame face figure to be identified
As face characteristic training set is added, automatic re -training CNN model promotes next accuracy of identification.
In an alternative embodiment, quality of human face image point S11: is carried out to the continuous frame number image data received
Analysis obtains multiframe facial image to be identified, specifically includes:
The continuous frame number image data is grouped in order；Wherein, every group of image data packet includes continuous N frame image, and N >
1；
Quality of human face image analysis is carried out to every group of image data, obtains the corresponding face figure to be identified of every group of image data
Picture.
In embodiments of the present invention, N=10, accordingly, the length of face characteristic list are 10.It is continuous for what is received
Frame number image data, every 10 frame image successively carry out quality of human face image analysis as one group.
It should be noted that the continuous frame number image data that the face Time Attendance Device based on self study receives is
The video data is divided into the sub-video data of several pieces regular length by video data, then passes through quality of human face image point
The target frame image of every one's share of expenses for a joint undertaking video data is screened in analysis, as facial image to be identified, it is possible to reduce calculation amount improves identification effect
Rate.
In an alternative embodiment, described that quality of human face image analysis is carried out to every group of image data, obtain every group
The corresponding facial image to be identified of image data, specifically includes:
Calculate the face swing, facial image clarity of each frame image, facial image brightness in every group of image data
And facial image sizes values；
According to the face swing, facial image clarity of each frame image in preset weight and every group of image data,
Facial image brightness and facial image sizes values calculate the image quality value of each frame image in every group of image data；
It is corresponding as every group of image data that the corresponding image of image quality value maximum value is obtained from every group of image data
Facial image to be identified.
In embodiments of the present invention, face swing r1 (the preset weight w 1=of facial image to be identified is calculated separately
1), facial image clarity q1 (preset power w2=0.8), facial image brightness c1 (preset power w3=0.6) and people
Face image sizes values s1 (preset power w4=0.9), and weighting processing is done, obtain the picture quality of a facial image to be identified
Value t:
T=(r1 × w1+q1 × w2+c1w3+s1 × w4)/(w1+w2+w3+w4).To realize in continuous video flowing frame
In can select an optimal facial image and identified, promote recognition result precision.
In an alternative embodiment, the facial image to be identified described in multiframe carries out positioning feature point, specifically
Include:
Using dlib facial feature points detection algorithm facial image progress positioning feature point to be identified described in multiframe.
Above embodiments have the following beneficial effects:
By carrying out quality of human face image analysis to the continuous frame number image data received, multiframe face to be identified is obtained
Image, realize the image that high quality is obtained from continuous frame number image data as facial image to be identified, can accurately from
The image with clear face image is extracted in continuous frame number image data；The facial image progress to be identified described in multiframe is special
Levy point location, and by preset convolutional neural networks model, extract face characteristic in every frame facial image to be identified to
Amount；The corresponding face feature vector of facial image to be identified described in multiframe is saved to preset face characteristic list；To described
Face characteristic list is clustered, and face characteristic matrix is obtained；Wherein, each same people of behavior in the face characteristic matrix
The corresponding face feature vector of facial image to be identified of different frame numbers, recorded in a manner of face characteristic list different people
Face feature vector in different frame facial image to be identified is simultaneously clustered, and face characteristic matrix is finally obtained, and the face is special
The corresponding face feature vector of facial image to be identified of the different frame numbers of each same people of behavior in matrix is levied, it can be right simultaneously
Multiple people carry out recognition of face simultaneously, realize more people's multiframe recognitions of face；It is special to the face using the KNN model constructed in advance
The face feature vector for levying every a line in matrix carries out the matching analysis, obtains the matching of each face feature vector in every a line
As a result, and the matching result is saved into the identification similarity matrix constructed in advance；According to the identification similarity matrix,
Face checking-in result is obtained, is carried out using image of the image quality analysis method combination face characteristic clustering method to more people's multiframes
Recognition of face, can effectively improve the precision of recognition of face during face attendance, while greatly improve the effect of face attendance
Rate, O&M cost are low.Further, the various face characteristic images of supplement are constantly automatically analyzed in identification process, reduce manpower at
This, carries out recognition of face comparison and continuous training pattern, lift scheme precision using KNN model.
