CN111428597A - Attendance management method based on face recognition - Google Patents
Attendance management method based on face recognition Download PDFInfo
- Publication number
- CN111428597A CN111428597A CN202010184511.9A CN202010184511A CN111428597A CN 111428597 A CN111428597 A CN 111428597A CN 202010184511 A CN202010184511 A CN 202010184511A CN 111428597 A CN111428597 A CN 111428597A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- human
- steps
- method based
- 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
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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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—Systems or methods specially adapted for 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Abstract
The invention provides an attendance management method based on face recognition, which comprises the following steps: the method comprises the following steps: establishing a face image file of school face; step two: acquiring a current human body face image; step three: and comparing the face image of the current face with the face image file stock of the school, retrieving and comparing the face print code of the current face image with the face print code in the file stock, confirming the identity of the student and authorizing the operation. The method has the advantages of high recognition speed and high accuracy, and is not influenced by ambient light.
Description
Technical Field
The invention relates to the technical field of image information processing, in particular to an attendance management method based on face recognition.
Background
The face recognition technology is to process an input face image or video stream based on the facial features of a person. Firstly, judging whether a human face exists, and if the human face exists, further giving the position and the size of each face and the position information of each main facial organ. And further extracting the identity characteristics contained in each face according to the information, and comparing the identity characteristics with the known faces so as to identify the identity of each face. The generalized face recognition actually comprises a series of related technologies for constructing a face recognition system, including face image acquisition, face positioning, face recognition preprocessing, identity confirmation, identity search and the like; the narrow-sense face recognition is a technology or a system for identity confirmation or identity search only through faces.
The biological characteristics studied by the biological characteristic identification technology comprise face, fingerprint, palm print, iris, retina, voice (language), body type, personal habit and the like, and the corresponding identification technology comprises face identification, fingerprint identification, palm print identification, iris identification, retina identification, voice identification, body type identification, keyboard knocking identification, signature identification and the like.
Because the faces of the human faces have similarity, different individuals have small difference, and the structures of all the human faces are similar. In addition to the development of modern makeup technology, face recognition still has great recognition difficulty.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides an attendance management method based on face recognition.
An attendance management method based on face recognition comprises the following steps:
The method comprises the following steps: establishing a face image file of school face;
Step two: acquiring a current human body face image;
Step three: and comparing the face image of the current face with the face image file stock of the school, retrieving and comparing the face print code of the current face image with the face print code in the file stock, confirming the identity of the student and authorizing the operation.
Further, according to the attendance management method based on face recognition, the second step includes the following steps:
Step 1: detecting the face, namely detecting the position of the face in the image;
Step 2: matching the face, and positioning the coordinates of irrelevant key points on the face;
And step 3: and (5) snapping the face to obtain a snap image.
Further, according to the attendance management method based on face recognition, the face snapshot includes the following steps:
Step 1): face real-time image information obtained by face recognition camera or panel machine
Step 2): reading frame video stream to extract video frame, each frame being converted into a picture
Step 3): and (3) capturing and comparing the personnel information in the picture by using a human face detection algorithm to finish the capturing process.
Further, according to the attendance management method based on face recognition, the third step includes the following steps:
And 4, step 4: the human face body characteristic is characterized in that a human face snapshot image is converted into a characteristic capable of representing human face characteristics, and the specific expression form is a string of numerical values with fixed length;
And 5: face verification, namely judging whether the two face images are the same person;
Step 6: comparing the faces, and measuring the similarity between the two faces;
And 7: the face retrieval comprises the steps of comparing an input face with faces in a set, sequencing the faces in the set according to the similarity after comparison, and finding out the face with the highest similarity according to the sequence from high to low of the similarity;
And 8: and the living human face judges whether the human face image is from a real human or from a picture or a video.
Further, in the attendance management method based on face recognition, in the step 6, a multi-index evaluation method or a face symmetry algorithm is adopted for face comparison;
The multi-index evaluation method obtains scores through contrast, brightness, definition and the like, and then weights and calculates the scores;
The face symmetry algorithm is used for analyzing gabor symmetry, and calculating definition or ambiguity by DCT and 1 DCT.
