CN108830559A - A kind of Work attendance method and device based on recognition of face - Google Patents
A kind of Work attendance method and device based on recognition of face Download PDFInfo
- Publication number
- CN108830559A CN108830559A CN201810557059.9A CN201810557059A CN108830559A CN 108830559 A CN108830559 A CN 108830559A CN 201810557059 A CN201810557059 A CN 201810557059A CN 108830559 A CN108830559 A CN 108830559A
- Authority
- CN
- China
- Prior art keywords
- student
- information
- attendance
- face
- class
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
-
- 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)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of Work attendance method and device based on recognition of face, including：Attendance relevant information is received, attendance relevant information includes row's class information and human image collecting information；Obtain multiple default student informations corresponding with row's class information；Wherein, each default student information includes student name and corresponding default face characteristic；When human image collecting information is video information, attendance face characteristic all in video information is extracted；Using multiple default student informations and all attendance face characteristics as foundation, class student's list and absent pupils list are got.Work attendance method and device provided by the invention based on recognition of face can quick and precisely complete attendance purpose, easy to operate, and then effectively promote attendance efficiency.
Description
Technical field
The present invention relates to data communication technology field, in particular to a kind of Work attendance method based on recognition of face and
Device.
Background technique
Student attendance is the important link of school's teaching management, and colleges and universities middle school student attendance of attending class mainly has always by the way of
Teacher calls the roll one by one on classroom carries out the mode of attendance and the mode of fixed attendance recorder progress attendance.In practice, it has been found that using
Teacher calls the roll one by one on classroom and carries out the mode of attendance, time-consuming and laborious, attendance low efficiency；Attendance is carried out using fixed attendance recorder
Mode need people line to be called the roll, pass sequentially through calling device and acquire personnel characteristics to be called the roll (recognition of face, fingerprint, rainbow
Film etc.), queuing time length, attendance low efficiency.As it can be seen that consuming time is long for existing attendance mode, attendance low efficiency.
Summary of the invention
In view of the above problems, the present invention provides a kind of Work attendance method and device based on recognition of face, can be quickly quasi-
Attendance purpose is really completed, it is easy to operate, and then effectively promote attendance efficiency.
To achieve the goals above, the present invention adopts the following technical scheme that：
First aspect present invention discloses a kind of Work attendance method based on recognition of face, including：
Attendance relevant information is received, the attendance relevant information includes row's class information and human image collecting information；
Obtain multiple default student informations corresponding with row's class information；Wherein, each default student information packet
Include student name and corresponding default face characteristic；
When the human image collecting information is video information, attendance face characteristic all in the video information is extracted；
Using the multiple default student information and all attendance face characteristics as foundation, class student's list is got
With absent pupils list.
As an alternative embodiment, in first aspect present invention, it is described when the human image collecting information is view
When frequency information, attendance face characteristic all in the video information is extracted, including：
Frame cutting process is carried out to the video information, obtains multiple frame pictures, and divide from multiple described frame pictures
All face pictures including face out；
All face pictures are normalized, multiple normalization pictures are obtained；
Extract attendance face characteristic all in multiple described normalization pictures.
As an alternative embodiment, in first aspect present invention, before the reception attendance relevant information,
The method also includes：
Obtain all row's class information, student name corresponding with each row's class information and with the student name pair
The student's photo answered；
The face characteristic that student's photo is extracted by deep learning network, as default people corresponding with student name
Face feature；
The building default student information corresponding with each row's class information.
As an alternative embodiment, in first aspect present invention, it is described with the multiple default student information
It is foundation with all attendance face characteristics, gets class student's list and absent pupils list, including：
The attendance face characteristic is matched one by one with the multiple default face characteristic, obtains the first Hash table；Wherein,
First Hash table includes the student name and multiple likelihoods corresponding with each student name；
Using first Hash table as foundation, the maximum phase in the corresponding the multiple likelihood of each student name is obtained
Like rate, the second Hash table is generated, second Hash table includes the student name and maximum corresponding with each student name
Likelihood；
The student name that likelihood in second Hash table is more than or equal to preset threshold is obtained, class student is generated to
List, and it is rejected to class student's list from the student's list that should turn out for work, obtain absent pupils list.
As an alternative embodiment, in first aspect present invention, when the human image collecting information is picture letter
When breath, flake Processing for removing and dividing processing are carried out to the pictorial information, obtain multiple segmentation pictures；
Attendance face characteristic all in multiple described segmentation pictures is extracted, and with the multiple default described in execution
Raw information and all attendance face characteristics are foundation, get class student's list and absent pupils list.