Referring to Fig. 4, second embodiment of the invention provides a kind of face Work attendance device based on self study, comprising:
Image quality analysis module 1, for carrying out quality of human face image analysis to the continuous frame number image data received,
Obtain multiframe facial image to be identified；
Face characteristic extraction module 2 carries out positioning feature point for the facial image to be identified described in multiframe, and by pre-
If convolutional neural networks model, extract the face feature vector in every frame facial image to be identified；
Face characteristic list builder module 3 is used for the corresponding face feature vector of facial image to be identified described in multiframe
It saves to preset face characteristic list；
Face characteristic cluster module 4 obtains face characteristic matrix for clustering to the face characteristic list；Its
In, in the face characteristic matrix the corresponding face characteristic of facial image to be identified of the different frame numbers of each same people of behavior to
Amount；
Face characteristic matching module 5, for using the KNN model constructed in advance to each in the face characteristic matrix
Capable face feature vector carries out the matching analysis, obtains the matching result of each face feature vector in every a line, and will be described
Matching result is saved into the identification similarity matrix constructed in advance；
Face checking-in result obtains module 6, for obtaining face checking-in result according to the identification similarity matrix.
In an alternative embodiment, the matching result includes name information, similarity, face characteristic information.
In an alternative embodiment, the face checking-in result acquisition module 6 includes:
Sequencing of similarity unit, for the similarity according to every a line in the identification similarity matrix, to the identification
The matching result of every a line is ranked up in similarity matrix, obtains the corresponding matching result of similarity maximum value；
Historical record query unit, for being examined using the name information in the corresponding matching result of similarity maximum value as target
It is diligent right, query history casting record；
First data transmission unit, for when the target attendance object is not broadcasted, record target attendance object to be examined
It is diligent and the corresponding matching result of the target attendance object is sent to voice broadcast module is broadcasted, by the target attendance
The corresponding matching result of object is sent to display module and is shown；
Second data transmission unit for having broadcasted when the target attendance object, and broadcasts time and current time
When difference is greater than preset time threshold, records the attendance of target attendance object and tie the corresponding matching of the target attendance object
Fruit be sent to voice broadcast module broadcasted, the corresponding matching result of the target attendance object is sent to display module into
Row display；
Third data transmission unit for having broadcasted when the target attendance object, and broadcasts time and current time
When difference is less than preset time threshold, analysis is ranked up to the similarity of next line in the identification similarity matrix.
In an alternative embodiment, described device further include:
Face characteristic training set update module, for being less than default similarity threshold when the similarity in the matching result
Value, and image quality value be greater than preset quality value when, the corresponding facial image to be identified of the matching result is added to face
Feature training set；
Model training module, for updated face characteristic training set to be input to the KNN model constructed in advance
Carry out model training.
In an alternative embodiment, described image quality analysis module 1 includes:
Image grouped element, for the continuous frame number image data to be grouped in order；Wherein, every group of image data packet
Include continuous N frame image, N > 1；
Mass analysis cell obtains every group of image data for carrying out quality of human face image analysis to every group of image data
Corresponding facial image to be identified.
In an alternative embodiment, the mass analysis cell, for including:
Image parameter computing unit, for calculating the face swing of each frame image, facial image in every group of image data
Clarity, facial image brightness and facial image sizes values；
Weight calculation unit, for being rotated according to the face of each frame image in preset weight and every group of image data
Degree, facial image clarity, facial image brightness and facial image sizes values calculate each frame image in every group of image data
Image quality value；
Optical sieving unit, for obtaining the corresponding image of image quality value maximum value from every group of image data as every
The corresponding facial image to be identified of group image data.
In an alternative embodiment, face characteristic extraction module 2, for using dlib facial feature points detection algorithm
The facial image progress positioning feature point to be identified described in multiframe.
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
It is the schematic diagram for the face Time Attendance Device based on self study that third embodiment of the invention provides referring to Fig. 5.Such as figure
Shown in 5, being somebody's turn to do the face Time Attendance Device based on self study includes: at least one processor 11, such as CPU, at least one network connects
Mouth 14 or other users interface 13, memory 15, at least one communication bus 12, communication bus 12 is for realizing these components
Between connection communication.Wherein, user interface 13 optionally may include USB interface and other standards interface, wireline interface.
