CN111611911A - Class attendance checking method based on convolutional neural network and multi-face recognition - Google Patents
Class attendance checking method based on convolutional neural network and multi-face recognition Download PDFInfo
- Publication number
- CN111611911A CN111611911A CN202010423564.1A CN202010423564A CN111611911A CN 111611911 A CN111611911 A CN 111611911A CN 202010423564 A CN202010423564 A CN 202010423564A CN 111611911 A CN111611911 A CN 111611911A
- Authority
- CN
- China
- Prior art keywords
- face
- attendance
- class
- neural network
- convolutional neural
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 42
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 230000014509 gene expression Effects 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 4
- 210000000887 face Anatomy 0.000 description 4
- 230000036544 posture Effects 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 208000029152 Small face Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 210000000216 zygoma Anatomy 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a classroom attendance checking method based on a convolutional neural network and multi-face recognition, which comprises the following steps: s01, collecting the full class face-righting clear group photo through the mobile phone, and uploading the collected full class face-righting clear group photo to a cloud server; s02, carrying out face recognition and face segmentation on the full-class face-setting clear photo through YOLOv3 to obtain all segmented face-setting small photos; s03, comparing the full-class front face small picture with a student face database through the insight face to respectively obtain the attendance checking condition of each student in the full class; and S04, sending the attendance condition of each student in the whole class to the student attendance system to obtain a whole class attendance result. The invention has the beneficial effects that: a convolutional neural network YOLOv3 and an insight face are introduced, and class attendance can be finished with high quality only by shooting a full-class co-illumination by using a mobile phone. Compared with single face attendance or video multi-frame attendance, the method has relative advantages, and the problems of poor timeliness, high complexity, high accuracy and the like of the system are solved.
Description
Technical Field
The invention relates to a classroom attendance checking method based on multi-face recognition, in particular to a classroom attendance checking method based on a convolutional neural network and multi-face recognition.
Background
The classroom attendance of Chinese college students is always a problem which cannot be really solved, the manual classroom attendance mode is time-consuming, and the problems of attendance by people and the like are difficult to avoid. In addition, the way of checking attendance using extra equipment, for example: fingerprint attendance, cell-phone attendance, scan two-dimensional code attendance, camera automatic capture attendance etc. they all derive some problems more or less, for example: long time consumption, low accuracy, or low price, and low efficiency. Currently, the most promising direction is to use artificial intelligence to assist with classroom attendance.
Document "design and implementation of a mobile classroom attendance system based on face recognition [ J ] software, 2018, 39 (01): 5-8 discloses an attendance checking method based on multi-face recognition. The method shoots a whole-shift co-shooting picture, uploads the picture to a self-built system of the picture, and carries out face recognition to obtain an attendance result. The self-built system needs to carry out face image acquisition and preprocessing, detection and positioning, feature extraction in advance, and finally face image matching and recognition can be realized. The Principal Component Analysis (PCA) is utilized to measure the distance between eyes, cheekbones, mouth, chin and the like in the face image to carry out identity authentication. The method has the main problems that the implementation process is complex, the algorithm is out of date, the effect is poor, the accuracy rate is only 75%, related experimental data samples are seriously lacked, only one class of 25 people is provided for the data sample, and the real practical value cannot be achieved.
A class attendance method based on a convolutional neural network and multi-face recognition can effectively solve the class attendance problem.
Disclosure of Invention
In order to solve the problem of the current class attendance system based on face recognition, if: the equipment is expensive, the attendance checking speed is low, the accuracy is low, and the attendance checking system is easily influenced by environmental illumination, photo noise, postures, expressions and the like. The invention provides a class attendance checking method based on a convolutional neural network and multi-face recognition. The method is based on two large modules of solving the problem of face detection and face recognition, and a YOLOv3 algorithm based on a convolutional neural network and an ArcFace algorithm for deep face recognition, which is also called an insight Face algorithm, are respectively used. The YOLOv3 network and the insight face network were trained in advance using public sea volume data sets and then used to detect and identify class attendance. The method does not need to train data in a target system, only needs to train by using the open-source Face data set WIDER Face, and the trained network can be directly used. The method has the characteristics of extremely high speed, extremely high accuracy and almost 0 additional cost. The Yolov3 can detect 30 photos and cut out a face image in one second, the recognition speed of the insight face is also in the millisecond level, the accuracy rate is over 99 percent and is far greater than 97 percent of human eyes. And can be free from the influence of illumination, noise, posture, expression and the like. The problem that the university classroom attendance is time-consuming and lack of accuracy rate can be well solved.