Second aspect of the present invention discloses a kind of Work attendance device based on recognition of face, including：
Receiving module, for receiving attendance relevant information, the attendance relevant information includes that row's class information and portrait are adopted
Collect information；
Module is obtained, for obtaining multiple default student informations corresponding with row's class information；Wherein, each described pre-
If student information includes student name and corresponding default face characteristic；
Face characteristic extraction module, for extracting the video information when the human image collecting information is video information
In all attendance face characteristic；
Turn out for work judgment module, for the multiple default student information and all attendance face characteristics be according to
According to getting class student's list and absent pupils list.
As an alternative embodiment, in second aspect of the present invention, the face characteristic extraction module includes：
First submodule obtains multiple frame pictures for carrying out frame cutting process to the video information, and from described more
It opens in frame picture and is partitioned into all face pictures including face；And all face pictures are normalized,
Obtain multiple normalization pictures；
Second submodule, for extracting attendance face characteristic all in multiple described normalization pictures.
As an alternative embodiment, in second aspect of the present invention, the acquisition module is also used to connect described
Before receiving attendance relevant information, obtain all row's class information, student name corresponding with each row's class information and with institute
State the corresponding student's photo of student name；
Further include：
Default characteristic extracting module, for extracting the face characteristic of student's photo by deep learning network, as
Default face characteristic corresponding with student name；
Module is constructed, for constructing the default student information corresponding with each row's class information.
Third aspect present invention discloses a kind of attendance checking system based on recognition of face, including：
Terminal device for obtaining video information or pictorial information, and sends attendance relevant information to background server,
The attendance relevant information includes row's class information and human image collecting information；
Background server for receiving attendance relevant information, and obtains multiple default corresponding with row's class information
Raw information；Wherein, each default student information includes student name and corresponding default face characteristic；With the multiple pre-
If in student information and the human image collecting information all attendance face characteristics be foundation, get class student's list and
Absent pupils list, and send the terminal device for arriving class student's list and the absent pupils list to attendance personnel.
Fourth aspect present invention discloses a kind of computer readable storage medium, is stored with disclosed in the third aspect described
The computer program used in attendance checking system based on recognition of face.
The Work attendance method and device based on recognition of face provided according to the present invention receives examine first when attendance
Diligent relevant information, the attendance relevant information include row's class information and human image collecting information；Then it obtains and row's class information pair
The multiple default student informations answered；Wherein, each default student information includes student name and corresponding default face characteristic；When
When human image collecting information is video information, then attendance face characteristic all in the video information is extracted；Again with multiple default
Raw information and all attendance face characteristics are foundation, get class student's list and absent pupils list.As it can be seen that implementing
Work attendance method and device provided by the invention based on recognition of face can quick and precisely complete attendance purpose, easy to operate, into
And effectively promote attendance efficiency.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of the scope of the invention.
Fig. 1 is a kind of flow diagram for Work attendance method based on recognition of face that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow diagram of Work attendance method based on recognition of face provided by Embodiment 2 of the present invention；
Fig. 3 is a kind of structural schematic diagram for Work attendance device based on recognition of face that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural schematic diagram for Work attendance device based on recognition of face that the embodiment of the present invention four provides；
Fig. 5 is a kind of system architecture schematic diagram of attendance checking system based on recognition of face provided by the invention.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
For the problems of the prior art, the present invention provides a kind of Work attendance method and device based on recognition of face；?
When attendance, attendance relevant information is received first, which includes row's class information and human image collecting information；So
Multiple default student informations corresponding with row's class information are obtained afterwards；Wherein, default student information includes student name and correspondence
Default face characteristic；When human image collecting information is video information, then it is special to extract attendance face all in the video information
Sign；Again using multiple default student informations and all attendance face characteristics as foundation, class student's list and absent pupils are got
List.As it can be seen that implementing the Work attendance method and device provided by the invention based on recognition of face, attendance mesh can be quick and precisely completed
, it is easy to operate, and then effectively promote attendance efficiency.Also, the technology can use relevant software or hardware realization, below
It is described by embodiment.
Embodiment 1
Referring to Fig. 1, the process that Fig. 1 is a kind of Work attendance method based on recognition of face that the embodiment of the present invention one provides is shown
It is intended to.Wherein, as shown in Figure 1, being somebody's turn to do the Work attendance method based on recognition of face may comprise steps of：
S101, attendance relevant information is received, attendance relevant information includes row's class information and human image collecting information.
In the embodiment of the present invention, the executing subject for implementing the Work attendance method based on recognition of face can be background server,
Wherein, server can be the communication resource received for managed operation quotient base station and provide the equipment of service for user, lead to
It often can be any one in file server, database server and apps server etc., the embodiment of the present invention is not
It limits.
In the embodiment of the present invention, when roll-call at school, the terminal device that teacher can be held by it, first according to reality
Border is taught course, and corresponding row's class is selected, and then long-pressing record button, shooting include the human image collecting information of all students again
Love, finally, row's class information and human image collecting information can be sent to background server by the terminal device.