Network interface 14 optionally may include Wi-Fi interface and other wireless interfaces.Memory 15 may be stored comprising high-speed RAM
Device, it is also possible to it further include non-labile memory (non-volatilememory), a for example, at least magnetic disk storage.It deposits
Reservoir 15 optionally may include at least one storage device for being located remotely from aforementioned processor 11.
In some embodiments, memory 15 stores following element, executable modules or data structures, or
Their subset or their superset:
Operating system 151 includes various system programs, for realizing various basic businesses and hardware based of processing
Business；
Program 152.
Specifically, processor 11 executes base described in above-described embodiment for calling the program 152 stored in memory 15
In the face Work attendance method of self study, such as step S11 shown in FIG. 1.Alternatively, the processor executes the computer program
The function of each module/unit in the above-mentioned each Installation practice of Shi Shixian, such as image quality analysis module.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the face Time Attendance Device based on self study.
The face Time Attendance Device based on self study can be desktop PC, notebook, palm PC and cloud
Server etc. calculates equipment.The face Time Attendance Device based on self study may include, but be not limited only to, processor, memory.
It will be understood by those skilled in the art that the schematic diagram is only based on the example of the face Time Attendance Device of self study, not structure
The restriction of face Time Attendance Device based on self study in pairs may include components more more or fewer than diagram, or combine certain
A little components or different components.
Alleged processor 11 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor 11 is the control centre of the face Time Attendance Device based on self study, and various interfaces and route is utilized to connect
Connect the various pieces of the entirely face Time Attendance Device based on self study.
The memory 15 can be used for storing the computer program and/or module, the processor 11 by operation or
Computer program and/or the module stored in the memory is executed, and calls the data being stored in memory, is realized
The various functions of the face Time Attendance Device based on self study.The memory 15 can mainly include storing program area and storage
Data field, wherein storing program area can application program needed for storage program area, at least one function (for example sound plays
Function, image player function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio number according to mobile phone
According to, phone directory etc.) etc..In addition, memory 15 may include high-speed random access memory, it can also include non-volatile memories
Device, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Wherein, if the integrated module/unit of the face Time Attendance Device based on self study is with SFU software functional unit
Form realize and when sold or used as an independent product, can store in a computer readable storage medium.Base
In such understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through computer program
It is completed to instruct relevant hardware, the computer program can be stored in a computer readable storage medium, the calculating
Machine program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes
Computer program code, the computer program code can for source code form, object identification code form, executable file or certain
A little intermediate forms etc..The computer-readable medium may include: any entity that can carry the computer program code
Or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software
Distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according to making laws in jurisdiction
Requirement with patent practice carries out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, computer
Readable medium does not include electric carrier signal and telecommunication signal.
Fourth embodiment of the invention provides a kind of computer readable storage medium, the computer readable storage medium packet
Include the computer program of storage, wherein where controlling the computer readable storage medium in computer program operation
Equipment executes the face Work attendance method based on self study as in the first embodiment.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of face Work attendance method based on self study characterized by comprising
Quality of human face image analysis is carried out to the continuous frame number image data received, obtains multiframe facial image to be identified；
The facial image progress positioning feature point to be identified described in multiframe, and by preset convolutional neural networks model, it extracts
Face feature vector in every frame facial image to be identified out；
The corresponding face feature vector of facial image to be identified described in multiframe is saved to preset face characteristic list；
The face characteristic list is clustered, face characteristic matrix is obtained；Wherein, every a line in the face characteristic matrix
For the corresponding face feature vector of facial image to be identified of the different frame numbers of same people；
Matching point is carried out using face feature vector of the KNN model constructed in advance to every a line in the face characteristic matrix
Analysis, obtains the matching result of each face feature vector in every a line, and the matching result is saved to the knowledge constructed in advance
In other similarity matrix；
According to the identification similarity matrix, face checking-in result is obtained.
2. the face Work attendance method based on self study as described in claim 1, which is characterized in that the matching result includes people
Name information, similarity, face characteristic information.
