CN111339939A - Attendance checking method and device based on image recognition - Google Patents
Attendance checking method and device based on image recognition Download PDFInfo
- Publication number
- CN111339939A CN111339939A CN202010118627.2A CN202010118627A CN111339939A CN 111339939 A CN111339939 A CN 111339939A CN 202010118627 A CN202010118627 A CN 202010118627A CN 111339939 A CN111339939 A CN 111339939A
- Authority
- CN
- China
- Prior art keywords
- activity
- information
- image
- attendance
- face
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an attendance checking method and device based on image recognition, wherein the method comprises the following steps: acquiring attendance data to be processed, wherein the attendance data comprises: a collective image containing a plurality of face images of users and corresponding activity information; preprocessing the collective image to identify a face image in the collective image; and performing matching operation according to the activity information and the recognized face image and pre-stored activity registration information, wherein the activity registration information comprises: user information and face images thereof needing to participate in activities; and identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data. The invention does not need to queue users in sequence to complete attendance recording, has good non-sensory experience, and does not need to complete attendance statistics manually, thereby having higher efficiency.
Description
Technical Field
The invention relates to the field of image processing, in particular to an attendance checking method and device based on image recognition.
Background
Attendance management is an important means for ensuring the teaching process of students and maintaining normal teaching order management of activities, training and course organizers. In the current traditional attendance mode, the attendance is usually carried out by means of active triggering (such as signature and roll call) of an entity card or a student, and the attendance is finished one by queuing in sequence, so that the attendance checking cost and time are increased, and meanwhile, the condition of poor noninductive experience is caused. The organization side needs to consume a certain amount of manpower and time cost to process the attendance data, so that the system has the defects of low timeliness, scattered information and easiness in error and leakage, and also has the influences of low efficiency and inaccurate statistical analysis on teaching management work to a certain extent.
Disclosure of Invention
In view of the above, the present invention provides an attendance checking method and apparatus based on image recognition, so as to solve at least one of the above-mentioned problems.
According to a first aspect of the invention, an attendance checking method based on image recognition is provided, and the method comprises the following steps: acquiring attendance data to be processed, wherein the attendance data comprises: a collective image containing a plurality of face images of users and corresponding activity information; preprocessing the collective image to identify a face image in the collective image; and performing matching operation according to the activity information and the recognized face image and pre-stored activity registration information, wherein the activity registration information comprises: user information and face images thereof needing to participate in activities; and identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
According to a second aspect of the present invention, there is provided an attendance checking apparatus based on image recognition, the apparatus comprising: the data acquisition unit is used for acquiring attendance data to be processed, and the attendance data comprises: a collective image containing a plurality of face images of users and corresponding activity information; the image recognition unit is used for preprocessing the collective image and recognizing a face image in the collective image; a matching unit configured to perform a matching operation based on the activity information and the recognized face image and pre-stored activity registration information, the activity registration information including: user information and face images thereof needing to participate in activities; and the identification unit is used for identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
According to a third aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the attendance checking method based on image recognition when executing the program.
According to a fourth aspect of the present invention, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described attendance method based on image recognition.
Compared with the prior art, the technical scheme has the advantages that users do not need to queue in sequence to complete attendance recording, the non-sensory experience is good, attendance statistics is not needed to be completed manually, and accordingly efficiency is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of an attendance method based on image recognition according to an embodiment of the present invention;
fig. 2 is a block diagram of an attendance checking apparatus based on image recognition according to an embodiment of the present invention;
fig. 3 is a block diagram of the structure of the image recognizing unit 22 according to the embodiment of the present invention;
fig. 4 is a detailed structural block diagram of an attendance checking apparatus based on image recognition according to an embodiment of the invention;
fig. 5 is a block diagram of the structure of the matching unit 23 according to the embodiment of the present invention;
fig. 6 is an exemplary block diagram of an attendance system based on face images according to an embodiment of the present invention;
fig. 7 is a block diagram of the structure of the information registration entry platform 1 according to the embodiment of the present invention;
fig. 8 is a block diagram of the configuration of the face image processing system 2 according to the embodiment of the present invention;
FIG. 9 is a block diagram of the structure of the data statistical analysis platform 3 according to the embodiment of the present invention;
FIG. 10 is a flow diagram of an initial information registration entry based on the system shown in FIG. 6, according to an embodiment of the present invention;
FIG. 11 is a flow chart of face image matching and recognition based on the system shown in FIG. 6 according to an embodiment of the present invention;
fig. 12 is a flowchart of statistical analysis of attendance data based on the system shown in fig. 6 according to an embodiment of the present invention;
FIG. 13 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In view of the problems of poor non-sensory experience, manpower consumption, time analysis and statistics and the like in the conventional attendance checking mode, the embodiment of the invention provides an attendance checking scheme based on image recognition so as to solve the problems.