As an alternative embodiment, terminal device can use File Transfer Protocol (File Transfer
Protocol, FTP) technology, row's class information and human image collecting information are sent to background server, it is simple and fast, be conducive to
Promote attendance speed.
S102, acquisition multiple default student informations corresponding with row's class information；Wherein, each default student information includes learning
Raw name and corresponding default face characteristic.
In the embodiment of the present invention, background server prestores all row's class information, row's class information include the class period,
Class appoints teacher's name, attend class class and course name etc., and the embodiment of the present invention is not construed as limiting.
As an alternative embodiment, class appoints teacher's name change section can also appoint information when uploading, with
The convenient appearance that should exchange the emergency cases such as class.
In the embodiment of the present invention, there are different curriculum schedules, in general, one in each grade each class of a school
A class of curriculum schedule, be recycled with a fixed cycle (i.e. 7 days), so, background server can be with institute of typing whole school
There is the curriculum schedule in class's a cycle, obtains and each class row's class information bank correspondingly.As an example it is assumed that one
The teacher of entitled Zhang San, when the second class in morning of Thursday be six grades two class's Chinese courses, at school before, Lao Shike
To acquire the human image collecting information of six grades two classes of all students by its hand-held terminal device, then terminal device can be with
The human image collecting information and row's class information are sent to background server, which includes (08 point of Thursday of the class period
50 points) and the class that attends class (six grades two classes)；Then background server can be first according to (six grades two classes) acquisitions of class of attending class
Then curriculum schedule in a cycle of the class is determined currently further according to the class period (Thursday 08 point 50 minutes) to attendance
Course be Thursday the second class, finally according to the curriculum schedule determine Thursday the second class be Chinese course, class appoint
Teacher's name be Zhang San, then server obtain again the student that attends class corresponding with the Chinese course list and with student on the list
The one-to-one face characteristic of name.
It should be noted that row's class information that terminal device is sent can only include the class period and the class that attends class, backstage
Server can orient the currently course to attendance according to class period and the class that attends class, and still further upload class appoints teacher's surname
Name, the information such as class and course name of attending class, can proofread current positioning result, be conducive to be promoted to current course
The accuracy of identification.
In the embodiment of the present invention, from the perspective of appointing teacher's name with class, due to each teacher, at the same time can only
For the upper class of a class, therefore, each class of a school appoints teacher's name to have a corresponding curriculum schedule, and one
As for, each class appoints the corresponding curriculum schedule of teacher's name, be recycled with a fixed cycle (i.e. 7 days), so,
Background server can appoint the curriculum schedule in teacher's name a cycle with all classes of typing whole school, obtain a pair of with each teacher one
The row's class information bank answered, so, row's class information that terminal device is sent can only include the class period and class appoints teacher's name, after
Platform server can orient the currently course to attendance, the embodiment of the present invention and not make according to class period and class times teacher's name
It limits.
S103, when human image collecting information is video information, extract all attendance face characteristic in video information.
It, can be first to the video before extracting attendance face characteristic all in video information in the embodiment of the present invention
Information carries out frame segmentation, obtains plurality of pictures；Then multiple face pictures are pre-processed, i.e., is accurately marked in plurality of pictures
Position and the size of face are made, then the picture of human face region is cut into, obtains multiple face pictures.Wherein, at multiple
Position and the size of face can be gone out in picture according to Face pattern feature accurate calibration, wherein Face pattern feature can be
Histogram feature, color characteristic, template characteristic, structure feature and Haar feature etc., the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, after obtaining multiple face pictures, can also to the face picture carry out gray correction,
The image preprocessings such as noise filtering.Wherein, carrying out pretreated process to face picture includes the light compensation of facial image, ash
Transformation, histogram equalization, normalization, geometric correction, filtering and sharpening etc. are spent, the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, attendance face characteristic all in video information is extracted, that is, extracts above-mentioned multiple face figures
All faces of piece characterize, and are the processes that feature modeling is carried out to face.Wherein, face characteristic extract method can for based on
The characterizing method of knowledge, characterizing method based on algebraic characteristic or statistical learning etc.；Meanwhile extracted attendance face characteristic can
Think visual signature, pixels statistics feature, facial image transformation coefficient feature, facial image algebraic characteristic etc., the present invention is implemented
Example is not construed as limiting.
Own as an alternative embodiment, can be extracted using Knowledge based engineering characterizing method in video information
Attendance face characteristic.Face is locally made of eyes, nose, mouth, chin etc., to these parts and structural relation between them
Geometric description, can be used as identification face important feature.First according to the shape description of each organ of face in face picture
The distance between data and each organ characteristic, characteristic component generally include Euclidean distance, curvature between characteristic point
With angle etc..