Has the advantages that:
The attendance management is realized by a face detection algorithm, a face tracking algorithm, a face snapshot algorithm, a face quality detection scoring algorithm and a face recognition algorithm in combination with matched front-end camera equipment and a back-end platform service system. As a first line of defense line for school safety protection, the system can timely receive real-time information push of whether students arrive at a school or leave the school for parents of the students. All internal personnel and external visitors are effectively controlled for school implementation. The mode that the monitoring video is checked after the campus is engaged in can be realized, and the mode is upgraded into a security system which actively alarms in real time. From the manager's perspective, the system informs the student of the current location in real time. Meanwhile, the system provides rich report functions and supports checking-in report query and analysis functions of school, year, class, individual, teacher, student and the like.
The recognition speed is high, the accuracy is high, and the influence of ambient light is avoided; the non-contact health and sanitation are completely non-contact, so that the situation that hundreds of people press a fingerprint collecting head by hands all the time in a long year is avoided, and the fingerprint collecting head is not sanitary and is not easy to wear; can be used independently without being connected with a computer, and can complete the functions of personnel registration, face attendance checking, record storage and the like
The recognition speed is high: by constructing a machine learning model with a plurality of hidden layers and massive training data, more useful features are learned by fewer parameters and deeper structures, so that the accuracy of classification or prediction is finally improved. Through the design of a finer model, cutting, pruning, quantification and other technologies, the huge neural network can be operated on a chip with low power consumption and limited calculation power after being deeply compressed.
The accuracy is high: by adopting the leading face recognition algorithm technology in the industry, the accurate recognition degree of the financial payment level of 99.99 percent is achieved; within 30 degrees of pitching and within 30 degrees of left and right, the behavior of wearing glasses, making up and other appearances is changed, and the recognition accuracy of the glasses cannot be influenced.
the device is not influenced by ambient light, the starlight level sensor of the device supports the lowest illumination value to reach or even be lower than 0.001L ux, and a color image is shot under the extremely dark illumination, and meanwhile, the automatic light supplement function is provided.
Drawings
Fig. 1 is a flow chart of an attendance management method based on face recognition.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described clearly and completely below, and it is obvious that the described embodiments are some, 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.
Fig. 1 is a flowchart of an attendance management method based on face recognition, and as shown in fig. 1, the method includes the following steps:
The method comprises the following steps: establishing a face image file of school face;
Step two: acquiring a current human body face image;
Step three: and comparing the face image of the current face with the face image file stock of the school, retrieving and comparing the face print code of the current face image with the face print code in the file stock, confirming the identity of the student and authorizing the operation.
Specifically, the method provided by the invention comprises the following steps:
Step 1: detecting the face, namely detecting the position of the face in the image;
Step 2: matching the face, and positioning the coordinates of irrelevant key points on the face;
And step 3: and (5) snapping the face to obtain a snap image.
And 4, step 4: the human face body characteristic is characterized in that a human face snapshot image is converted into a characteristic capable of representing human face characteristics, and the specific expression form is a string of numerical values with fixed length;
And 5: face verification, namely judging whether the two face images are the same person;
Step 6: comparing the faces, and measuring the similarity between the two faces;
And 7: the face retrieval comprises the steps of comparing an input face with faces in a set, sequencing the faces in the set according to the similarity after comparison, and finding out the face with the highest similarity according to the sequence from high to low of the similarity;
And 8: and the living human face judges whether the human face image is from a real human or from a picture or a video.
The face snapshot comprises the following steps:
Step 1): face real-time image information obtained by face recognition camera or panel machine
Step 2): reading frame video stream to extract video frame, each frame being converted into a picture
Step 3): and (3) capturing and comparing the personnel information in the picture by using a human face detection algorithm to finish the capturing process.
Further, in the attendance management method based on face recognition, in the step 6, a multi-index evaluation method or a face symmetry algorithm is adopted for face comparison;
The multi-index evaluation method obtains scores through contrast, brightness, definition and the like, and then weights and calculates the scores;
The face symmetry algorithm is used for analyzing gabor symmetry, and calculating definition or ambiguity by DCT and 1 DCT.