Fig. 1 is a flowchart of an attendance checking method based on image recognition according to an embodiment of the present invention, and as shown in fig. 1, the method includes:
Preferably, the collective image can be acquired through the camera device, and the non-sensory experience of the user is improved.
And 102, preprocessing the collective image to identify a face image in the collective image.
Specifically, the face feature extraction operation may be performed on the preprocessed collective images based on the parallel processing mode to identify the face images therein.
103, performing matching operation according to the activity information, the recognized face image and pre-stored activity registration information, wherein the activity registration information comprises: user information and face images thereof which need to participate in activities.
And 104, identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
Compared with the prior art, the attendance recording method and device have the advantages that users do not need to queue in sequence to complete attendance recording, noninductive experience is good, attendance statistics is not needed to be completed manually, and accordingly efficiency is high.
In actual operation, when a user needs to participate in a plurality of different activities, the activity registration information can be classified based on the trained classification model; and generates activity registration information in which the activity information is classified according to the classification processing result.
For example, in the case of teaching work, a student attends a plurality of courses, and therefore, activity registration information is generated based on the courses as categories, and a correspondence relationship between the courses, the student, and a face image thereof is established.
The classification model herein may employ a KNN (K-Nearest Neighbors) model.
For the matching operation in step 103, the activity registration information of the corresponding category may be determined according to the activity information, and then the matching operation may be performed on the identified face image based on the traversal loop mechanism according to the determined activity registration information of the corresponding category.
After attendance is completed, attendance result data can be counted by activity information or user information according to a preset rule so as to facilitate later-stage checking and counting.
Based on similar inventive concepts, the embodiment of the invention further provides an attendance checking device based on image recognition, and the attendance checking device is preferably used for realizing the process in the method embodiment.
Fig. 2 is a block diagram illustrating an attendance checking apparatus based on image recognition according to an embodiment of the present invention, and as shown in fig. 2, the apparatus includes: a data acquisition unit 21, an image recognition unit 22, a matching unit 23 and an identification unit 24, wherein:
the data acquisition unit 21 is configured to acquire attendance data to be processed, where the attendance data includes: the image processing device comprises a collective image containing a plurality of face images of users and corresponding activity information. Particularly, collective images of users participating in activities can be acquired through the camera device, and therefore non-sensory user image acquisition is achieved.
And the image recognition unit 22 is used for preprocessing the collective image and recognizing the face image in the collective image.
A matching unit 23, configured to perform a matching operation according to the activity information and the recognized face image and pre-stored activity registration information, where the activity registration information includes: user information and face images thereof which need to participate in activities.
And the identification unit 24 is used for identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
The image recognition unit 22 recognizes the collective image in the attendance data acquired by the data acquisition unit 21 to obtain the face image of each user, the matching unit 23 performs matching operation on a plurality of face images based on the pre-stored activity registration information, and the identification unit 24 generates attendance result data according to the matching result.
Specifically, as shown in fig. 3, the image recognition unit 22 includes: a pre-processing module 221 and an image recognition module 222, wherein:
a preprocessing module 221, configured to preprocess the collective image;
and the image identification module 222 is used for performing a face feature extraction operation on the preprocessed collective image based on a parallel processing mode so as to identify a face image in the collective image.
In practical operation, as shown in fig. 4, the apparatus further comprises: a classification unit 25 and an activity registration information generation unit 26, wherein:
a classification unit 25, configured to, when a user needs to participate in multiple different activities, perform classification processing on the activity registration information based on a trained classification model;
an activity registration information generating unit 26 for generating activity registration information of which the category is the activity information, based on the classification processing result.
Specifically, as shown in fig. 5, the matching unit 23 includes: an activity registration information determination module 231 and a matching module 232, wherein:
an activity registration information determining module 231, configured to determine activity registration information of a corresponding category according to the activity information;
and the matching module 232 is configured to perform matching operation on the identified face image based on a traversal loop mechanism according to the determined activity registration information of the corresponding category.
With continued reference to fig. 4, the apparatus further comprises: and the counting unit 27 is used for counting attendance result data according to a preset rule by using activity information or user information.
For specific execution processes of the units and the modules, reference may be made to the description in the foregoing method embodiments, and details are not described here again.
For a better understanding of embodiments of the present invention, they are described in detail below in conjunction with the teaching scenario.
Fig. 6 is a diagram illustrating an example of an attendance system based on a face image according to an embodiment of the present invention, and as shown in fig. 6, the attendance system includes: the system comprises an information registration and entry platform 1, a face image processing system 2 and a data statistical analysis platform 3. Preferably, the face image processing system 2 has the function of the attendance checking device. The information registration and entry platform 1 can be in communication connection with the facial image processing system 2 through a mobile or wired network, and the data statistical analysis platform 3 is in communication connection with the information registration and entry platform 1 and the facial image processing system 2.