S104, using multiple default student informations and all attendance face characteristics as foundation, get class student's list and
Absent pupils list.
In the embodiment of the present invention, after getting class student's list and absent pupils list, class can also be sent to
Give birth to the terminal device of list and absent pupils list to attendance personnel.
In the embodiment of the present invention, since default face characteristic and student name correspond, it is possible to examine all
Diligent face characteristic loops through compared with the progress one by one of default face characteristic.
For example, when there are three (such as the first face characteristic, the second face characteristic and third face are special for attendance face characteristic
Sign), default face characteristic there are two when, wherein the corresponding student name of the first default face characteristic is Zhang San, the second default people
The corresponding student name of face feature is Zhang Si.Using multiple default student informations and all attendance face characteristics as foundation, obtain
When getting class student's list and absent pupils list, first by the first face characteristic, the second face characteristic and third face characteristic one
One compared with the first default face characteristic carries out matching, and the similarity obtained is followed successively by 0,69,0.81,0.52, then by first
Face characteristic, the second face characteristic and third face characteristic compared with the second default face characteristic carries out matching, obtain one by one
Similarity is followed successively by 0,1,0.3,0.2.It can be concluded that, similarity corresponding with Zhang San is 0,69,0.81,0.52 at this time, then takes
Its maximum similarity 0.81, as final identification similarity corresponding with Zhang San, similarly, with a four corresponding final identification phases
It is 0.3 like degree.
Still further, final identification similarity is compared with default similarity threshold, when judging finally to identify
When similarity is greater than default similarity threshold, it is determined that this finally identifies that the corresponding student name of similarity is to class student's surname
Name, it is on the contrary, it is determined that this finally identifies that the corresponding student name of similarity is absent pupils name.Example as above, it is similar when presetting
When degree threshold value is 0.6, the corresponding final identification similarity of Zhang San is greater than default similarity threshold, then Zhang San is to class student's surname
Name, four corresponding final identification similarities are less than default similarity threshold, then Zhang Siwei absent pupils name, then final identification
Out include all to class student name to class student's list, absent pupils list includes all absent names.
It should be noted that multiple above-mentioned face pictures include multiple pictures of the same person, then it is finally obtained to arrive class
Student's list includes multiple identical student names, so, terminal device is getting class student's list and absent pupils name
After list, duplicate removal processing can also be carried out respectively to the student name in class student's list and absent pupils list to this, obtained
Class student's list and the absent pupils list without repetition name are arrived without repetition name, then retransmits and arrives class without repetition name
Student's list and without repeating the absent pupils list of name to the terminal device of attendance personnel.
As it can be seen that implement as described in Figure 1 based on the Work attendance method of recognition of face, it can be quasi- by face recognition technology
It really is determined to class student's list and absent pupils list, attendance purpose is rapidly completed, it is easy to operate, it can effectively promote attendance
Efficiency.
Embodiment 2
Referring to Fig. 2, the process that Fig. 2 is a kind of Work attendance method based on recognition of face provided by Embodiment 2 of the present invention is shown
It is intended to.Wherein, as shown in Fig. 2, being somebody's turn to do the Work attendance method based on recognition of face may comprise steps of：
S201, all row's class information, student name corresponding with each row's class information and corresponding with student name are obtained
Student's photo.
S202, the face characteristic that student's photo is extracted by deep learning network, as corresponding with student name default
Face characteristic.
S203, building default student information corresponding with each row's class information.
In the embodiment of the present invention, all row's class information, corresponding with each row's class information can be obtained by background server
Student name and student's photo corresponding with student name.Then, background server can by deep learning network from
Face characteristic is extracted in student's photo corresponding with student name, as default face characteristic corresponding with the student name.
Finally, the default student information of each student can also be associated with each row's class information.
S204, attendance relevant information is received, attendance relevant information includes row's class information and human image collecting information.
S205, acquisition multiple default student informations corresponding with row's class information；Wherein, each default student information includes learning
Raw name and corresponding default face characteristic.
As an alternative embodiment, after obtaining multiple default student informations corresponding with row's class information, also
It may comprise steps of：
When human image collecting information is pictorial information, flake Processing for removing and dividing processing are carried out to pictorial information, obtained
Multiple segmentation pictures.
Attendance face characteristic all in multiple segmentation pictures is extracted, and executes step S208.
S206, frame cutting process is carried out to video information, obtains multiple frame pictures, and be partitioned into institute from multiple frame pictures
There is the face picture including face.
S207, all face pictures are normalized, obtain multiple normalization pictures, and extract multiple normalization
All attendance face characteristics in picture.