3. the face Work attendance method based on self study as claimed in claim 2, which is characterized in that described according to the identification phase
Like degree matrix, face checking-in result is obtained, is specifically included:
Matching according to the similarity of every a line in the identification similarity matrix, to every a line in the identification similarity matrix
As a result it is ranked up, obtains the corresponding matching result of similarity maximum value；
Using the name information in the corresponding matching result of similarity maximum value as target attendance pair, query history casting record；
When the target attendance object is not broadcasted, records the attendance of target attendance object and correspond to the target attendance object
Matching result be sent to voice broadcast module broadcasted, the corresponding matching result of the target attendance object is sent to it is aobvious
Show that module is shown；
When the target attendance object has been broadcasted, and broadcasts the difference of time and current time greater than preset time threshold, note
It records the attendance of target attendance object and the corresponding matching result of the target attendance object is sent to voice broadcast module and carry out
The corresponding matching result of the target attendance object is sent to display module and shows by casting；
It is right when the target attendance object has been broadcasted, and broadcasts the difference of time and current time less than preset time threshold
The similarity of next line is ranked up analysis in the identification similarity matrix.
4. the face Work attendance method based on self study as claimed in claim 2, which is characterized in that the method also includes:
When the similarity in the matching result is less than default similarity threshold, and image quality value is greater than preset quality value,
The corresponding facial image to be identified of the matching result is added to face characteristic training set；
Updated face characteristic training set is input to the KNN model constructed in advance and carries out model training.
5. the face Work attendance method based on self study as described in claim 1, which is characterized in that described pair receive it is continuous
Frame number image data carries out quality of human face image analysis, obtains multiframe facial image to be identified, specifically includes:
The continuous frame number image data is grouped in order；Wherein, every group of image data packet includes continuous N frame image, N > 1；
Quality of human face image analysis is carried out to every group of image data, obtains the corresponding facial image to be identified of every group of image data.
6. the face Work attendance method based on self study as claimed in claim 5, which is characterized in that described to every group of image data
Quality of human face image analysis is carried out, the corresponding facial image to be identified of every group of image data is obtained, specifically includes:
Calculate the face swing, facial image clarity of each frame image in every group of image data, facial image brightness and
Facial image sizes values；
According to face swing, the facial image clarity, face of each frame image in preset weight and every group of image data
Image brightness and facial image sizes values calculate the image quality value of each frame image in every group of image data；
It is corresponding wait know as every group of image data that the corresponding image of image quality value maximum value is obtained from every group of image data
Others' face image.
7. the face Work attendance method based on self study as described in claim 1, which is characterized in that it is described described in multiframe wait know
Others carries out positioning feature point at face image, specifically includes:
Using d l i b facial feature points detection algorithm facial image progress positioning feature point to be identified described in multiframe.
8. a kind of face Work attendance device based on self study characterized by comprising
Image quality analysis module is obtained for carrying out quality of human face image analysis to the continuous frame number image data received
Multiframe facial image to be identified；
Face characteristic extraction module carries out positioning feature point for the facial image to be identified described in multiframe, and by preset
Convolutional neural networks model extracts the face feature vector in every frame facial image to be identified；
Face characteristic list builder module, for by the corresponding face feature vector of facial image to be identified described in multiframe save to
Preset face characteristic list；
Face characteristic cluster module obtains face characteristic matrix for clustering to the face characteristic list；Wherein, institute
State the corresponding face feature vector of facial image to be identified of the different frame numbers of each same people of behavior in face characteristic matrix；
Face characteristic matching module, for using the KNN model constructed in advance to every a line in the face characteristic matrix
Face feature vector carries out the matching analysis, obtains the matching result of each face feature vector in every a line, and by the matching
As a result it saves into the identification similarity matrix constructed in advance；
Face checking-in result obtains module, for obtaining face checking-in result according to the identification similarity matrix.
