CN112052731A - Intelligent portrait recognition card punching attendance system and method - Google Patents
Intelligent portrait recognition card punching attendance system and method Download PDFInfo
- Publication number
- CN112052731A CN112052731A CN202010754291.9A CN202010754291A CN112052731A CN 112052731 A CN112052731 A CN 112052731A CN 202010754291 A CN202010754291 A CN 202010754291A CN 112052731 A CN112052731 A CN 112052731A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- image
- recognition
- identification
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004080 punching Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 51
- 238000013459 approach Methods 0.000 claims abstract description 21
- 238000012795 verification Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000586 desensitisation Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 210000000887 face Anatomy 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 230000006698 induction Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the technical field of attendance management, and discloses an intelligent portrait recognition card punching attendance system and a method, which comprise the following steps: the identity information acquisition module acquires user information in advance; the infrared identification module senses whether a person approaches by using infrared equipment; when a person approaches, the image acquisition module acquires the face of the person by using the camera equipment when the person approaches; the main control module controls the face recognition module to recognize and verify the collected face image, and when the face verification is passed, the living body detection module performs living body detection and recognition; the entrance guard control module controls entrance guard to open when face recognition passes and living body detection recognition passes. The method greatly reduces the identification time, and effectively reduces the operation complexity of the model on the premise of ensuring the precision; the invention has high identification efficiency and high identification accuracy, enhances the anti-cheating effect, improves the working efficiency of the attendance system and the degree of freedom of attendance, realizes the automation of the attendance process and greatly improves the attendance efficiency.
Description
Technical Field
The invention belongs to the technical field of attendance management, and particularly relates to an intelligent portrait recognition card punching attendance system and method.
Background
At present: with the progress of internet technology and information technology, the face recognition algorithm is deeply researched. At present, the application of a face recognition algorithm is wide, the face recognition algorithm exists in various aspects in real life, and an intelligent attendance system is an important embodiment of the face detection and recognition algorithm. As an intelligent attendance checking mode, the human face attendance checking method has important practical significance and use value, such as attendance or attendance check-in, access check and the like.
Most of the existing card punching attendance systems are based on keys, passwords, access control cards or fingerprint identification and the like, the keys, the passwords and the access control cards are easy to crack and copy, and the safety factor is low; voice or fingerprint recognition is easy to counterfeit, and the equipment generally has high cost and low efficiency in large batch.
Through the above analysis, the problems and defects of the prior art are as follows: the existing attendance system is low in safety factor, high in equipment cost, low in identification efficiency and low in intelligent degree.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent portrait recognition card punching attendance system and method.
The invention is realized in such a way that an intelligent portrait recognition card punching attendance method comprises the following steps:
the method comprises the following steps that firstly, an identity information acquisition module acquires identity information, face information and other related information of a user in advance by using radio frequency identification equipment, input equipment and camera equipment; the infrared identification module senses whether a person approaches by using infrared equipment;
the infrared identification module utilizes infrared equipment to sense whether someone is close to including:
the infrared sensor performs human body induction to generate a sensing signal;
performing analog-to-digital conversion on the generated sensing signal to obtain a digital signal;
carrying out Fourier transform on the digital signal to obtain a frequency domain characteristic curve of the digital signal;
analyzing the frequency domain characteristic curve of the obtained digital signal, and judging whether human motion exists; when no human body moves, judging that no human body approaches; if the human body moves, further judging that the motion state of the human body is close or far, and when the motion state is far, judging that no person approaches; if the motion state is approaching, judging that a person approaches;
when a person approaches, the image acquisition module acquires the face of the person by using the camera equipment; the main control module controls the face recognition module to recognize and verify the collected face image, and when the face verification is passed, the living body detection module performs living body detection and recognition;
the identifying and verifying the collected face image comprises the following steps:
carrying out gray level equalization and median filtering processing on the acquired image; constructing a face recognition model and carrying out model training;
carrying out alignment processing and feature extraction on the processed image;
carrying out face recognition by using the constructed face detection model based on the extracted face features;
the face recognition model construction method comprises the following steps:
acquiring a data set of a face image, and cleaning the data set; augmenting the data of the dataset by image rotation, translation and scaling;
dividing a data set into a training set, a testing set and a verification set according to a certain proportion;
carrying out model parameter configuration, and constructing a face recognition model and a loss function;
and performing model training by using an Adam back propagation algorithm, and performing model testing and verification by using a test set and a verification set respectively to obtain the face recognition model.