And the information registration and entry platform 1 is responsible for interaction with an operator and the facial image processing system 2, and receiving teaching information, facial image acquisition, attendance request and results. The information registration and entry platform provides a visual interaction interface for operators based on Web browsing and mobile intelligent device modes, wherein the mobile intelligent device modes include but are not limited to a mobile phone and a tablet personal computer, and the interaction modes include but are not limited to a mode of being called by a camera of the mobile intelligent device and an H5 (Web page of a mobile terminal) page information entry mode.
The face image processing system 2 is responsible for preprocessing, positioning and cutting, feature extraction, classification training, matching, recognition and the like of the received face image.
In response to the initial information registration and input, the face image processing system 2 performs preprocessing such as normalization, light enhancement/weakening, geometric correction, gray level conversion adjustment and the like on the face image by using an image processing algorithm, and then performs positioning clipping on the face related to the image according to a predetermined positioning clipping algorithm, wherein the positioning clipping algorithm mainly judges whether the face exists, the size, the range and the like of the face, so that the calculation amount and the processing time are reduced when the face features are extracted subsequently. The embodiment of the invention can adopt an EigenFaces algorithm based on PCA (Principal Components Analysis) to extract the characteristic value of the face image, and then a folder is generated according to the unique identification code (including but not limited to a mobile phone number, a school number and an ID (identity) card) and the name of a single student, and the face image of the student is stored in the folder. Meanwhile, a binding relationship is established among the teaching class, the personnel information and the face characteristic value, and a corresponding classifier is generated for the dimensionality according to the teaching class. And meanwhile, the facial image processing result is returned to the information registration and input platform, and the course information is transmitted to the data statistical analysis platform for storage and registration.
Responding to an attendance checking process, the face image processing system 2 is mainly used for matching and identifying face images, and the specific process comprises the following steps: the teaching worker collects the collective photos of students in teaching classes through an information registration and input platform 1 of the intelligent mobile device terminal, and uploads the collective photos containing face images of a plurality of students to a face image processing system 2. Therefore, the condition that a single student queues up to collect the face can be avoided, time and input cost can be saved and the non-sensory experience of the student is improved through one-time collection. The face image processing system 2 receives, preprocesses, positions and cuts the collective face image, extracts the face characteristic value and other operations, matches the corresponding classifier according to the teaching class selected by the teaching worker, searches the matched target characteristic value in the classifier according to the extracted face characteristic value, if the face image is similar to the classifier, finishes the matching of the face image, finishes the recognition, acquires the student information corresponding to the target characteristic value at the moment, and records the attendance mark as the 'attendance' state. And synchronously transmitting the attendance result data to a data statistical analysis platform. And after all the processes are finished, returning the collective human face image processing result to the information registration and entry platform.
And the data statistical analysis platform 3 is mainly used for storing the association relation data of classes and students in the teaching management and receiving the matching and recognition results in the face image processing system, registering and updating the attendance conditions of the corresponding teaching classes and the students according to the results, and providing visual inquiry and timed reminding functions for the students and teaching workers. The query form includes but is not limited to a list, a downloadable report, and the reminder form includes but is not limited to a mail, APP (application) notification.
Fig. 7 is a block diagram showing the structure of the information registration entry platform 1, and as shown in fig. 7, the information registration entry platform 1 includes: an information registration processing application unit 11, a face image acquisition unit 12, an information registration request unit 13, and an information registration processing result receiving unit 14, wherein:
the information registration processing application unit 11 provides a visual form to interact with an operator, and is responsible for providing teaching class information, attendance information input, collection, query and the like for students and teaching workers, wherein the attendance information includes but is not limited to: class type, name, mobile phone number, school number, identification number, color face image (including multiple student face images).
The face image acquisition unit 12 takes a picture through a camera of the intelligent device held by an operator, checks the face image acquired by the camera in format, image size and resolution, and converts the face image into readable electronic data information after checking. The formats of the face image include, but are not limited to, JPG (an image format), PNG (an image format), BMP (an image format).
And the information registration request unit 13 is used for packaging and transmitting the attendance information to be processed, the face image and the operation user query request to the face image processing system 2 and the data statistical analysis platform 3 according to a uniform message format, so that the attendance data can be conveniently registered and stored and the face image can be conveniently processed.
And the information registration processing result receiving unit 14 is responsible for informing or visually displaying the facial image processing result returned by the facial image processing system 2 and the query result returned by the data statistical analysis platform 3 to the operating user in a visible message form.