9. a kind of face Time Attendance Device based on self study, which is characterized in that including processor, memory and be stored in described
In memory and it is configured as the computer program executed by the processor, when the processor executes the computer program
Realize the face Work attendance method based on self study as claimed in any of claims 1 to 7 in one of claims.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 7 described in the face Work attendance method based on self study.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239165.7A CN110110593A (en) | 2019-03-27 | 2019-03-27 | Face Work attendance method, device, equipment and storage medium based on self study |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239165.7A CN110110593A (en) | 2019-03-27 | 2019-03-27 | Face Work attendance method, device, equipment and storage medium based on self study |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110110593A true CN110110593A (en) | 2019-08-09 |
Family
ID=67484632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910239165.7A Pending CN110110593A (en) | 2019-03-27 | 2019-03-27 | Face Work attendance method, device, equipment and storage medium based on self study |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110593A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473306A (en) * | 2019-08-15 | 2019-11-19 | 优估（上海）信息科技有限公司 | A kind of Work attendance method based on face recognition, device and system |
| CN110688892A (en) * | 2019-08-20 | 2020-01-14 | 武汉烽火众智数字技术有限责任公司 | Portrait identification alarm method and system based on data fusion technology |
| CN110728225A (en) * | 2019-10-08 | 2020-01-24 | 北京联华博创科技有限公司 | High-speed face searching method for attendance checking |
| CN110728783A (en) * | 2019-08-31 | 2020-01-24 | 苏州浪潮智能科技有限公司 | Self-correction method, system and equipment of face recognition system |
| CN111291656A (en) * | 2020-01-21 | 2020-06-16 | 杭州微洱网络科技有限公司 | Human body posture matching method for 2d image measurement in E-commerce image |
| CN111325156A (en) * | 2020-02-24 | 2020-06-23 | 北京沃东天骏信息技术有限公司 | Face recognition method, device, equipment and storage medium |
| CN111401196A (en) * | 2020-03-10 | 2020-07-10 | 珠海全志科技股份有限公司 | Method, computer device and computer readable storage medium for self-adaptive face clustering in limited space |
| CN111666862A (en) * | 2020-06-01 | 2020-09-15 | 北京软通智慧城市科技有限公司 | Attendance statistical method, device, system and storage medium |
| CN111723647A (en) * | 2020-04-29 | 2020-09-29 | 平安国际智慧城市科技股份有限公司 | Path-based face recognition method and device, computer equipment and storage medium |
| CN111860318A (en) * | 2020-07-20 | 2020-10-30 | 杭州品茗安控信息技术股份有限公司 | Construction site pedestrian loitering detection method, device, equipment and storage medium |
| CN112200924A (en) * | 2020-09-30 | 2021-01-08 | 广东技术师范大学 | Class attendance checking method and system based on face recognition |
| CN112417939A (en) * | 2019-08-21 | 2021-02-26 | 南京行者易智能交通科技有限公司 | Passenger flow OD data acquisition method and device based on image recognition, mobile terminal equipment, server and model training method |
| CN112465999A (en) * | 2020-12-29 | 2021-03-09 | 天津科技大学 | Attendance checking equipment and attendance checking system based on face and finger vein fusion recognition |
| CN112733570A (en) * | 2019-10-14 | 2021-04-30 | 北京眼神智能科技有限公司 | Glasses detection method and device, electronic equipment and storage medium |
| CN112784733A (en) * | 2021-01-21 | 2021-05-11 | 敖客星云(北京)科技发展有限公司 | Emotion recognition method and device based on online education and electronic equipment |
| CN113361366A (en) * | 2021-05-27 | 2021-09-07 | 北京百度网讯科技有限公司 | Face labeling method and device, electronic equipment and storage medium |
| CN113656422A (en) * | 2021-08-17 | 2021-11-16 | 北京百度网讯科技有限公司 | Method and device for updating human face base |
| CN113807229A (en) * | 2021-09-13 | 2021-12-17 | 深圳市巨龙创视科技有限公司 | Non-contact attendance checking device, method, equipment and storage medium for intelligent classroom |
| CN113920606A (en) * | 2021-10-09 | 2022-01-11 | 中国银行股份有限公司 | Attendance card punching method, background server and employee mobile terminal |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359368A (en) * | 2008-09-09 | 2009-02-04 | 华为技术有限公司 | Video image clustering method and system |