In the embodiment of the present invention, implement above-mentioned steps S207~step S208, when human image collecting information is video information,
Attendance face characteristic all in video information can be extracted.
S208, attendance face characteristic is matched one by one with multiple default face characteristics, obtains the first Hash table；Wherein, institute
Stating the first Hash table includes the student name and multiple likelihoods corresponding with each student name.
S209, using the first Hash table as foundation, obtain in the corresponding multiple likelihoods of each student name maximum it is similar
Rate, generates the second Hash table, and the second Hash table includes student name and maximum likelihood corresponding with each student name.
S210, the student name that likelihood in the second Hash table is more than or equal to preset threshold is obtained, is generated to class
Raw list, and it is rejected to class student's list from the student's list that should turn out for work, obtain absent pupils list.
In the embodiment of the present invention, when maximum likelihood is 1, which can be set to 0.8,0.75,0.6 etc.,
Meanwhile the preset threshold can carry out unified setting by management equipment by teaching management person, can also pass through terminal by teacher
Equipment is configured, and the embodiment of the present invention is not construed as limiting.
As it can be seen that implementing quick and precisely complete attendance mesh as described in Figure 2 based on the Work attendance method of recognition of face
, it is easy to operate, and then effectively promote attendance efficiency.
Embodiment 3
Referring to Fig. 3, the structure that Fig. 3 is a kind of Work attendance device based on recognition of face that the embodiment of the present invention three provides is shown
It is intended to.Wherein, as shown in figure 3, the Work attendance device based on recognition of face includes：
Receiving module 301, for receiving attendance relevant information, attendance relevant information includes row's class information and human image collecting
Information.
Module 302 is obtained, multiple default student informations corresponding with row's class information are obtained；Wherein, each default student believes
Breath includes student name and corresponding default face characteristic.
Face characteristic extraction module 303, for extracting in video information and owning when human image collecting information is video information
Attendance face characteristic.
It turns out for work judgment module 304, for obtaining using multiple default student informations and all attendance face characteristics as foundation
To class student's list and absent pupils list.
As it can be seen that implement as described in Figure 3 based on the Work attendance device of recognition of face, it can be quasi- by face recognition technology
It really is determined to class student's list and absent pupils list, attendance purpose is rapidly completed, it is easy to operate, it can effectively promote attendance
Efficiency.
Embodiment 4
Referring to Fig. 4, Fig. 4 is the structural representation for the Work attendance device based on recognition of face that the embodiment of the present invention four provides
Figure.Wherein, the Work attendance device shown in Fig. 4 based on recognition of face be as shown in Figure 3 based on the Work attendance device of recognition of face into
Row optimization obtains.As shown in figure 4, face characteristic extraction module 303 includes：
First submodule 3031 obtains multiple frame pictures for carrying out frame cutting process to video information, and from multiple frames
All face pictures including face are partitioned into picture；And all face pictures are normalized, obtain multiple
Normalize picture.
Second submodule 3032, for extracting attendance face characteristic all in multiple normalization pictures.
In the embodiment of the present invention, module 302 is obtained, is also used to before receiving attendance relevant information, obtains all row's classes
The information and corresponding student name of each row's class information and student's photo corresponding with student name.
In the embodiment of the present invention, being somebody's turn to do the Work attendance device based on recognition of face, this further includes：
Default characteristic extracting module 305, for extracting the face characteristic of student's photo by deep learning network, as with
The corresponding default face characteristic of student name.
Module 306 is constructed, for constructing default student information corresponding with each row's class information, default student information includes
Student name and default face characteristic corresponding with student name.
As it can be seen that implementing quick and precisely complete attendance mesh as described in Figure 4 based on the Work attendance device of recognition of face
, it is easy to operate, and then effectively promote attendance efficiency.
In addition, the present invention also provides a kind of attendance checking systems based on recognition of face.
Referring to Fig. 5, Fig. 5 is a kind of system architecture signal of attendance checking system based on recognition of face provided by the invention
Figure.As shown in figure 5, the attendance checking system based on recognition of face includes：
Terminal device 402 for obtaining video information or pictorial information, and sends attendance relevant information to background service
Device 403, attendance relevant information include row's class information and human image collecting information.
In the embodiment of the present invention, terminal device 402 is referred to as user equipment (UE, User Equipment), movement
Platform, access terminal, subscriber unit, subscriber station, movement station, remote station, remote terminal, mobile device, terminal, wireless communication are set
Standby, user agent or user apparatus etc. specifically can be website (ST, Station), cellular phone, wireless electricity in WLAN
Words, session initiation protocol (SIP, Session Initiation Protocol) phone, wireless local loop (WLL,
Wireless Local Loop) it stands, personal digital assistant (PDA, Personal Digital Assistant), have wirelessly
The handheld device of communication function calculates equipment, the other processing equipments for being connected to radio modem, mobile unit, can wear
Any one in terminal device in the PLMN network of equipment, the mobile station in future 5G network and the following evolution etc. is worn,
The embodiment of the present invention is not construed as limiting.