Fig. 8 is a block diagram of a face image processing system 2, and as shown in fig. 8, the system 2 includes: an information receiving and returning unit 21, a preprocessing unit 22, a positioning and cutting unit 23, a human face feature extracting unit 24, a classifier unit 25, a matching and identifying unit 26 and an information forwarding unit 27, wherein:
the information receiving and returning unit 21 is responsible for receiving attendance information and facial image data information from the information registration and entry platform 1, splitting a message according to a unified instruction to obtain attendance information (including facial images) to be processed and business data, forwarding the data to other processing units for processing, and returning a final result to the information registration and entry platform 1.
The preprocessing unit 22 performs preprocessing operations such as noise reduction, light enhancement/weakening, geometric correction, gray scale conversion adjustment, normalization and the like on the face image based on an OpenCV (cross-platform computer vision library) image processing library algorithm according to the face image data from the information receiving and returning unit 21, so that the requirements of face image feature extraction can be met. Image pre-processing algorithms include, but are not limited to: multiscale Retinex (an image enhancement algorithm) algorithm, Gopfert' S (an image processing algorithm) algorithm.
The positioning clipping unit 23 is configured to position and clip the face picture according to the processing result of the preprocessing unit 22, where the positioning clipping algorithm includes, but is not limited to, RGB-HIS (image segmentation algorithm), KF (kalman filter algorithm), and SEIF (filter-based positioning algorithm) algorithm, and is used to determine whether a face exists, the size and range of the face, and reduce the amount of computation and processing time during subsequent feature extraction.
The face feature extraction unit 24 extracts face features from the processed image according to the image processing result of the positioning and clipping unit 23, where the algorithms used herein include, but are not limited to, HOUGH transform (HOUGH transform) and Scale-invariant feature transform (SIFT-invariant feature transform) algorithms, and generate specific feature data. The unit can adopt a parallel processing mode when working, mainly aims at a group photo containing a plurality of face head photos of users, can simultaneously extract a plurality of face features, and achieves the aim of improving the processing efficiency of the system.
The classifier unit 25 is invoked in response to the face image processing system 2 judging that the current operation is the initial information registration entry. A folder is generated in the background of the system according to the unique identification code (including but not limited to a mobile phone number, a school number and an ID) and name of a single student, and facial images of the student are stored in the folder. Meanwhile, a binding relation is established among the teaching class, the personnel information and the face characteristic value in the system, and the corresponding classifier is generated according to the KNN model algorithm by taking the teaching class as a dimensionality. When the unit works, a face feature library data association mechanism is dynamically adjusted according to the change of the number of students in a teaching class, namely, when the number of the students or face images of the students changes (such as class quitting and face image re-uploading), a classifier is trained according to the latest data, so that the efficiency of subsequent matching and recognition operation can be improved, and unnecessary overhead of a system is reduced.
And the matching and identifying unit 26 is called in response to the face image processing system 2 judging that the current operation is the face image matching and identifying of the attendance checking process. And matching the corresponding classifier according to the teaching class selected by the teaching worker, searching a target characteristic value matched with the characteristic value of the face image in the classifier, if the target characteristic value is similar to the characteristic value of the face image, finishing the matching of the face image, and finishing the identification.
And the information forwarding unit 27 is used for acquiring student information corresponding to the target characteristic value when the facial image processing system 2 judges that the facial image currently operated as the attendance process is matched and identified and the matching and identifying unit 26 passes the processing result, recording the attendance mark as the attendance state, and synchronously forwarding the result to the data statistical analysis platform 3 for updating. When the face image processing system 2 judges that the current operation is the initial information registration record, the classifier unit 25 synchronizes the attendance information to the data statistical analysis platform 3 for registration storage after finishing the processing.
Fig. 9 is a block diagram of the structure of the data statistical analysis platform 3, and as shown in fig. 9, the data statistical analysis platform 3 includes: an information receiving and returning unit 31, a storage unit 32, a statistical analysis unit 33, wherein:
the information receiving and returning unit 31 is responsible for receiving attendance information, facial image data processing results and query requests from the information registration and entry platform 1 and the facial image processing system 2, splitting messages according to unified instructions to obtain attendance information (including facial image recognition results) and business data, forwarding the data to other processing units for processing, and returning final results to the information registration and entry platform 1 and the facial image processing system 2.
And the storage unit 32 is responsible for storing the association relation data of classes and students in the teaching management and updating the face image processing result in the face image processing system 2.
The statistical analysis unit 33 is responsible for performing statistical analysis on the data in the storage unit 32 in different dimensions, including but not limited to: the related program is scheduled regularly (according to days/months/quarters/years) to trigger the attendance statistical actions of corresponding teaching classes and students, and the results are returned through the information receiving and returning unit 31. The students and the teaching workers can receive inquiry and reminding information through the information registration processing result receiving unit 14 in the information registration and entry platform 1. The query result is in the form of a list and a downloadable report, and the reminding is in the form of a mail and an APP notification.