| CN204156985U (en) * | 2014-08-29 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | There is high-definition camera equipment and the supervisory control system of face recognition comparison function |
| CN105631430A (en) * | 2015-12-30 | 2016-06-01 | 浙江宇视科技有限公司 | Matching method and apparatus for face image |
| CN106250821A (en) * | 2016-07-20 | 2016-12-21 | 南京邮电大学 | The face identification method that a kind of cluster is classified again |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
| CN108564673A (en) * | 2018-04-13 | 2018-09-21 | 北京师范大学 | A kind of check class attendance method and system based on Global Face identification |
| CN108830980A (en) * | 2018-05-22 | 2018-11-16 | 重庆大学 | Security protection integral intelligent robot is received in Study of Intelligent Robot Control method, apparatus and attendance |
| CN108875522A (en) * | 2017-12-21 | 2018-11-23 | 北京旷视科技有限公司 | Face cluster methods, devices and systems and storage medium |
| CN109003346A (en) * | 2018-07-13 | 2018-12-14 | 河海大学 | A kind of campus Work attendance method and its system based on face recognition technology |
-
2019
- 2019-03-27 CN CN201910239165.7A patent/CN110110593A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359368A (en) * | 2008-09-09 | 2009-02-04 | 华为技术有限公司 | Video image clustering method and system |
| CN204156985U (en) * | 2014-08-29 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | There is high-definition camera equipment and the supervisory control system of face recognition comparison function |
| CN105631430A (en) * | 2015-12-30 | 2016-06-01 | 浙江宇视科技有限公司 | Matching method and apparatus for face image |
| CN106250821A (en) * | 2016-07-20 | 2016-12-21 | 南京邮电大学 | The face identification method that a kind of cluster is classified again |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
| CN108875522A (en) * | 2017-12-21 | 2018-11-23 | 北京旷视科技有限公司 | Face cluster methods, devices and systems and storage medium |
| CN108564673A (en) * | 2018-04-13 | 2018-09-21 | 北京师范大学 | A kind of check class attendance method and system based on Global Face identification |
| CN108830980A (en) * | 2018-05-22 | 2018-11-16 | 重庆大学 | Security protection integral intelligent robot is received in Study of Intelligent Robot Control method, apparatus and attendance |
| CN109003346A (en) * | 2018-07-13 | 2018-12-14 | 河海大学 | A kind of campus Work attendance method and its system based on face recognition technology |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473306A (en) * | 2019-08-15 | 2019-11-19 | 优估（上海）信息科技有限公司 | A kind of Work attendance method based on face recognition, device and system |
| CN110688892A (en) * | 2019-08-20 | 2020-01-14 | 武汉烽火众智数字技术有限责任公司 | Portrait identification alarm method and system based on data fusion technology |
| CN112417939A (en) * | 2019-08-21 | 2021-02-26 | 南京行者易智能交通科技有限公司 | Passenger flow OD data acquisition method and device based on image recognition, mobile terminal equipment, server and model training method |
| CN110728783A (en) * | 2019-08-31 | 2020-01-24 | 苏州浪潮智能科技有限公司 | Self-correction method, system and equipment of face recognition system |
| CN110728225A (en) * | 2019-10-08 | 2020-01-24 | 北京联华博创科技有限公司 | High-speed face searching method for attendance checking |
| CN110728225B (en) * | 2019-10-08 | 2022-04-19 | 北京联华博创科技有限公司 | High-speed face searching method for attendance checking |
| CN112733570B (en) * | 2019-10-14 | 2024-04-30 | 北京眼神智能科技有限公司 | Glasses detection method and device, electronic equipment and storage medium |
| CN112733570A (en) * | 2019-10-14 | 2021-04-30 | 北京眼神智能科技有限公司 | Glasses detection method and device, electronic equipment and storage medium |
| CN111291656A (en) * | 2020-01-21 | 2020-06-16 | 杭州微洱网络科技有限公司 | Human body posture matching method for 2d image measurement in E-commerce image |
| CN111291656B (en) * | 2020-01-21 | 2023-06-02 | 杭州微洱网络科技有限公司 | Human body trunk posture matching method in measurement 2d image |
| CN111325156A (en) * | 2020-02-24 | 2020-06-23 | 北京沃东天骏信息技术有限公司 | Face recognition method, device, equipment and storage medium |
| CN111325156B (en) * | 2020-02-24 | 2023-08-11 | 北京沃东天骏信息技术有限公司 | Face recognition method, device, equipment and storage medium |