In order to solve the above technical problem, as shown in fig. 2, the technical solution adopted by the present invention is: a class attendance checking method based on a convolutional neural network and multi-face recognition comprises the steps of,
s01, collecting the full class face-righting clear group photo through the mobile phone, and uploading the collected full class face-righting clear group photo to the cloud server;
s02, carrying out face recognition and face segmentation on the full-class face-setting clear photo through a convolutional neural network YOLOv3 to obtain all segmented face-setting small photos;
s03, comparing the whole class front face small photo with a student face database through a convolutional neural network insight face to respectively obtain the attendance checking condition of each student in the whole class, wherein the student face database consists of two parts, namely, a face photo existing in a school educational administration system or a front face portrait photo uploaded by the student;
s04, sending the attendance condition of each student in the whole class to the student attendance system to obtain a whole class attendance result;
s05 sends the work attendance result to the mobile phone client for the teacher and the student to check, the mobile phone client can be APP or WeChat applet.
In step S01, the mobile phone collects the full-shift face-correcting clear photos without using additional equipment.
In step S02, the YOLOv3 is a convolutional neural network-based object detection segmentation network, which can efficiently detect and segment a face photo and obtain segmented small photos.
In step S03, the insight face is a face recognition network based on a convolutional neural network, and can perform efficient face comparison and recognition with an existing student face database.
In step S04, the student attendance system obtains the face comparison and recognition results after the insight face processing, and obtains the work attendance result.
In step S05, the APP or wechat applet mobile phone client capable of viewing the result in real time is provided, so that the client can timely perform feedback correction with the student, and timeliness is guaranteed.
A classroom attendance method based on a convolutional neural network and multi-face recognition comprises a mobile phone client, a cloud server, a face detection segmentation convolutional neural network YOLOv3, a face comparison recognition convolutional neural network insight face, a student attendance module and a student face database.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
FIG. 2 is a schematic flow chart of the present invention.
Fig. 3 is a flow chart of the process of forming the face database according to the present invention.
Detailed Description
In order to explain technical contents, structural features, and objects and effects of the present invention in detail, the following detailed description is made with reference to the accompanying drawings in combination with the embodiments.
The most key concept of the invention is as follows: the method comprises the steps that a plurality of faces in a classroom are checked without extra image acquisition equipment or cloud uploading equipment, an ordinary personal mobile phone can work, only one class front face is shot by the mobile phone before class, the whole class front face is uploaded to a cloud server, front face small photographs of each student are obtained after treatment through a convolutional neural network YOLOv3 and an insight face, and checking results can be obtained after comparison and identification with a face database of the student. The mobile phone is adopted to replace complex peripherals, the rapid development of the conventional convolutional neural network is mainly based, and the precision and the efficiency of the method are far beyond the requirements of class multi-face attendance. The mode of taking pictures by the mobile phone can effectively avoid students from replacing the point arrival, and greatly saves the time and the accuracy of the point arrival in class.
The invention provides a classroom attendance method based on a convolutional neural network and multi-face recognition, which comprises the steps of establishing a student face database and working flows of an attendance system;
the process for establishing the student face database, as shown in fig. 3, comprises the steps of,
s1), the cloud server directly acquires the existing student face database of the school educational administration system;
s2) when the school face database can not meet the requirements, the students register by themselves to collect the face data and update the face data to the face database of the cloud server;
the work flow of the attendance system comprises a process of processing collected full class front face photos through a convolutional neural network YOLOv3 and an insight face to obtain front face small photos of each student, comparing the front face small photos with a face database of a cloud server, and obtaining an attendance result.
From the above description, the beneficial effects of the present invention are: the attendance result can be obtained only by using the mobile phone to shoot a full class face-to-face photo before class and uploading the photo to the cloud server. The method is simple, and can effectively avoid students from replacing the point arrival, and greatly save the time and the accuracy of the point arrival in class. The method has the characteristics of high speed, high accuracy and almost 0 additional cost. YOLOv3 can detect 30 photos and cut out human face images in one second, the recognition speed of the insight face is the millisecond level, the accuracy is over 99 percent and far greater than 97 percent of human eyes, the recognition speed is not affected by illumination, noise, postures, expressions and the like, and the problems that the time consumption is large and the accuracy is low in university class attendance can be well solved.