Step three, the entrance guard control module controls entrance guard to open when the face recognition passes and the living body detection recognition passes; the storage module stores pre-acquired identity information, face information and other related information of the user, and simultaneously stores face information, user leave information, card punching information and access information acquired by the camera equipment;
step four, the display module displays the acquired image and the identification result; the voice broadcasting module broadcasts the recognition result; and when the face detection identification fails or the living body detection identification fails, the alarm module utilizes an alarm to alarm in real time or sends an alarm record to the client to alarm remotely.
Further, in the second step, the performing the living body detection and identification specifically includes:
step A, acquiring an acquired face image;
b, extracting feature data in the face image;
step C, performing living body identification on the characteristic data by adopting a living body identification model;
and D, desensitizing the characteristic data and adding the desensitized characteristic data into a sample characteristic database.
Further, in step D, the desensitization treatment is performed by:
extracting data related to living body identification in the characteristic data;
carrying out encryption operation on the characteristic data;
and carrying out encryption operation on the label name of the feature data.
Further, the extracting data related to living body identification in the feature data includes:
clustering the characteristic data to complete classification;
selecting feature data related to living body identification from the feature data according to a result of the classification.
Further, in the second step, the aligning and feature extracting the processed image includes:
1) the processed image data is subjected to original localization, scaling and averaging to obtain the average shape of the image; meanwhile, carrying out standardization processing on the image;
2) extracting coordinate information of 68 key points of the normalized face image;
3) calculating the coordinates of the central points of the left eye and the right eye to obtain the angle of the central point connecting line, calculating the actual distance between the two eyes according to the coordinate information of the left eye and the right eye, calculating the expected size of zooming by dividing the expected distance, and determining the rotating angle;
4) calculating the coordinates of the center points of the actual left eye and the actual right eye to obtain the parameter information of the mapping matrix of the zooming and rotating parts;
5) calculating to obtain translation coordinate information according to actual and expected coordinates of the central point of the two eyes;
6) and giving the width and height of the expected picture to obtain the aligned image.
Further, in the second step, the aligning and feature extracting the processed image further includes:
(1) acquiring an image after alignment processing; blocking the aligned face image to obtain N image blocks, wherein N is an integer greater than 1;
(2) respectively adopting radiuses with 5 different pixel sizes to respectively carry out multi-scale LBP characteristic extraction on each image block to obtain the multi-scale LBP characteristic of each image block;
(3) and combining the multi-scale LBP characteristics of the N image blocks, and performing normalization processing to obtain the LBP characteristics of the face image.
Further, in the third step, the controlling the entrance guard to open when the face recognition passes and the living body detection recognition passes includes: the method comprises the steps of converting a color image of a human face into an HSV color space, extracting color distribution characteristics, extracting ambiguity characteristic information by using a gray level co-occurrence matrix, taking the two characteristics as discrimination information of a true and false human face image, and judging a living body by using an SVM.
Another object of the present invention is to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the intelligent portrait recognition card-punching attendance method when executed on an electronic device.
Another object of the present invention is to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to execute the intelligent portrait recognition card punching attendance method.