Background server 403 for receiving attendance relevant information, and obtains multiple default students corresponding with row's class information
Information；Wherein, default student information includes student name and corresponding default face characteristic；And with multiple default student informations
It is foundation with human image collecting information, gets class student's list and absent pupils list, and be sent to class student's list and absence
Student's list to attendance personnel 401 terminal device 402.
In the embodiment of the present invention, it can both be carried out by operator base station between terminal device 402 and background server 403
Mobile communication (LTE), and can be communicated by physical communication lines, the embodiment of the present invention is not construed as limiting.
The present embodiment additionally provides a kind of computer storage medium, for storing the above-mentioned attendance checking system based on recognition of face
Used in computer program.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and structure in attached drawing
Figure shows the system frame in the cards of the device of multiple embodiments according to the present invention, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of module, section or code includes one or more for implementing the specified logical function holds
Row instruction.It should also be noted that function marked in the box can also be to be different from attached drawing in the implementation as replacement
Middle marked sequence occurs.For example, two continuous boxes can actually be basically executed in parallel, they sometimes can also be with
It executes in the opposite order, this depends on the function involved.It is also noted that each of structure chart and/or flow chart
The combination of box and the box in structure chart and/or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be intelligence
Can mobile phone, personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory),
Random access memory (RAM, Random Access Memory), magnetic or disk etc. be various to can store program code
Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of Work attendance method based on recognition of face, which is characterized in that including：
Attendance relevant information is received, the attendance relevant information includes row's class information and human image collecting information；
Obtain multiple default student informations corresponding with row's class information；Wherein, each default student information includes learning
Raw name and corresponding default face characteristic；
When the human image collecting information is video information, attendance face characteristic all in the video information is extracted；
Using the multiple default student information and all attendance face characteristics as foundation, gets class student's list and lack
Seat student's list.
2. the Work attendance method according to claim 1 based on recognition of face, which is characterized in that described to work as the human image collecting
When information is video information, attendance face characteristic all in the video information is extracted, including：
Frame cutting process is carried out to the video information, obtains multiple frame pictures, and be partitioned into institute from multiple described frame pictures
There is the face picture including face；
All face pictures are normalized, multiple normalization pictures are obtained；
Extract attendance face characteristic all in multiple described normalization pictures.
3. the Work attendance method according to claim 1 based on recognition of face, which is characterized in that related in the reception attendance
Before information, the method also includes：
Obtain all row's class information and the corresponding student name of each row's class information and corresponding with the student name
Student's photo；
The face characteristic that student's photo is extracted by deep learning network, it is special as default face corresponding with student name
Sign；
The building default student information corresponding with each row's class information.
4. the Work attendance method according to claim 1 based on recognition of face, which is characterized in that described with the multiple default
Student information and all attendance face characteristics are foundation, get class student's list and absent pupils list, including：
The attendance face characteristic is matched one by one with the multiple default face characteristic, obtains the first Hash table；Wherein, described
First Hash table includes the student name and multiple likelihoods corresponding with each student name；
Using first Hash table as foundation, the maximum obtained in the corresponding the multiple likelihood of each student name is similar
Rate, generates the second Hash table, and second Hash table includes the student name and maximum phase corresponding with each student name
Like rate；
The student name that likelihood in second Hash table is more than or equal to preset threshold is obtained, class student's name is generated to
It is single, and it is rejected to class student's list from the student's list that should turn out for work, obtain absent pupils list.
5. the Work attendance method according to claim 1 based on recognition of face, which is characterized in that
When the human image collecting information is pictorial information, flake Processing for removing and dividing processing are carried out to the pictorial information,
Obtain multiple segmentation pictures；
Attendance face characteristic all in multiple described segmentation pictures is extracted, and is believed described in execution with the multiple default student
Breath and all attendance face characteristics are foundation, get class student's list and absent pupils list.
6. a kind of Work attendance device based on recognition of face, which is characterized in that including：
Receiving module, for receiving attendance relevant information, the attendance relevant information includes row's class information and human image collecting letter
Breath；
Module is obtained, for obtaining multiple default student informations corresponding with row's class information；Wherein, each default
Raw information includes student name and corresponding default face characteristic；
Face characteristic extraction module, for extracting institute in the video information when the human image collecting information is video information
Some attendance face characteristics；
It turns out for work judgment module, for obtaining using the multiple default student information and all attendance face characteristics as foundation
Get class student's list and absent pupils list.