In practical operation, the units, the modules and the sub-modules may be combined or may be arranged singly, and the present invention is not limited thereto.
The attendance system based on the face image realizes the functions of attendance information and face image acquisition, face image preprocessing and characteristic value extraction, attendance information and face image storage, face image matching identification, attendance information statistical analysis, attendance information processing request forwarding, result returning and the like.
Based on the attendance system, when the human face attendance processing is carried out on the students in class, the attendance system mainly relates to three processes of initial information registration and entry, human face image matching and identification and data statistical analysis. The general summary is as follows: the method comprises the steps of providing a visual interaction interface for students and teaching workers to bind courses and students and collect face images by selecting a Web browsing and mobile intelligent device mode provided by an information registration and input platform 1, then forwarding the course information and the face images to a face image processing system 2, receiving the course information and the face image data by the face image processing system 2, then carrying out preprocessing and characteristic value extraction and characteristic matching and identification on the face images, and then forwarding an identification result to a data statistical analysis platform 3. And the data statistical analysis platform 3 performs storage and updating operations after receiving the data information to complete statistical analysis of the attendance data. The students or the teaching workers can inquire through a visual interface provided by the information registration and entry platform 1, and the data statistical analysis platform 3 informs or visually displays the inquiry result to the students or the teaching workers in a visible message form.
Fig. 10 is a flow chart of initial information registration entry based on the system shown in fig. 6, and as shown in fig. 10, the flow chart includes:
step 11: information input and face image acquisition. The teaching worker inputs relevant course information into the information registration and input platform 1 in advance for the student to select, the student selects courses and fills in student information (including but not limited to class types, names, mobile phone numbers, school numbers and identification numbers) on a visual interface provided by the information registration processing application unit 11 in the information registration and input platform 1, a camera of intelligent equipment held by the student is called by the face image acquisition unit 12 to take pictures, face images acquired by the camera are subjected to formatting, image size and resolution inspection, and the face images are converted into readable electronic data information after the face images are passed.
Step 12: course information and a face image registration request. The course, the student and the facial image information are packaged and transmitted to the facial image processing system 2 according to a uniform message format through an information registration request unit 13 in the information registration and entry platform 1.
Step 13: and (5) preprocessing the face image. After receiving the information in step 12, the information receiving and returning unit 21 in the face image processing system 2 splits the message according to a unified instruction to obtain attendance information (including a face image) and service data, and transmits the obtained data to the preprocessing unit 22 for face image preprocessing, and transmits the data to the positioning and cutting unit 23 after the preprocessing is completed.
Step 14: and positioning and cutting the face image. The positioning clipping unit 23 receives the processing result of the preprocessing unit 22, positions and clips the face picture, and has the function of judging whether the face exists, the size and the range of the face, so that the calculation amount and the processing time are reduced when the features are extracted subsequently. Then, the face image data after positioning and cutting is transmitted to the face feature extraction unit 24.
Step 15: and extracting the characteristic value of the face image. And according to the processing result of the positioning cutting unit 23, performing face feature extraction on the processed image to generate specific feature data. After that, the face image processing system 2 calls the classifier unit 25 when judging that the current operation is the initial information registration entry.
Step 16: and (5) training a classifier. A folder is generated in the background of the system according to the unique identification code (including but not limited to a mobile phone number, a school number and an ID) and name of a single student, and facial images of the student are stored in the folder. Meanwhile, a binding relation is established among courses, personnel information and face characteristic values according to a paired value data format, and a corresponding classifier is generated according to a KNN model algorithm by taking a teaching class as a dimensionality. In the step, a face feature library data association mechanism is dynamically adjusted according to the change of the number of students in the teaching class, namely, when the number of the students or face images of the students changes (such as class quitting and face image uploading again), a classifier is trained according to the latest data, so that the efficiency of subsequent matching and recognition operation can be improved, and unnecessary overhead of the system is reduced.
And step 17: and storing the course information. After finishing the processing by the classifier unit 25 in the face image processing system 2, the course information is packed into a message according to a specific data format and is synchronized to the data statistical analysis platform 3 for registration. The information receiving and returning unit 31 located on the data statistical analysis platform 3 receives the course information and forwards the course information to the storage unit 32 for registration and storage.
Step 18: and returning the result. After the course information is registered, the information receiving and returning unit 31 in the data statistical analysis platform 3 returns the result to the face image processing system 2, and then calls the information receiving and returning unit 21 in the face image processing system 2 to return the result to the information registration entry platform 1. After receiving the result, the information registration processing result receiving unit 14 in the information registration entry platform 1 displays the course selection and face image entry result to students in a visual form.