The following is a detailed technical scheme of the invention, which specifically comprises the following steps:
1. Firstly, establishing a face image file of school faces. The face image file of the face of a person is acquired by a camera, the picture of the person is acquired to form the face image file, and feature data which is helpful for face classification is obtained according to the shape description of the face organ and the distance characteristic between the face organ and the person, wherein the feature components generally comprise Euclidean distance, curvature, angle and the like between feature points. The human face is composed of parts such as eyes, a nose, a mouth, a chin and the like, and geometric description of the parts and the structural relationship among the parts can be used as important features for recognizing the human face. According to the geometric characteristic data, a coding algorithm is carried out to generate a face print code and store the face print code;
2. And acquiring a current human body face image. The face image of the current person coming in and going out is captured by a camera or a film is taken for input, and the current face image file is generated into a face print code;
3. And comparing the current face print codes with the school face image file stock. The face print code of the current face image is retrieved and compared with the face print code in the file stock, the identity of the student is confirmed, and the operation is authorized.
In the model training process, the neural network model can be divided into a feature network and a classification network. The feature network is used for converting an input face image into a feature description with a fixed length, and the classification network is used for judging which training face class the feature belongs to. The weights of the feature networks are updated in each training period through a gradient descent method, and the weights of the classification networks are not updated through the gradient descent method, but are directly replaced by the corresponding classes of certificate photo normalized features in the period. By the method, the characteristic network can learn the intrinsic associated information of the image of the same identity in different scenes such as a life photo and a certificate photo more easily, and meanwhile, the difference information of different identities in different scenes is more concerned. Therefore, the performance of the model in the testimony comparison task is further improved under the condition of not carrying out large-scale certificate photo training.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. An attendance management method based on face recognition is characterized by comprising the following steps:
The method comprises the following steps: establishing a face image file of school face;
Step two: acquiring a current human body face image:
Step three: and comparing the face image of the current face with the face image file stock of the school, retrieving and comparing the face print code of the current face image with the face print code in the file stock, confirming the identity of the student and authorizing the operation.
2. The attendance management method based on the face recognition of claim 1, wherein the second step comprises the following steps:
Step 1: detecting the face, namely detecting the position of the face in the image;
Step 2: matching the face, and positioning the coordinates of irrelevant key points on the face;
And step 3: and (5) snapping the face to obtain a snap image.
3. The attendance management method based on the face recognition of claim 2, wherein the face snapshot comprises the following steps:
Step 1): face real-time image information obtained by face recognition camera or panel machine
Step 2): reading frame video stream to extract video frame, each frame being converted into a picture
Step 3): and (3) capturing and comparing the personnel information in the picture by using a human face detection algorithm to finish the capturing process.
4. The attendance management method based on the face recognition of claim 1, wherein the third step comprises the following steps:
And 4, step 4: the human face body characteristic is characterized in that a human face snapshot image is converted into a characteristic capable of representing human face characteristics, and the specific expression form is a string of numerical values with fixed length;
And 5: face verification, namely judging whether the two face images are the same person;
Step 6: comparing the faces, and measuring the similarity between the two faces;
And 7: the face retrieval comprises the steps of comparing an input face with faces in a set, sequencing the faces in the set according to the similarity after comparison, and finding out the face with the highest similarity according to the sequence from high to low of the similarity;
And 8: and the living human face judges whether the human face image is from a real human or from a picture or a video.