7. the Work attendance device according to claim 6 based on recognition of face, which is characterized in that the face characteristic extracts mould
Block includes：
First submodule obtains multiple frame pictures for carrying out frame cutting process to the video information, and from multiple described frames
All face pictures including face are partitioned into picture；And all face pictures are normalized, it obtains
Multiple normalization pictures；
Second submodule, for extracting attendance face characteristic all in multiple described normalization pictures.
8. the Work attendance device according to claim 6 based on recognition of face, which is characterized in that the acquisition module is also used
In before the reception attendance relevant information, obtaining all row's class information, student's surname corresponding with each row's class information
Name and student's photo corresponding with the student name；
Further include：
Default characteristic extracting module, for extracting the face characteristic of student's photo by deep learning network, as with
The corresponding default face characteristic of life name；
Module is constructed, for constructing the default student information corresponding with each row's class information.
9. a kind of attendance checking system based on recognition of face, which is characterized in that including：
Terminal device for obtaining video information or pictorial information, and sends attendance relevant information to background server, described
Attendance relevant information includes row's class information and human image collecting information；
Background server for receiving attendance relevant information, and obtains multiple default student's letters corresponding with row's class information
Breath；Wherein, each default student information includes student name and corresponding default face characteristic；With the multiple default
All attendance face characteristics are foundation in raw information and the human image collecting information, get class student's list and absence
Student's list, and send the terminal device for arriving class student's list and the absent pupils list to attendance personnel.
10. a kind of computer readable storage medium, which is characterized in that it is stored with as claimed in claim 9 based on recognition of face
Attendance checking system used in the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810557059.9A CN108830559A (en) | 2018-06-01 | 2018-06-01 | A kind of Work attendance method and device based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810557059.9A CN108830559A (en) | 2018-06-01 | 2018-06-01 | A kind of Work attendance method and device based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108830559A true CN108830559A (en) | 2018-11-16 |
Family
ID=64146832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810557059.9A Pending CN108830559A (en) | 2018-06-01 | 2018-06-01 | A kind of Work attendance method and device based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830559A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598809A (en) * | 2018-12-05 | 2019-04-09 | 上海创视通软件技术有限公司 | A kind of check class attendance method and system based on recognition of face |
| CN110310385A (en) * | 2019-06-28 | 2019-10-08 | 林心 | A kind of Intelligent campus Work attendance management system |
| CN110378261A (en) * | 2019-07-08 | 2019-10-25 | 湖北盟道信息科技有限公司 | A kind of student's recognition methods and device |
| CN110675518A (en) * | 2019-08-20 | 2020-01-10 | 吴益光 | Intelligent attendance management and interaction method and system |
| CN110807450A (en) * | 2020-01-08 | 2020-02-18 | 成都依能科技股份有限公司 | Face attendance system based on MIS system and PTZ camera |
| CN111160849A (en) * | 2019-12-10 | 2020-05-15 | 广州市十牛信息科技有限公司 | Face identification campus attendance system based on camera |
| CN111259799A (en) * | 2020-01-16 | 2020-06-09 | 广州市十牛信息科技有限公司 | Name list early warning system based on face recognition camera |
| CN111325865A (en) * | 2020-03-20 | 2020-06-23 | 广州美电恩智电子科技有限公司 | Non-inductive attendance checking method and device and equipment |
| CN111382595A (en) * | 2018-12-27 | 2020-07-07 | 深圳云天励飞技术有限公司 | Student park leaving management method and device, computer device and readable storage medium |
| CN111582143A (en) * | 2020-05-06 | 2020-08-25 | 郑州工程技术学院 | Student classroom attendance method and device based on image recognition and storage medium |
| CN111753798A (en) * | 2020-07-03 | 2020-10-09 | 重庆智者炎麒科技有限公司 | Teaching auxiliary system based on image processing and method thereof |
| CN112907775A (en) * | 2021-01-27 | 2021-06-04 | 江西中科瓦力科技有限公司 | Attendance system based on face recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204780A (en) * | 2016-07-04 | 2016-12-07 | 武汉理工大学 | A kind of based on degree of depth study and the human face identification work-attendance checking system and method for cloud service |
| CN107392179A (en) * | 2017-08-11 | 2017-11-24 | 安徽辉墨教学仪器有限公司 | A kind of teaching Work attendance method based on recognition of face |
| CN107918636A (en) * | 2017-09-07 | 2018-04-17 | 北京飞搜科技有限公司 | A kind of face method for quickly retrieving, system |
-
2018