Example 1:
the work flow of the attendance system further includes a mobile phone terminal to correct the attendance result, as shown in fig. 1, the mobile phone terminal to correct the attendance result includes the following steps:
s11) the teacher uses the mobile phone to shoot a whole class face-to-face photo at will before class and uploads the photo to the cloud server;
s12) the cloud server processes the group photo through a convolutional neural network;
s13) the automatic attendance system receives the co-illumination processing result and obtains an attendance result;
s14) the teacher or the mobile phone terminal of the student obtains the attendance result;
s15) the teacher or the student disagrees the attendance result, and can shoot the co-photos again and repeat the above steps, or the teacher corrects the attendance result manually;
s16) the result is unanimous, and the final attendance result is output for teachers and students to check.
Example 2:
further, the step S12 is implemented in the mobile phone terminal correction attendance result through the convolutional neural network YOLOv3 and the convolutional neural network insight face,
the convolutional neural network YOLOv3 is mainly used for target detection, is the third version of YOLO and is the latest version, is proposed by Joseph Redmon and Ali Farhadi of Washington university, and by adding the improvement of design details into the YOLO, the novel model realizes the great improvement of detection speed under the condition of obtaining considerable accuracy rate, and under general request, the novel model is 1000 times faster than R-CNN and 100 times faster than FastR-CNN, and is the first choice of an open-source general target detection algorithm at present;
the convolutional neural network insight is proposed by Jia Guo and Jiankang Deng based on ArcFace, the code of insight face is issued under MIT permission, and has no limitation on academic and commercial use, and the network backbone thereof includes ResNet, MobilefaceNet, MobileNet, IncepotionResNet _ v2, DenseNet, DPN, Loss functions include Softmax, Sphereface, Cosine face, Arcface and triple (Euclidean/Angular) Loss, and at present, insight face is in the field of face recognition, and is significantly advanced in effect or performance.
Example 3:
the process of establishing the student face database further comprises a face registration process, and the face registration process comprises the following steps:
s21) the student opens the mobile phone attendance app or the WeChat applet;
s22) acquiring a clear front face image;
s23) processing the face image by using YOLOv3 and the insight face to obtain a small segmented face picture;
s24) storing the segmented small face picture and key information such as the school number, the name and the like into a face database.
Example 4:
the specific flow steps of this patent include image acquisition, upload the server, and many faces detect cuts apart, and many faces are compared the discernment, return the attendance condition, and the personnel that lack in duty confirm, and final information is uploaded to the server.
The following is a description of the specific process steps of this patent:
s31) image acquisition
A clear full-class face-to-face photo is shot by using a common thousand-yuan mobile phone, the collected person does not need to pay attention to the control of the expression, and a teacher does not need to pay attention to other external conditions such as illumination, shadow and the like of the environment.
S32) upload server
And uploading the collected clear front face image to a cloud server through mobile phone traffic or a WIFI network.
S33) Multi-face detection segmentation
YOLOv3 performs face detection and face segmentation operations on the received image.
S34) multi-face comparison recognition
And the insight face compares and identifies the face segmentation small image processed by the YOLOv3 with a face database. Usually, this face database does not need to be created additionally, and nowadays almost all schools have their own student management system with ready-made database of student information and faces of students. Therefore, the face comparison is carried out only by accessing the existing student management system of the school and taking the class as a unit. When the face database of the school can not meet the requirements, students can register the personal face database at first and then merge and unify the personal face database with the face database of the school.
S35) return attendance condition
And the automatic attendance system receives the result of the insight face, and sends the related result back to the mobile phone client of the teacher so as to provide preview for the teacher and students.
S36) absence person confirmation
In order to ensure the accuracy of the attendance checking result, students can make objections to the confirmation result, and teachers can modify the result.
S37) final information is uploaded to the server
The teacher submits the final result to the server again, and the teacher and the students are provided to check and correct.
The improved class attendance checking method based on the convolutional neural network and the multi-face recognition has the following characteristics:
(1) and performing high-precision face detection segmentation and comparison identification on the involution image through the convolutional neural network YOLOv3 and the insight face. The Yolov3 can detect 30 photos and cut out face images in one second, the recognition speed of the insight face is also in the millisecond level, and the accuracy is over 99% and far greater than 97% of human eyes. Due to the fact that the latest artificial intelligence is introduced into the method, the method can be put into practical use only by using other open-source face data sets to train well in advance, accuracy and credibility of results are improved, careless mistakes caused by human factors can be avoided, and the problems that time is long and accuracy rate is poor in university classroom attendance can be well solved.