5. The attendance management method based on face recognition according to claim 4, characterized in that in the step 6, a multi-index evaluation method or a face symmetry algorithm is adopted for face comparison;
The multi-index evaluation method obtains scores through contrast, brightness, definition and the like, and then weights and calculates the scores;
The face symmetry algorithm is used for analyzing gabor symmetry, and calculating definition or fuzziness through DCT and IDCT.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010184511.9A CN111428597A (en) | 2020-03-04 | 2020-03-04 | Attendance management method based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010184511.9A CN111428597A (en) | 2020-03-04 | 2020-03-04 | Attendance management method based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111428597A true CN111428597A (en) | 2020-07-17 |
Family
ID=71549532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010184511.9A Pending CN111428597A (en) | 2020-03-04 | 2020-03-04 | Attendance management method based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428597A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158931A (en) * | 2021-04-27 | 2021-07-23 | 河南能创电子科技有限公司 | Low-voltage centralized reading, operation and maintenance implementation method based on AI intelligent face recognition technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930616A (en) * | 2012-10-06 | 2013-02-13 | 南京大五教育科技有限公司 | Smiling face sign-in system for early childhood education |
| CN108986245A (en) * | 2018-06-14 | 2018-12-11 | 深圳市商汤科技有限公司 | Work attendance method and terminal based on recognition of face |
| CN109145734A (en) * | 2018-07-17 | 2019-01-04 | 深圳市巨龙创视科技有限公司 | Algorithm is captured in IPC Intelligent human-face identification based on 4K platform |
| CN110827432A (en) * | 2019-11-11 | 2020-02-21 | 深圳算子科技有限公司 | Class attendance checking method and system based on face recognition |
-
2020
- 2020-03-04 CN CN202010184511.9A patent/CN111428597A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930616A (en) * | 2012-10-06 | 2013-02-13 | 南京大五教育科技有限公司 | Smiling face sign-in system for early childhood education |
| CN108986245A (en) * | 2018-06-14 | 2018-12-11 | 深圳市商汤科技有限公司 | Work attendance method and terminal based on recognition of face |
| CN109145734A (en) * | 2018-07-17 | 2019-01-04 | 深圳市巨龙创视科技有限公司 | Algorithm is captured in IPC Intelligent human-face identification based on 4K platform |
| CN110827432A (en) * | 2019-11-11 | 2020-02-21 | 深圳算子科技有限公司 | Class attendance checking method and system based on face recognition |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158931A (en) * | 2021-04-27 | 2021-07-23 | 河南能创电子科技有限公司 | Low-voltage centralized reading, operation and maintenance implementation method based on AI intelligent face recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934176B (en) | Pedestrian recognition system, recognition method, and computer-readable storage medium | |
| Jain et al. | Latent fingerprint matching | |
| CN111325115B (en) | Cross-modal countervailing pedestrian re-identification method and system with triple constraint loss | |
| KR100974293B1 (en) | METHOD AND SYSTEM FOR AUTOMATED FACE DETECTION and Recognition | |
| Lucey et al. | Automatically detecting pain in video through facial action units | |
| CN109819208A (en) | A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring | |
| CN102682309B (en) | Face feature registering method and device based on template learning | |
| CN106650693A (en) | Multi-feature fusion identification algorithm used for human face comparison | |
| CN107967458A (en) | A kind of face identification method | |
| CN109255289B (en) | Cross-aging face recognition method based on unified generation model | |
| US20220180534A1 (en) | Pedestrian tracking method, computing device, pedestrian tracking system and storage medium | |
| CN106355154B (en) | Method for detecting frequent passing of people in surveillance video | |
| CN103049459A (en) | Feature recognition based quick video retrieval method | |
| CN111127830A (en) | Alarm method, alarm system and readable storage medium based on monitoring equipment | |
| CN104239766A (en) | Video and audio based identity authentication method and system for nuclear power plants | |
| Bhanu et al. | Human ear recognition by computer | |
| CN107977439A (en) | A kind of facial image base construction method | |
| CN108846269A (en) | One kind is towards manifold identity identifying method and identification authentication system | |
| Mustakim et al. | Face recognition system based on raspberry Pi platform | |
| Kumar et al. | Face Recognition Attendance System Using Local Binary Pattern Algorithm | |
| CN114581990A (en) | Intelligent running test method and device | |
| RU2005100267A (en) | METHOD AND SYSTEM OF AUTOMATIC VERIFICATION OF THE PRESENCE OF A LIVING FACE OF A HUMAN IN BIOMETRIC SECURITY SYSTEMS | |
| CN111428597A (en) | Attendance management method based on face recognition | |
| Kadhim et al. | A multimodal biometric database and case study for face recognition based deep learning | |
| Ndubuisi et al. | Digital Criminal Biometric Archives (DICA) and Public Facial Recognition System (FRS) for Nigerian criminal investigation using HAAR cascades classifier technique |
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 |