| CN111401196A (en) * | 2020-03-10 | 2020-07-10 | 珠海全志科技股份有限公司 | Method, computer device and computer readable storage medium for self-adaptive face clustering in limited space |
| CN111723647A (en) * | 2020-04-29 | 2020-09-29 | 平安国际智慧城市科技股份有限公司 | Path-based face recognition method and device, computer equipment and storage medium |
| CN111723647B (en) * | 2020-04-29 | 2022-04-15 | 平安国际智慧城市科技股份有限公司 | Path-based face recognition method and device, computer equipment and storage medium |
| CN111666862A (en) * | 2020-06-01 | 2020-09-15 | 北京软通智慧城市科技有限公司 | Attendance statistical method, device, system and storage medium |
| CN111860318A (en) * | 2020-07-20 | 2020-10-30 | 杭州品茗安控信息技术股份有限公司 | Construction site pedestrian loitering detection method, device, equipment and storage medium |
| CN112200924A (en) * | 2020-09-30 | 2021-01-08 | 广东技术师范大学 | Class attendance checking method and system based on face recognition |
| CN112465999A (en) * | 2020-12-29 | 2021-03-09 | 天津科技大学 | Attendance checking equipment and attendance checking system based on face and finger vein fusion recognition |
| CN112784733A (en) * | 2021-01-21 | 2021-05-11 | 敖客星云(北京)科技发展有限公司 | Emotion recognition method and device based on online education and electronic equipment |
| CN113361366A (en) * | 2021-05-27 | 2021-09-07 | 北京百度网讯科技有限公司 | Face labeling method and device, electronic equipment and storage medium |
| CN113656422A (en) * | 2021-08-17 | 2021-11-16 | 北京百度网讯科技有限公司 | Method and device for updating human face base |
| CN113807229A (en) * | 2021-09-13 | 2021-12-17 | 深圳市巨龙创视科技有限公司 | Non-contact attendance checking device, method, equipment and storage medium for intelligent classroom |
| CN113920606A (en) * | 2021-10-09 | 2022-01-11 | 中国银行股份有限公司 | Attendance card punching method, background server and employee mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110593A (en) | Face Work attendance method, device, equipment and storage medium based on self study | |
| CN110119673A (en) | Noninductive face Work attendance method, device, equipment and storage medium | |
| CN110619423B (en) | Multitask prediction method and device, electronic equipment and storage medium | |
| CN109173263B (en) | Image data processing method and device | |
| CN109697416B (en) | Video data processing method and related device | |
| CN109117803B (en) | Face image clustering method and device, server and storage medium | |
| CN110996116B (en) | Anchor information pushing method and device, computer equipment and storage medium | |
| WO2019119505A1 (en) | Face recognition method and device, computer device and storage medium | |
| CN109376596A (en) | Face matching process, device, equipment and storage medium | |
| CN110363091A (en) | Face identification method, device, equipment and storage medium in the case of side face | |
| CN106295567A (en) | The localization method of a kind of key point and terminal | |
| CN109815936B (en) | Target object analysis method and device, computer equipment and storage medium | |
| CN104112143A (en) | Weighted hyper-sphere support vector machine algorithm based image classification method | |
| CN109271533A (en) | A kind of multimedia document retrieval method | |
| CN108897757B (en) | Photo storage method, storage medium and server | |
| CN109767757A (en) | A kind of minutes generation method and device | |
| CN108733676A (en) | The extracting method and device of video thumbnails | |
| WO2021000830A1 (en) | Face recognition method, apparatus, computer device, and storage medium | |
| WO2019119396A1 (en) | Facial expression recognition method and device | |
| CN110572570B (en) | Intelligent recognition shooting method and system for multi-person scene and storage medium | |
| CN112307886A (en) | Pedestrian re-identification method and device | |
| WO2021036309A1 (en) | Image recognition method and apparatus, computer apparatus, and storage medium | |
| CN109271930A (en) | Micro- expression recognition method, device and storage medium | |
| CN111783681A (en) | Large-scale face library recognition method, system, computer equipment and storage medium | |
| CN111091106B (en) | Image clustering method and device, storage medium and electronic device |
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: 20190809 |
|
| RJ01 | Rejection of invention patent application after publication |