(2) The classroom attendance can be finished by only one mobile phone without configuring additional equipment.
(3) Because artificial intelligence is adopted, the collection of the photos does not need to consider the noise of the photos, the illumination shadow of the environment, the gestures and expressions of the people and the like, and the collection of the combined photos only needs a few seconds.
(4) The face database can be obtained from a school educational administration system, and students can register and merge themselves, so that the timeliness and the accuracy of the face database are ensured.
(5) The attendance result of the method can be confirmed through the interaction between the teacher and the students, and the final result fairness is ensured.
(6) And the attendance checking result is stored in a cloud database and can be checked at any time.
In conclusion, the method provides a high-precision and high-efficiency class attendance checking method, and by introducing the artificial intelligence YOLOv3 network and the insight face network, the method has the characteristics of extremely high speed and accuracy, almost no cost exists in each attendance checking, the method is not influenced by illumination, noise, postures, expressions and the like, and the problems of much time consumption and lack of accuracy in college class attendance checking can be well solved. The attendance result needs interactive confirmation of teachers and students, the attendance data is stored in the cloud end to be checked at any time, and the public credibility of the attendance result is guaranteed.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and it will be obvious to those skilled in the art that the technical solutions of the foregoing embodiments may be modified, or some technical features may be equivalently replaced. Any modification, improvement, equivalent replacement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A class attendance method based on a convolutional neural network and multi-face recognition is characterized by comprising the following steps:
s01: collecting a full class face-righting clear photo through a mobile phone, and uploading the collected full class face-righting clear photo to a cloud server;
s02: carrying out face recognition and face segmentation on the full-class face-setting clear photo through a convolutional neural network YOLO v3 to obtain all segmented face-setting small photos;
s03: comparing the whole class front face small photo with a student face database through a convolutional neural network insight face to respectively obtain the attendance checking condition of each student in the whole class, wherein the student face database consists of two parts, namely the existing face photo of a school educational administration system or the front face portrait photo uploaded by the student;
s04: then, the attendance condition of each student in the whole class is sent to a student attendance system to obtain a whole class attendance result;
s05: and sending the work attendance result to a mobile phone client for a teacher and students to check, wherein the mobile phone client can be an APP or a WeChat applet.
2. The classroom attendance method based on convolutional neural network and multi-face recognition as claimed in claim 1, wherein in step S01, the full class face-looking clear photo collected by the mobile phone is taken without using additional equipment.
3. The classroom attendance method based on convolutional neural network and multi-face recognition as claimed in claim 1, wherein in step S02, the YOLO v3 is a convolutional neural network-based object detection segmentation network, which can efficiently detect and segment face photographs and obtain segmented small photographs.
4. The classroom attendance method based on convolutional neural network and multi-face recognition as claimed in claim 1, wherein in step S03, the insight face is a face recognition network based on convolutional neural network, which can perform efficient face comparison and recognition with the existing student face database.
5. The classroom attendance method based on the convolutional neural network and the multi-face recognition as claimed in claim 1, wherein in step S04, the student attendance system obtains the face comparison and recognition results after the insight face processing to obtain the work attendance result.
6. The classroom attendance method based on convolutional neural network and multi-face recognition as claimed in claim 1, wherein in step S05, an APP or wechat applet mobile phone client capable of viewing results in real time is provided, which can be fed back and corrected with students in time to ensure timeliness.