Fig. 11 is a flow chart of face image matching and recognition based on the system shown in fig. 6, and as shown in fig. 11, the flow chart includes:
step 21: and collecting the face images of the group. Teaching workers log in the information registration and entry platform 1 by using intelligent equipment in a classroom, confirm corresponding courses through the information registration processing application unit 11, and call a camera of the intelligent equipment held by the teaching workers for collective photo collection through the face image collection unit 12. Therefore, the method can avoid the condition that every student queues up to collect the face, achieves the aims of collecting once, saving time and input cost and improving the sensorless experience of the students. The collective image which is collected by the camera and contains a plurality of trainee face images is subjected to formatting, image size and resolution inspection, and is converted into readable electronic data information after the inspection.
Step 22: and matching the face image and identifying the request. An information registration request unit 13 positioned in the information registration and input platform 1 packages and transmits the collective facial image information to the facial image processing system 2 according to a specific uniform message format.
Step 23: and (5) preprocessing the face image. After the information receiving and returning unit 21 in the face image processing system 2 receives the information in step 22, the message is split according to a unified instruction to obtain attendance information (including a face image) and service data, the data is transmitted to the preprocessing unit 22 for face image preprocessing, and then the preprocessed image is transmitted to the positioning and cutting unit 23.
Step 24: and positioning and cutting the face image. The positioning clipping unit 23 receives the processing result of the preprocessing unit 22, positions and clips the face picture, and has the function of judging whether the face exists, the size and the range of the face, so that the calculation amount and the processing time are reduced when the features are extracted subsequently. Then, the face image data after positioning and cutting is transmitted to the face feature extraction unit 24.
Step 25: and extracting the characteristic value of the face image. And according to the processing result of the positioning and cutting unit 23, extracting the face features of the processed face image containing a plurality of trainees, and generating specific feature data according to a multitask parallel processing mode so as to improve the image processing efficiency. Thereafter, the face image processing system 2 calls the matching and identifying unit 26 when it judges that the current operation is the face image matching and identification.
Step 26: and matching and identifying the face image. The matching and identifying unit 26 in the face image processing system 2 maps to the corresponding classifier according to the teaching class selected by the teaching worker, and searches for a target feature value matched with the feature value in the classifier by adopting a traversal loop mechanism according to the feature value extracted collectively, and if the target feature value is similar to the feature value, the matching of the face image is completed, and the face image passes the identification.
Step 27: and registering and updating attendance data. And if the matching and identifying unit 26 passes the processing result, acquiring the student information corresponding to the target characteristic value, recording the attendance mark as the attendance state, and synchronously forwarding the result to the data statistical analysis platform 3. After receiving the attendance result, the information receiving and returning unit 31 located in the data statistical analysis platform 3 calls the storage unit 32 to register and update the result.
Step 28: and returning the result. After the attendance data is registered and updated, the information receiving and returning unit 31 in the data statistical analysis platform 3 returns the result to the facial image processing system 2, and then the facial image processing system 2 calls the information receiving and returning unit 21 to return the result to the information registration and entry platform 1. After receiving the result, the information registration processing result receiving unit 14 in the information registration entry platform 1 displays the face image matching and recognition result to the teaching worker in a visual form.
Fig. 12 is a flowchart of statistical analysis of attendance data based on the system shown in fig. 6, and as shown in fig. 12, the flowchart includes:
step 31: and triggering data statistical analysis. The statistical analysis action can be triggered by 2 ways: firstly, students and teaching workers actively trigger query requests through an information registration processing application unit 11 in an information registration entry platform 1; the second is that the statistical analysis unit 33 in the data statistical analysis platform 3 regularly schedules the related program trigger according to the data in the storage unit 32. Wherein, the periodic period includes but is not limited to: at the end of the course, and according to/day/month/quarter/year, the statistical analysis content includes, but is not limited to, corresponding teaching class, student attendance rate, attendance ranking statistics.
Step 32: and returning the statistical result. An information receiving and returning unit 31 in the data statistical analysis platform 3 returns the data result of active query or periodic statistics to the information registration entry platform 1, and an information registration processing result receiving unit 14 located in the information registration entry platform 1 receives the query statistical result, and displays the query statistical result to students or teaching workers on the information registration entry platform 1 in a form of notification reminding in a visual form and a downloadable report.
As can be seen from the above description, an attendance system based on facial images is provided in an embodiment of the present invention, wherein the information registration and entry platform is configured to provide students and teaching workers with teaching information (including but not limited to courses, classes, etc.), collect and enter facial image information, and send collected facial image data to the facial image processing system. The face image processing system receives the teaching information and the face image, and performs image preprocessing, image feature extraction, image matching and recognition to generate an image recognition result. And the human face image processing system sends the recognition result to a data statistics analysis platform to carry out data statistics, analysis and subsequent notification actions. The face image and the teaching information data are transmitted in a corresponding network through a TSL (Transport Layer Security) protocol in the circulation process of an information registration and entry platform, a face image processing system and a data statistical analysis platform, decryption and verification are carried out when the data reach a distribution system, TSL communication is established with a next processing system after the data are processed, and data information is transmitted, so that the confidentiality and the integrity of information flow in the transmission process are guaranteed.