- 2018-06-01 CN CN201810557059.9A patent/CN108830559A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204780A (en) * | 2016-07-04 | 2016-12-07 | 武汉理工大学 | A kind of based on degree of depth study and the human face identification work-attendance checking system and method for cloud service |
| CN107392179A (en) * | 2017-08-11 | 2017-11-24 | 安徽辉墨教学仪器有限公司 | A kind of teaching Work attendance method based on recognition of face |
| CN107918636A (en) * | 2017-09-07 | 2018-04-17 | 北京飞搜科技有限公司 | A kind of face method for quickly retrieving, system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598809A (en) * | 2018-12-05 | 2019-04-09 | 上海创视通软件技术有限公司 | A kind of check class attendance method and system based on recognition of face |
| CN111382595B (en) * | 2018-12-27 | 2024-03-26 | 深圳云天励飞技术有限公司 | Student off-garden management method and device, computer device and readable storage medium |
| CN111382595A (en) * | 2018-12-27 | 2020-07-07 | 深圳云天励飞技术有限公司 | Student park leaving management method and device, computer device and readable storage medium |
| CN110310385A (en) * | 2019-06-28 | 2019-10-08 | 林心 | A kind of Intelligent campus Work attendance management system |
| CN110378261B (en) * | 2019-07-08 | 2022-12-27 | 湖北盟道信息科技有限公司 | Student identification method and device |
| CN110378261A (en) * | 2019-07-08 | 2019-10-25 | 湖北盟道信息科技有限公司 | A kind of student's recognition methods and device |
| CN110675518A (en) * | 2019-08-20 | 2020-01-10 | 吴益光 | Intelligent attendance management and interaction method and system |
| CN111160849A (en) * | 2019-12-10 | 2020-05-15 | 广州市十牛信息科技有限公司 | Face identification campus attendance system based on camera |
| CN110807450A (en) * | 2020-01-08 | 2020-02-18 | 成都依能科技股份有限公司 | Face attendance system based on MIS system and PTZ camera |
| CN111259799A (en) * | 2020-01-16 | 2020-06-09 | 广州市十牛信息科技有限公司 | Name list early warning system based on face recognition camera |
| CN111325865A (en) * | 2020-03-20 | 2020-06-23 | 广州美电恩智电子科技有限公司 | Non-inductive attendance checking method and device and equipment |
| CN111582143A (en) * | 2020-05-06 | 2020-08-25 | 郑州工程技术学院 | Student classroom attendance method and device based on image recognition and storage medium |
| CN111753798A (en) * | 2020-07-03 | 2020-10-09 | 重庆智者炎麒科技有限公司 | Teaching auxiliary system based on image processing and method thereof |
| CN112907775A (en) * | 2021-01-27 | 2021-06-04 | 江西中科瓦力科技有限公司 | Attendance system based on face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830559A (en) | A kind of Work attendance method and device based on recognition of face | |
| CN110119673B (en) | Non-inductive face attendance checking method, device, equipment and storage medium | |
| CN109359521A (en) | The two-way assessment system of Classroom instruction quality based on deep learning | |
| CN110910549A (en) | Campus personnel safety management system based on deep learning and face recognition features | |
| CN206147769U (en) | Classroom management equipment of registering based on two -dimensional code and face identification | |
| CN109785400B (en) | Silhouette image manufacturing method and device, electronic equipment and storage medium | |
| CN110543811B (en) | Deep learning-based non-cooperative examination personnel management method and system | |
| CN109872406B (en) | Progressive judgment updating method and device and face card punching system | |
| CN111275345B (en) | Classroom informatization evaluation and management system and method based on deep learning | |
| CN110443183A (en) | A kind of class state monitoring method, device, storage medium and server | |
| CN108734146A (en) | Facial image Age estimation method, apparatus, computer equipment and storage medium | |
| CN112906047A (en) | Image privacy information protection system and method based on deep learning | |
| CN111382655A (en) | Hand-lifting behavior identification method and device and electronic equipment | |
| Mridha et al. | Study and analysis of implementing a smart attendance management system based on face recognition tecqnique using OpenCV and machine learning | |
| CN112149517A (en) | Face attendance checking method and system, computer equipment and storage medium | |
| CN112819984B (en) | Classroom multi-person roll-call sign-in method based on face recognition | |
| CN107203647B (en) | Student information acquisition method and device based on biological characteristics | |
| CN111611911A (en) | Class attendance checking method based on convolutional neural network and multi-face recognition | |
| Yadav et al. | Attendance Management System Based on Face Recognition Using Haar-Cascade | |
| CN112734966B (en) | Classroom roll call method integrating WiFi data and face recognition | |
| Mishra et al. | Multimodal Biometric Attendance System | |
| CN114971965A (en) | Student management system based on big data | |
| CN111339939B (en) | Attendance checking method and device based on image recognition | |
| CN103955708B (en) | Face photo library fast-reduction method for face synthesis portrait recognition | |
| Devi et al. | Iot based automatic attendance system |
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: 20181116 |
|
| RJ01 | Rejection of invention patent application after publication |