7. The classroom attendance method based on the convolutional neural network and the multi-face recognition is characterized by comprising a mobile phone client, a cloud server, a face detection segmentation convolutional neural network YOLO v3, a face comparison recognition convolutional neural network insight face, a student attendance module and a student face database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423564.1A CN111611911A (en) | 2020-05-19 | 2020-05-19 | Class attendance checking method based on convolutional neural network and multi-face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423564.1A CN111611911A (en) | 2020-05-19 | 2020-05-19 | Class attendance checking method based on convolutional neural network and multi-face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111611911A true CN111611911A (en) | 2020-09-01 |
Family
ID=72200287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010423564.1A Pending CN111611911A (en) | 2020-05-19 | 2020-05-19 | Class attendance checking method based on convolutional neural network and multi-face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611911A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112241695A (en) * | 2020-09-25 | 2021-01-19 | 上海荷福人工智能科技（集团）有限公司 | Method for recognizing portrait without safety helmet and with face recognition function |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183029A (en) * | 2014-09-02 | 2014-12-03 | 济南大学 | Portable quick crowd attendance method |
| 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 |
| CN109543979A (en) * | 2018-11-14 | 2019-03-29 | 广州慧睿思通信息科技有限公司 | A kind of environmental monitoring management method, system, service platform and medium |
| 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 |
| CN109635766A (en) * | 2018-12-20 | 2019-04-16 | 中国地质大学（武汉） | The face of convolutional neural networks based on small sample is taken pictures Work attendance method and system |
| CN110097003A (en) * | 2019-04-29 | 2019-08-06 | 中南民族大学 | Check class attendance method, equipment, storage medium and device neural network based |
| CN110246244A (en) * | 2019-05-16 | 2019-09-17 | 珠海华园信息技术有限公司 | Intelligent foreground management system based on recognition of face |
-
2020
- 2020-05-19 CN CN202010423564.1A patent/CN111611911A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183029A (en) * | 2014-09-02 | 2014-12-03 | 济南大学 | Portable quick crowd attendance method |
| 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 |
| CN109543979A (en) * | 2018-11-14 | 2019-03-29 | 广州慧睿思通信息科技有限公司 | A kind of environmental monitoring management method, system, service platform and medium |
| 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 |
| CN109635766A (en) * | 2018-12-20 | 2019-04-16 | 中国地质大学（武汉） | The face of convolutional neural networks based on small sample is taken pictures Work attendance method and system |
| CN110097003A (en) * | 2019-04-29 | 2019-08-06 | 中南民族大学 | Check class attendance method, equipment, storage medium and device neural network based |
| CN110246244A (en) * | 2019-05-16 | 2019-09-17 | 珠海华园信息技术有限公司 | Intelligent foreground management system based on recognition of face |
Non-Patent Citations (1)
| Title |
|---|
| 孟同学: "insightface部署问题", 《HTTPS://BLOG.CSDN.NET/WEIXIN_39610043/ARTICLE/DETAILS/86509350》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112241695A (en) * | 2020-09-25 | 2021-01-19 | 上海荷福人工智能科技（集团）有限公司 | Method for recognizing portrait without safety helmet and with face recognition function |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Samet et al. | Face recognition-based mobile automatic classroom attendance management system | |
| CN108830559A (en) | A kind of Work attendance method and device based on recognition of face | |
| CN103455958B (en) | A kind of check class attendance method based on cell phone platform | |
| CN109712456A (en) | System is intelligently read and made comments in a kind of student's papery operation based on camera | |
| CN206147769U (en) | Classroom management equipment of registering based on two -dimensional code and face identification | |
| CN109214303B (en) | Multithreading dynamic face sign-in method based on cloud API | |
| CN104167025A (en) | Mobile attendance system based on dynamic face recognition and WIFI positioning and method of attendance system | |
| CN105303632A (en) | Mobile signing monitoring system and working method | |
| CN110543811B (en) | Deep learning-based non-cooperative examination personnel management method and system | |
| KR20200068771A (en) | An attendance check system using deep learning based face recognition | |
| CN108766075A (en) | A kind of individualized education analysis system and method based on video analysis | |
| CN206147770U (en) | Classroom management equipment of registering based on two -dimensional code and fingerprint identification | |
| CN105338183A (en) | People recognition prompting system and method based on mobile terminal | |
| CN111611911A (en) | Class attendance checking method based on convolutional neural network and multi-face recognition | |
| CN113326747A (en) | Teaching worker face recognition attendance checking method and system | |
| CN111047726A (en) | Simple attendance checking method and system based on face recognition | |
| CN112819984B (en) | Classroom multi-person roll-call sign-in method based on face recognition | |
| CN112734966B (en) | Classroom roll call method integrating WiFi data and face recognition | |
| Devi et al. | Iot based automatic attendance system | |
| CN114065163A (en) | Display mainboard and terminal with face identification and identity verification functions | |
| CN112560705A (en) | Face detection method and device and electronic equipment | |
| CN116935493B (en) | Education management system | |
| CN109978736A (en) | A kind of multiple spot information extraction, feedback method and the system of the wisdom class board based on recognition of face | |
| Kumar et al. | Smart Attendance Management System Using Raspberry Pi and Deep Learning Technique | |
| CN202939606U (en) | Similar portrait searching 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200901 |