FIG. 13 is a schematic diagram of an electronic device according to an embodiment of the invention. The electronic device shown in fig. 13 is a general-purpose data processing apparatus comprising a general-purpose computer hardware structure including at least a processor 1301 and a memory 1302. The processor 1301 and the memory 1302 are connected by a bus 1303. The memory 1302 is adapted to store one or more instructions or programs that are executable by the processor 1301. The one or more instructions or programs are executed by processor 1301 to implement the steps in the attendance method based on image recognition described above.
The processor 1301 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 1301 implements the processing of data and the control of other devices by executing the commands stored in the memory 1302 to thereby execute the method flows of the embodiments of the present invention as described above. The bus 1303 connects the above-described components together, and also connects the above-described components to a display controller 1304 and a display device and an input/output (I/O) device 1305. Input/output (I/O) devices 1305 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, an input/output (I/O) device 1305 is connected to the system through an input/output (I/O) controller 1306.
The memory 1302 may store, among other things, software components such as an operating system, communication modules, interaction modules, and application programs. Each of the modules and applications described above corresponds to a set of executable program instructions that perform one or more functions and methods described in embodiments of the invention.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of the attendance checking method based on image recognition.
In summary, the embodiment of the invention provides an attendance checking scheme based on face image recognition, which collects collective face images by relying on the convenience of mobile intelligent equipment, and completes attendance checking by extracting and recognizing features of the face images. The embodiment of the invention replaces the traditional sensible operation process with the technical means, improves the attendance efficiency, can conveniently match student information according to the face picture information, can quickly carry out attendance statistics and analysis work, ensures the high efficiency of attendance management, and provides more intelligent, more accurate and more efficient management means for the attendance management.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments which fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (14)
1. An attendance checking method based on image recognition is characterized by comprising the following steps:
acquiring attendance data to be processed, wherein the attendance data comprises: a collective image containing a plurality of face images of users and corresponding activity information;
preprocessing the collective image to identify a face image in the collective image;
and performing matching operation according to the activity information and the recognized face image and pre-stored activity registration information, wherein the activity registration information comprises: user information and face images thereof needing to participate in activities;
and identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
2. The method of claim 1, wherein when the user is to engage in a plurality of different activities, the method further comprises:
classifying the activity registration information based on the trained classification model;
and generating activity registration information with the activity information as a category according to the classification processing result.
3. The method according to claim 2, wherein performing a matching operation based on the activity information and the recognized face image with pre-stored activity registration information comprises:
determining activity registration information of corresponding categories according to the activity information;
and matching the recognized face images based on a traversal loop mechanism according to the determined activity registration information of the corresponding category.
4. The method of claim 1, wherein the collective image is preprocessed to identify face images therein, comprising:
preprocessing the collective image;
and performing face feature extraction operation on the preprocessed collective images based on a parallel processing mode to identify face images in the collective images.
5. The method of claim 1, further comprising:
and counting attendance result data according to a preset rule by using activity information or user information.
6. The method of claim 1, wherein obtaining attendance data to be processed comprises:
collective images of users participating in the activity are acquired by the camera device.
7. An attendance device based on image recognition, the device comprising:
the data acquisition unit is used for acquiring attendance data to be processed, and the attendance data comprises: a collective image containing a plurality of face images of users and corresponding activity information;
the image recognition unit is used for preprocessing the collective image and recognizing a face image in the collective image;
a matching unit configured to perform a matching operation based on the activity information and the recognized face image and pre-stored activity registration information, the activity registration information including: user information and face images thereof needing to participate in activities;
and the identification unit is used for identifying whether the user needing to participate in the activity participates in the activity according to the matching operation result so as to generate attendance result data.
8. The apparatus of claim 7, wherein when the user needs to engage in a plurality of different activities, the apparatus further comprises:
the classification unit is used for classifying the activity registration information based on the trained classification model;
and an activity registration information generation unit configured to generate activity registration information in which the activity information is classified according to the classification processing result.
9. The apparatus of claim 8, wherein the matching unit comprises:
the activity registration information determining module is used for determining activity registration information of corresponding categories according to the activity information;
and the matching module is used for matching the recognized face images based on a traversal loop mechanism according to the determined activity registration information of the corresponding category.
10. The apparatus according to claim 7, wherein the image recognition unit comprises:
the preprocessing module is used for preprocessing the collective image;
and the image identification module is used for carrying out face feature extraction operation on the preprocessed collective image based on the parallel processing mode so as to identify the face image in the collective image.