Another object of the present invention is to provide an intelligent portrait recognition card-punching attendance system, which includes:
the system comprises an identity information acquisition module, an infrared recognition module, an image acquisition module, a main control module, a face recognition module, a living body detection module, an access control module, a storage module, a leave-asking module, a data statistics module, a display module, a voice broadcast module and an alarm module;
the identity information acquisition module is connected with the main control module and is used for acquiring identity information, face information and other related information of a user in advance by utilizing the radio frequency identification equipment, the input equipment and the camera equipment;
the infrared identification module is connected with the main control module and used for sensing whether a person approaches by utilizing infrared equipment;
the image acquisition module is connected with the main control module and is used for acquiring human faces by utilizing the camera equipment when a person approaches;
the main control module is connected with the identity information acquisition module, the infrared recognition module, the image acquisition module, the face recognition module, the living body detection module, the access control module, the storage module, the leave-asking module, the data statistics module, the display module, the voice broadcast module and the alarm module and is used for controlling each module to normally operate by utilizing a controller or a single chip microcomputer;
the face recognition module is connected with the main control module and is used for recognizing the collected face image;
the living body detection module is connected with the main control module and is used for carrying out living body detection and identification when the face identification passes;
the access control module is connected with the main control module and is used for controlling the access to be opened when the face recognition passes and the living body detection recognition passes;
the storage module is connected with the main control module and is used for storing the pre-acquired identity information, face information and other related information of the user and simultaneously storing the face information, user leave information, card punching information and access information acquired by the camera equipment;
the leave-asking module is connected with the main control module and used for acquiring a leave-asking record of the user;
the data statistics module is connected with the main control module and used for carrying out statistics on the attendance records and generating a corresponding statistical report;
the display module is connected with the main control module and used for displaying the acquired image and the identification result;
the voice broadcasting module is connected with the main control module and used for broadcasting the recognition result;
and the alarm module is connected with the main control module and used for giving an alarm in real time or sending an alarm record to the client for remote alarm when the face detection identification fails or the living body detection identification fails.
By combining all the technical schemes, the invention has the advantages and positive effects that: the method greatly reduces the identification time, and effectively reduces the operation complexity of the model on the premise of ensuring the precision; the invention has high identification efficiency and high identification accuracy, enhances the anti-cheating effect, improves the working efficiency of the attendance system and the degree of freedom of attendance, realizes the automation of the attendance process and greatly improves the attendance efficiency. The invention generates the attendance result in real time, is efficient and rapid, and prevents the attendance from being signed or checked and forging the attendance record.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a flowchart of an intelligent portrait identification card punching attendance method provided by an embodiment of the invention.
Fig. 2 is a flowchart for performing living body detection and identification according to an embodiment of the present invention.
Fig. 3 is a flowchart of alignment processing and feature extraction performed on a processed image according to an embodiment of the present invention.
Fig. 4 is a flowchart of alignment processing and feature extraction performed on a processed image according to an embodiment of the present invention.
Fig. 5 is a block diagram of a structure of an intelligent portrait recognition card-punching attendance system provided by an embodiment of the invention;
in the figure: 1. an identity information acquisition module; 2. an infrared recognition module; 3. an image acquisition module; 4. a main control module; 5. a face recognition module; 6. a living body detection module; 7. an access control module; 8. a storage module; 9. a leave-asking module; 10. a data statistics module; 11. a display module; 12. a voice broadcasting module; 13. and an alarm module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides an intelligent portrait recognition card punching attendance system and a method thereof, and the invention is described in detail below with reference to the attached drawings.
As shown in fig. 1, the method for checking attendance by recognizing a card by using an intelligent portrait according to an embodiment of the present invention includes:
s101, an identity information acquisition module acquires identity information, face information and other related information of a user in advance by using radio frequency identification equipment, input equipment and camera equipment; the infrared identification module senses whether a person approaches by using infrared equipment;
s102, when a person approaches, the image acquisition module acquires the face of the person by using the camera equipment; the main control module controls the face recognition module to recognize and verify the collected face image, and when the face verification is passed, the living body detection module performs living body detection and recognition;
s103, the entrance guard control module controls entrance guard to open when the face recognition passes and the living body detection recognition passes; the storage module stores pre-acquired identity information, face information and other related information of the user, and simultaneously stores face information, user leave information, card punching information and access information acquired by the camera equipment;
s104, displaying the acquired image and the identification result by a display module; the voice broadcasting module broadcasts the recognition result; and when the face detection identification fails or the living body detection identification fails, the alarm module utilizes an alarm to alarm in real time or sends an alarm record to the client to alarm remotely.
The method for identifying and verifying the collected face image comprises the following steps:
carrying out gray level equalization and median filtering processing on the acquired image; constructing a face recognition model and carrying out model training;
carrying out alignment processing and feature extraction on the processed image;
and carrying out face recognition by using the constructed face detection model based on the extracted face features.
The method for constructing the face recognition model provided by the embodiment of the invention comprises the following steps:
acquiring a data set of a face image, and cleaning the data set; augmenting the data of the dataset by image rotation, translation and scaling;
dividing a data set into a training set, a testing set and a verification set according to a certain proportion;
carrying out model parameter configuration, and constructing a face recognition model and a loss function;
and performing model training by using an Adam back propagation algorithm, and performing model testing and verification by using a test set and a verification set respectively to obtain the face recognition model.
As shown in fig. 2, in step S102, the performing living body detection and identification provided by the embodiment of the present invention specifically includes:
s201, acquiring an acquired face image;
s202, extracting feature data in the face image;
s203, performing living body identification on the characteristic data by adopting a living body identification model;
and S204, desensitizing the characteristic data and adding the desensitized characteristic data into a sample characteristic database.
In step S204, the desensitization processing provided in the embodiment of the present invention is:
extracting data related to living body identification in the characteristic data;
carrying out encryption operation on the characteristic data;
and carrying out encryption operation on the label name of the feature data.
The method for extracting the data related to living body identification in the feature data comprises the following steps:
clustering the characteristic data to complete classification;
selecting feature data related to living body identification from the feature data according to a result of the classification.
As shown in fig. 3, in step S102, the aligning and feature extracting process performed on the processed image according to the embodiment of the present invention includes:
s301, performing original localization, scaling and averaging on the processed image data to obtain an average shape of the image; meanwhile, carrying out standardization processing on the image;
s302, extracting coordinate information of 68 key points of the normalized human face image;
s303, calculating coordinates of central points of the left eye and the right eye to obtain an angle of a central point connecting line, calculating an actual distance between the two eyes according to coordinate information of the left eye and the right eye, calculating to obtain an expected size of zooming by dividing the distance with the expected distance, and determining a rotating angle;
s304, calculating the coordinates of the center points of the actual left eye and the actual right eye to obtain the parameter information of the mapping matrix of the zooming and rotating parts;
s305, calculating to obtain translation coordinate information according to actual and expected coordinates of the central point of the two eyes;
s306, giving the width and the height of the expected picture to obtain the image after the alignment processing.
As shown in fig. 4, in step S102, the performing alignment processing and feature extraction on the processed image further includes:
s401, acquiring an image after alignment processing; blocking the aligned face image to obtain N image blocks, wherein N is an integer greater than 1;
s402, respectively adopting radiuses with 5 different pixel sizes to respectively carry out multi-scale LBP feature extraction on each image block to obtain multi-scale LBP features of each image block;
and S403, combining the multi-scale LBP characteristics of the N image blocks, and performing normalization processing to obtain the LBP characteristics of the face image.
In step S103, the controlling the entrance guard to open when the face recognition passes and the living body detection recognition passes according to the embodiment of the present invention includes: the method comprises the steps of converting a color image of a human face into an HSV color space, extracting color distribution characteristics, extracting ambiguity characteristic information by using a gray level co-occurrence matrix, taking the two characteristics as discrimination information of a true and false human face image, and judging a living body by using an SVM.
As shown in fig. 5, the intelligent portrait identification card-punching attendance system provided by the embodiment of the present invention includes:
the system comprises an identity information acquisition module 1, an infrared recognition module 2, an image acquisition module 3, a main control module 4, a face recognition module 5, a living body detection module 6, an access control module 7, a storage module 8, a leave asking module 9, a data statistics module 10, a display module 11, a voice broadcasting module 12 and an alarm module 13;
the identity information acquisition module 1 is connected with the main control module 4 and is used for acquiring identity information, face information and other related information of a user in advance by utilizing radio frequency identification equipment, input equipment and camera equipment;
the infrared identification module 2 is connected with the main control module 4 and used for sensing whether a person approaches by using infrared equipment;
the image acquisition module 3 is connected with the main control module 4 and is used for acquiring human faces by utilizing camera equipment when a person approaches;
the main control module 4 is connected with the identity information acquisition module 1, the infrared identification module 2, the image acquisition module 3, the face identification module 5, the living body detection module 6, the entrance guard control module 7, the storage module 8, the leave asking module 9, the data statistics module 10, the display module 11, the voice broadcasting module 12 and the alarm module 13, and is used for controlling each module to normally operate by using a controller or a single chip microcomputer;
the face recognition module 5 is connected with the main control module 4 and used for recognizing the collected face image;
the living body detection module 6 is connected with the main control module 4 and is used for carrying out living body detection and identification when the face identification passes;
the access control module 7 is connected with the main control module 4 and is used for controlling the access to be opened when the face recognition passes and the living body detection recognition passes;
the storage module 8 is connected with the main control module 4 and is used for storing the pre-acquired identity information, face information and other related information of the user and simultaneously storing the face information, user leave information, card punching information and access information acquired by the camera equipment;
the leave asking module 9 is connected with the main control module 4 and used for acquiring a leave asking record of a user;
the data statistics module 10 is connected with the main control module 4 and used for performing statistics on the attendance records and generating a corresponding statistical report;
the display module 11 is connected with the main control module 4 and is used for displaying the acquired images and the identification result;
the voice broadcasting module 12 is connected with the main control module 4 and used for broadcasting the recognition result;
and the alarm module 13 is connected with the main control module 4 and is used for giving an alarm in real time or sending an alarm record to the client for remote alarm when the face detection identification fails or the living body detection identification fails.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. An intelligent portrait recognition card punching attendance method is characterized by comprising the following steps:
the method comprises the following steps that firstly, an identity information acquisition module acquires identity information, face information and other related information of a user in advance by using radio frequency identification equipment, input equipment and camera equipment; the infrared identification module senses whether a person approaches by using infrared equipment;
the infrared identification module utilizes infrared equipment to sense whether someone is close to including:
the infrared sensor performs human body induction to generate a sensing signal;
performing analog-to-digital conversion on the generated sensing signal to obtain a digital signal;
carrying out Fourier transform on the digital signal to obtain a frequency domain characteristic curve of the digital signal;
analyzing the frequency domain characteristic curve of the obtained digital signal, and judging whether human motion exists; when no human body moves, judging that no human body approaches; if the human body moves, further judging that the motion state of the human body is close or far, and when the motion state is far, judging that no person approaches; if the motion state is approaching, judging that a person approaches;
when a person approaches, the image acquisition module acquires the face of the person by using the camera equipment; the main control module controls the face recognition module to recognize and verify the collected face image, and when the face verification is passed, the living body detection module performs living body detection and recognition;
the identifying and verifying the collected face image comprises the following steps:
carrying out gray level equalization and median filtering processing on the acquired image; constructing a face recognition model and carrying out model training;
carrying out alignment processing and feature extraction on the processed image;
carrying out face recognition by using the constructed face detection model based on the extracted face features;
the face recognition model construction method comprises the following steps:
acquiring a data set of a face image, and cleaning the data set; augmenting the data of the dataset by image rotation, translation and scaling;
dividing a data set into a training set, a testing set and a verification set according to a certain proportion;
carrying out model parameter configuration, and constructing a face recognition model and a loss function;
and performing model training by using an Adam back propagation algorithm, and performing model testing and verification by using a test set and a verification set respectively to obtain the face recognition model.
Step three, the entrance guard control module controls entrance guard to open when the face recognition passes and the living body detection recognition passes; the storage module stores pre-acquired identity information, face information and other related information of the user, and simultaneously stores face information, user leave information, card punching information and access information acquired by the camera equipment;
step four, the display module displays the acquired image and the identification result; the voice broadcasting module broadcasts the recognition result; and when the face detection identification fails or the living body detection identification fails, the alarm module utilizes an alarm to alarm in real time or sends an alarm record to the client to alarm remotely.
2. The method for checking attendance by punching a card through intelligent portrait identification of claim 1, wherein in the second step, the performing of the living body detection identification specifically comprises:
step A, acquiring an acquired face image;
b, extracting feature data in the face image;
step C, performing living body identification on the characteristic data by adopting a living body identification model;
and D, desensitizing the characteristic data and adding the desensitized characteristic data into a sample characteristic database.
3. The intelligent portrait recognition card punching attendance method of claim 2, wherein in the step D, the desensitization treatment is carried out as follows:
extracting data related to living body identification in the characteristic data;
carrying out encryption operation on the characteristic data;
and carrying out encryption operation on the label name of the feature data.
4. The intelligent portrait recognition card punching attendance method as claimed in claim 3, wherein the extracting of the data related to the living body recognition in the feature data comprises:
clustering the characteristic data to complete classification;
selecting feature data related to living body identification from the feature data according to a result of the classification.
5. The intelligent portrait recognition card punching attendance method of claim 1, wherein in the second step, the alignment processing and feature extraction of the processed image comprises:
1) the processed image data is subjected to original localization, scaling and averaging to obtain the average shape of the image; meanwhile, carrying out standardization processing on the image;
2) extracting coordinate information of 68 key points of the normalized face image;
3) calculating the coordinates of the central points of the left eye and the right eye to obtain the angle of the central point connecting line, calculating the actual distance between the two eyes according to the coordinate information of the left eye and the right eye, calculating the expected size of zooming by dividing the expected distance, and determining the rotating angle;
4) calculating the coordinates of the center points of the actual left eye and the actual right eye to obtain the parameter information of the mapping matrix of the zooming and rotating parts;
5) calculating to obtain translation coordinate information according to actual and expected coordinates of the central point of the two eyes;
6) and giving the width and height of the expected picture to obtain the aligned image.
6. The method for checking attendance by punching a card through intelligent portrait recognition of claim 1, wherein in the second step, the alignment processing and feature extraction of the processed image further comprises:
(1) acquiring an image after alignment processing; blocking the aligned face image to obtain N image blocks, wherein N is an integer greater than 1;
(2) respectively adopting radiuses with 5 different pixel sizes to respectively carry out multi-scale LBP characteristic extraction on each image block to obtain the multi-scale LBP characteristic of each image block;
(3) and combining the multi-scale LBP characteristics of the N image blocks, and performing normalization processing to obtain the LBP characteristics of the face image.
7. The intelligent portrait recognition card punching attendance method of claim 1, wherein in the third step, the controlling of the entrance guard to open when the face recognition passes and the living body detection recognition passes comprises: the method comprises the steps of converting a color image of a human face into an HSV color space, extracting color distribution characteristics, extracting ambiguity characteristic information by using a gray level co-occurrence matrix, taking the two characteristics as discrimination information of a true and false human face image, and judging a living body by using an SVM.
8. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the intelligent portrait identification card punching attendance method of any one of claims 1-7 when executed on an electronic device.
9. A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method of smart portrait recognition card punching attendance as claimed in any one of claims 1 to 7.
10. A smart portrait recognition card-punching attendance system applying the smart portrait recognition card-punching attendance method according to claims 1-7, wherein the smart portrait recognition card-punching attendance system comprises:
the system comprises an identity information acquisition module, an infrared recognition module, an image acquisition module, a main control module, a face recognition module, a living body detection module, an access control module, a storage module, a leave-asking module, a data statistics module, a display module, a voice broadcast module and an alarm module;
the identity information acquisition module is connected with the main control module and is used for acquiring identity information, face information and other related information of a user in advance by utilizing the radio frequency identification equipment, the input equipment and the camera equipment;
the infrared identification module is connected with the main control module and used for sensing whether a person approaches by utilizing infrared equipment;
the image acquisition module is connected with the main control module and is used for acquiring human faces by utilizing the camera equipment when a person approaches;
the main control module is connected with the identity information acquisition module, the infrared recognition module, the image acquisition module, the face recognition module, the living body detection module, the access control module, the storage module, the leave-asking module, the data statistics module, the display module, the voice broadcast module and the alarm module and is used for controlling each module to normally operate by utilizing a controller or a single chip microcomputer;
the face recognition module is connected with the main control module and is used for recognizing the collected face image;
the living body detection module is connected with the main control module and is used for carrying out living body detection and identification when the face identification passes;
the access control module is connected with the main control module and is used for controlling the access to be opened when the face recognition passes and the living body detection recognition passes;
the storage module is connected with the main control module and is used for storing the pre-acquired identity information, face information and other related information of the user and simultaneously storing the face information, user leave information, card punching information and access information acquired by the camera equipment;
the leave-asking module is connected with the main control module and used for acquiring a leave-asking record of the user;
the data statistics module is connected with the main control module and used for carrying out statistics on the attendance records and generating a corresponding statistical report;
the display module is connected with the main control module and used for displaying the acquired image and the identification result;
the voice broadcasting module is connected with the main control module and used for broadcasting the recognition result;
and the alarm module is connected with the main control module and used for giving an alarm in real time or sending an alarm record to the client for remote alarm when the face detection identification fails or the living body detection identification fails.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010754291.9A CN112052731B (en) | 2020-07-30 | 2020-07-30 | Intelligent portrait identification card punching attendance system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010754291.9A CN112052731B (en) | 2020-07-30 | 2020-07-30 | Intelligent portrait identification card punching attendance system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112052731A true CN112052731A (en) | 2020-12-08 |
| CN112052731B CN112052731B (en) | 2024-03-29 |
Family
ID=73602341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010754291.9A Active CN112052731B (en) | 2020-07-30 | 2020-07-30 | Intelligent portrait identification card punching attendance system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112052731B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785742A (en) * | 2021-01-22 | 2021-05-11 | 广东交通职业技术学院 | Attendance system and control method thereof |
| CN112884313A (en) * | 2021-02-05 | 2021-06-01 | 湖南嘿哈猫网络科技有限公司 | Model for effectively calculating energy consumption of user in fitness venue |
| CN113312984A (en) * | 2021-05-08 | 2021-08-27 | 宁波盈芯信息科技有限公司 | Button type man-machine interaction device and method |
| CN113392719A (en) * | 2021-05-21 | 2021-09-14 | 华南农业大学 | Intelligent electronic lock unlocking method, electronic equipment and storage medium |
| CN113570764A (en) * | 2021-07-02 | 2021-10-29 | 厦门科安达智能科技有限公司 | Industrial-grade access control all-purpose card real-time monitoring management system based on enterprise |
| CN113743549A (en) * | 2021-08-21 | 2021-12-03 | 太原向明智控科技有限公司 | Personnel approach recognition alarm system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
| CN109285234A (en) * | 2018-09-29 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Human face identification work-attendance checking method, device, computer installation and storage medium |
| WO2019051665A1 (en) * | 2017-09-13 | 2019-03-21 | 深圳传音通讯有限公司 | Start control method and start control system for smart terminal |
| CN109829691A (en) * | 2019-01-16 | 2019-05-31 | 北京影谱科技股份有限公司 | C/S punch card method and device based on position and deep learning multi-biological feature |
| WO2019134246A1 (en) * | 2018-01-03 | 2019-07-11 | 平安科技（深圳）有限公司 | Facial recognition-based security monitoring method, device, and storage medium |
| WO2019228091A1 (en) * | 2018-06-01 | 2019-12-05 | 杭州海康威视数字技术股份有限公司 | Attendance management method and attendance management device |
| WO2020000196A1 (en) * | 2018-06-26 | 2020-01-02 | 深圳齐心集团股份有限公司 | Face recognition method and apparatus, and access control attendance machine |
| CN110992502A (en) * | 2019-11-18 | 2020-04-10 | 广州杰赛科技股份有限公司 | Face recognition attendance checking method and system and readable storage medium |
-
2020
- 2020-07-30 CN CN202010754291.9A patent/CN112052731B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
| WO2019051665A1 (en) * | 2017-09-13 | 2019-03-21 | 深圳传音通讯有限公司 | Start control method and start control system for smart terminal |
| WO2019134246A1 (en) * | 2018-01-03 | 2019-07-11 | 平安科技（深圳）有限公司 | Facial recognition-based security monitoring method, device, and storage medium |
| WO2019228091A1 (en) * | 2018-06-01 | 2019-12-05 | 杭州海康威视数字技术股份有限公司 | Attendance management method and attendance management device |
| WO2020000196A1 (en) * | 2018-06-26 | 2020-01-02 | 深圳齐心集团股份有限公司 | Face recognition method and apparatus, and access control attendance machine |
| CN109285234A (en) * | 2018-09-29 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Human face identification work-attendance checking method, device, computer installation and storage medium |
| CN109829691A (en) * | 2019-01-16 | 2019-05-31 | 北京影谱科技股份有限公司 | C/S punch card method and device based on position and deep learning multi-biological feature |
| CN110992502A (en) * | 2019-11-18 | 2020-04-10 | 广州杰赛科技股份有限公司 | Face recognition attendance checking method and system and readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 张心怡;李刚;: "智能人脸识别考勤***", 电子制作, no. 09, 1 May 2019 (2019-05-01) * |
| 霍妍;李长明;: "基于人脸识别考勤***的设计与实现", 通化师范学院学报, no. 12, 20 December 2016 (2016-12-20) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785742A (en) * | 2021-01-22 | 2021-05-11 | 广东交通职业技术学院 | Attendance system and control method thereof |
| CN112884313A (en) * | 2021-02-05 | 2021-06-01 | 湖南嘿哈猫网络科技有限公司 | Model for effectively calculating energy consumption of user in fitness venue |
| CN113312984A (en) * | 2021-05-08 | 2021-08-27 | 宁波盈芯信息科技有限公司 | Button type man-machine interaction device and method |
| CN113392719A (en) * | 2021-05-21 | 2021-09-14 | 华南农业大学 | Intelligent electronic lock unlocking method, electronic equipment and storage medium |
| CN113570764A (en) * | 2021-07-02 | 2021-10-29 | 厦门科安达智能科技有限公司 | Industrial-grade access control all-purpose card real-time monitoring management system based on enterprise |
| CN113743549A (en) * | 2021-08-21 | 2021-12-03 | 太原向明智控科技有限公司 | Personnel approach recognition alarm system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112052731B (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052731B (en) | Intelligent portrait identification card punching attendance system and method | |
| WO2020207189A1 (en) | Method and device for identity authentication, storage medium, and computer device | |
| CN109359548B (en) | Multi-face recognition monitoring method and device, electronic equipment and storage medium | |
| CN108875833B (en) | Neural network training method, face recognition method and device | |
| CN109886697B (en) | Operation determination method and device based on expression group and electronic equipment | |
| CN101558431B (en) | Face authentication device | |
| CN109285234B (en) | Face recognition attendance checking method and device, computer device and storage medium | |
| CN107133608A (en) | Identity authorization system based on In vivo detection and face verification | |
| CN102629320B (en) | Ordinal measurement statistical description face recognition method based on feature level | |
| CN101145261A (en) | ATM system automatic recognition device | |
| CN105335722A (en) | Detection system and detection method based on depth image information | |
| CN103324912A (en) | Face recognition system and method for ATM | |
| CN109376604B (en) | Age identification method and device based on human body posture | |
| CN101739742A (en) | Networking type multi-channel access control and attendance system | |
| CN110555931A (en) | Face detection and gate inhibition system device based on deep learning recognition | |
| CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
| CN104636730A (en) | Method and device for face verification | |
| CN111178136A (en) | Big data-based smart campus identity recognition method and system | |
| CN112183219A (en) | Public safety video monitoring method and system based on face recognition | |
| CN109145812A (en) | Squatter building monitoring method and device | |
| CN105184236A (en) | Robot-based face identification system | |
| CN106845500A (en) | A kind of human face light invariant feature extraction method based on Sobel operators | |
| CN115116119A (en) | Face recognition system based on digital image processing technology | |
| CN101739571A (en) | Block principal component analysis-based device for confirming face | |
| Kalangi et al. | Deployment of Haar Cascade algorithm to detect real-time faces |
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 |