11. The apparatus of claim 7, further comprising:
and the counting unit is used for counting attendance result data according to the preset rule by using the activity information or the user information.
12. The apparatus according to claim 7, wherein the data acquisition unit is specifically configured to:
collective images of users participating in the activity are acquired by the camera device.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the image recognition-based attendance method according to any one of claims 1 to 6 when executing the program.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the image recognition-based attendance method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010118627.2A CN111339939B (en) | 2020-02-26 | 2020-02-26 | Attendance checking method and device based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010118627.2A CN111339939B (en) | 2020-02-26 | 2020-02-26 | Attendance checking method and device based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111339939A true CN111339939A (en) | 2020-06-26 |
| CN111339939B CN111339939B (en) | 2023-09-26 |
Family
ID=71186947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010118627.2A Active CN111339939B (en) | 2020-02-26 | 2020-02-26 | Attendance checking method and device based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339939B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550253A (en) * | 2022-02-22 | 2022-05-27 | 支付宝(杭州)信息技术有限公司 | Method and device for preprocessing face image in queuing scene |
Citations (4)
| 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 |
| CN107481343A (en) * | 2017-07-22 | 2017-12-15 | 华中师范大学 | A kind of check class attendance based on face recognition technology is registered system and its method of work |
| CN108022318A (en) * | 2017-12-28 | 2018-05-11 | 上海享服信息技术有限公司 | More people's recognition of face attendance checking systems and its Work attendance method |
| CN108875606A (en) * | 2018-06-01 | 2018-11-23 | 重庆大学 | A kind of classroom teaching appraisal method and system based on Expression Recognition |
-
2020
- 2020-02-26 CN CN202010118627.2A patent/CN111339939B/en active Active
Patent Citations (4)
| 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 |
| CN107481343A (en) * | 2017-07-22 | 2017-12-15 | 华中师范大学 | A kind of check class attendance based on face recognition technology is registered system and its method of work |
| CN108022318A (en) * | 2017-12-28 | 2018-05-11 | 上海享服信息技术有限公司 | More people's recognition of face attendance checking systems and its Work attendance method |
| CN108875606A (en) * | 2018-06-01 | 2018-11-23 | 重庆大学 | A kind of classroom teaching appraisal method and system based on Expression Recognition |
Non-Patent Citations (1)
| Title |
|---|
| 方冠男: "基于视频流人脸识别的课堂考勤系统的设计与实现" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550253A (en) * | 2022-02-22 | 2022-05-27 | 支付宝(杭州)信息技术有限公司 | Method and device for preprocessing face image in queuing scene |
| CN114550253B (en) * | 2022-02-22 | 2024-05-10 | 支付宝(杭州)信息技术有限公司 | Method and device for preprocessing face image in queuing scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111339939B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11321583B2 (en) | Image annotating method and electronic device | |
| CN109800320B (en) | Image processing method, device and computer readable storage medium | |
| CN109285234B (en) | Face recognition attendance checking method and device, computer device and storage medium | |
| CN108846911A (en) | A kind of Work attendance method and device | |
| CN109345417B (en) | Online assessment method and terminal equipment for business personnel based on identity authentication | |
| CN108491866B (en) | Pornographic picture identification method, electronic device and readable storage medium | |
| CN110598008B (en) | Method and device for detecting quality of recorded data and storage medium | |
| CN112581081B (en) | Computer examination informatization-based machine room seat management method, device and equipment | |
| US20230410220A1 (en) | Information processing apparatus, control method, and program | |
| CN110264243A (en) | Product promotion method, apparatus, equipment and storage medium based on In vivo detection | |
| CN110852714A (en) | Salary improvement data management system applied to decoration service platform | |
| CN111339939B (en) | Attendance checking method and device based on image recognition | |
| CN113822645A (en) | Interview management system, equipment and computer medium | |
| CN114257640A (en) | Cloud computing scheduling method and system | |
| CN111639879A (en) | Intelligent security personnel information management method, device and system, storage medium and server | |
| CN109801394B (en) | Staff attendance checking method and device, electronic equipment and readable storage medium | |
| CN115690819A (en) | Big data-based identification method and system | |
| CN114581130A (en) | Bank website number assigning method and device based on customer portrait and storage medium | |
| CN111681745A (en) | Data processing method and device | |
| CN112686156A (en) | Emotion monitoring method and device, computer equipment and readable storage medium | |
| US11657649B2 (en) | Classification of subjects within a digital image | |
| CN117077972A (en) | Matching degree detection method, device, equipment and storage medium | |
| Muhammad et al. | A generic face detection algorithm in electronic attendance system for educational institute | |
| CN116778508A (en) | OCR recognition system based on cloud edge end cooperation | |
| CN113919308A (en) | Method and device for determining vote information, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |