CN114612068B - Automatic attendance checking and supplementing method and device - Google Patents
Automatic attendance checking and supplementing method and device Download PDFInfo
- Publication number
- CN114612068B CN114612068B CN202210240073.2A CN202210240073A CN114612068B CN 114612068 B CN114612068 B CN 114612068B CN 202210240073 A CN202210240073 A CN 202210240073A CN 114612068 B CN114612068 B CN 114612068B
- Authority
- CN
- China
- Prior art keywords
- data
- staff
- classification
- image
- approval
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000001502 supplementing effect Effects 0.000 title claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010056342 Pulmonary mass Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image recognition, in particular to an automatic attendance checking and label supplementing method, which comprises the following steps: s1, installing an acquisition camera and acquiring data; s2, data processing; s3, extracting features; s4 determining a classification mark; s5, designing a classifier model; s6, optimizing a classifier; s7, generating a approval result. Compared with the prior art, the method and the device have the advantages that the image recognition technology is applied to daily attendance of enterprises, the image information of staff is collected from each entrance and exit of the enterprises, and the staff is associated with self-transmission images of the staff to be supplemented according to a specific algorithm, so that a conclusion is obtained whether the staff goes on duty before work or goes off duty after work. The accuracy and the reliability of the automatic approval result are ensured, the links of manpower approval are saved, and the problem that post approval causes abnormal wage release possibly occurs.
Description
Technical Field
The invention relates to the technical field of image recognition, and particularly provides an automatic attendance checking and label supplementing method and device.
Background
Image recognition technology is an important field of artificial intelligence, which refers to technology that performs object recognition on images to identify targets and objects in various modes. Image recognition is a comprehensive problem, covers technologies such as image matching, image classification, image retrieval, face detection, pedestrian detection and the like, has wide application value in the fields such as internet search engines, automatic driving, medical analysis, remote sensing analysis and the like, and is applied to living aspects. Such as: in the education field, the current popular intelligent search questions are adopted, students encounter questions which cannot be met, the questions are shot by using a mobile phone, the questions in the pictures are identified through an image identification technology, and then the questions in the pictures are automatically searched out on the internet, so that the time of manual input is greatly reduced; in the medical field, the image recognition technology can diagnose the lung nodule, can reach the level of doctors in a good hospital, and can enjoy accurate medical diagnosis service in small places by using the tool or the system.
The basic process of image recognition mainly comprises the steps of information acquisition, preprocessing, feature extraction and selection, classifier design and classification decision. With the continuous development of society and technology, the monitoring system is spread over all corners of our work and life, enterprise office buildings, roads and malls are all provided with various 24-hour operation monitoring systems, the monitoring systems can capture people and objects in the nearby range in real time and various events generated by the people and objects, and the monitoring systems running around the society provide a wide information source for image recognition.
At present, the situation that the image recognition technology is applied to the daily attendance of the enterprise is relatively few, and if the image recognition technology can be applied to the daily attendance of the enterprise, the approval link can be saved, so that the intellectualization is realized.
Disclosure of Invention
The invention provides an automatic attendance checking and label supplementing method with strong practicability aiming at the defects of the prior art.
The invention further aims to provide an automatic attendance checking and label supplementing device which is reasonable in design, safe and applicable.
The technical scheme adopted for solving the technical problems is as follows:
an automatic attendance checking and supplementing method comprises the following steps:
s1, installing an acquisition camera and acquiring data;
s2, data processing;
s3, extracting features;
s4, determining a classification mark;
s5, designing a classifier model;
s6, optimizing a classifier;
s7, generating a approval result.
Further, in step S1, the enterprise installs an acquisition camera at each entrance and exit, acquires data of personnel images, places and time, and uploads the acquired data to a designated database as raw data, where the acquired data sets a validity period.
Further, in step S2, original personnel image, place and time data in the database are cleaned, duplication is removed, redundant data, dirty data and noise data are removed, and the cleaned data are stored in the system database.
Further, in step S3, a specific machine learning algorithm is used to perform feature extraction on the cleaned data, and the data is normalized into 128-bit small data and stored in a database lookup table.
Further, in step S4, staff in the enterprise self-transfers the pictures to the system database, and feature extraction is performed on the pictures according to the mode of step S3, and the pictures are stored in the system database to be compared.
Further, in step S5, the image feature data of the tab staff is used as a classification mark, the image feature data of the tab staff is used as data to be marked, and a training sample required by classification is obtained, which is expressed as x1= [ x11, x12, x13, …, x1n ], the corresponding result set y= { L1, L2}, L1 represents that the image feature is associable, and L2 represents that the image feature is not associable.
Further, the training examples are subjected to classification learning by using a two-classification algorithm, a labeling model Y=f (x) is established, for an unknown example x, the matched images can be predicted according to the model, the holding probability is calculated according to the probability, and the larger the holding probability is, the higher the matching degree of the images is.
Further, in step S6, the classifier model is trained multiple times according to the ten-fold cross-validation method, and the classifier model is continuously optimized.
Further, in step S7, according to the classification result of the classifier model, if the fitness reaches the standard, the image collected by the camera is considered to be the employee, and before the image collection time is the working time specified by the enterprise, the employee is considered to arrive at the post on time, and the approval passes, otherwise, the approval does not pass.
An automatic attendance device of filling in labels, includes: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform an automatic attendance check supplementing method.
Compared with the prior art, the automatic attendance checking and label supplementing method and device have the following outstanding beneficial effects:
the invention applies the image recognition technology to the daily attendance of enterprises, acquires the image information of staff from each entrance and exit of the enterprises, and associates with self-transmission images of staff to be checked according to a specific algorithm to obtain a conclusion whether the staff goes on duty before work or goes off duty after work. The accuracy and the reliability of the automatic approval result are ensured, the links of manpower approval are saved, and the problem that post approval causes abnormal wage release possibly occurs.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an automatic attendance compensation method.
Detailed Description
In order to provide a better understanding of the aspects of the present invention, the present invention will be described in further detail with reference to specific embodiments. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A preferred embodiment is given below:
as shown in fig. 1, an automatic attendance checking and labeling method in this embodiment includes the following steps:
s1, installing an acquisition camera and acquiring data:
the method comprises the steps that an acquisition camera is installed at each entrance and exit of an enterprise, personnel image, place and time data are acquired, the acquired data are uploaded to a specified database to serve as original data, and the effective period of the data is formulated according to the attendance period of the enterprise.
S2, data processing:
cleaning original personnel images, places and time data in a database, removing duplication, removing redundant data, dirty data and noise data, and storing the cleaned data into a system database.
S3, feature extraction:
specific machine learning algorithms are used, such as Scale Invariant Feature Transforms (SIFTs), speeded Up Robust Features (SURFs), direction gradient Histograms (HOG), etc. And extracting the characteristics of the cleaned data, and regularizing the data into 128-bit small data which are stored in a database lookup table. And the later retrieval and inquiry are convenient.
S4, determining classification marks:
and (3) the staff automatically transmits the pictures to the system, extracts the characteristics of the pictures according to the mode of the step (3), and stores the pictures in a database to be compared. The staff photo can be updated at any time for more accurate judgment because parameters such as staff appearance, hairstyle and the like can be changed.
S5, designing a classifier model:
taking the image feature data of the label supplementing staff as a classification label, collecting the image feature data as data to be labeled, and obtaining a training sample required by classification, wherein the training sample is expressed as x1= [ x11, x12, x13, …, x1n ], a corresponding result set y= { L1, L2}, the label L1 represents that the image features can be correlated, and the label L2 represents that the image features cannot be correlated.
The training sample uses a two-classification algorithm to perform classification learning, and a labeling model Y=f (x) is established. For an unknown sample x, the matched image can be predicted according to the model, and the holding probability is calculated according to the probability, so that the higher the holding probability is, the higher the matching degree of the image is.
S6, optimizing a classifier:
and training the classification model for multiple times according to a ten-fold cross-validation mode, and continuously optimizing the classifier model to ensure that the performance of the classifier is more stable.
S7, generating a supplementary approval result:
according to the classification result of the classifier model, if the coincidence degree reaches more than 90% (the standard can be adjusted according to the actual situation), the image collected by the camera is considered to be the employee, and the image collection time is before the working time specified by the enterprise, the employee is considered to arrive at the post on time, the approval passes, and otherwise the approval passes.
An automatic attendance device of filling in labels, includes: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform an automatic attendance check supplementing method.
The above-mentioned specific embodiments are merely specific examples of the present invention, and the scope of the present invention includes, but is not limited to, the specific embodiments described above, any suitable changes or substitutions made by one of ordinary skill in the art, which are consistent with the present invention, of an automatic attendance checking method and apparatus claims, and shall fall within the scope of the present invention.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (2)
1. An automatic attendance checking and supplementing method is characterized by comprising the following steps:
s1, installing an acquisition camera and acquiring data;
the method comprises the steps that an acquisition camera is installed at each entrance and exit of an enterprise, data of personnel images, places and time are acquired, the acquired data are uploaded to a specified database to serve as original data, and the acquired data are provided with a validity period;
s2, data processing;
cleaning original personnel images, places and time data in a database, removing duplication, removing redundant data, dirty data and noise data, and storing the cleaned data into a system database;
s3, extracting features;
extracting features of the cleaned data by using a specific machine learning algorithm, and regularizing the data into 128-bit small data which are stored in a database lookup table;
s4, determining a classification mark;
staff in the enterprise self-transfers the pictures to the system database, extracts the characteristics of the pictures in a mode of step S3, and stores the pictures in the system database to be compared;
s5, designing a classifier model;
taking the image feature data of the label staff as a classification mark and taking the image feature data of the label staff as data to be marked to obtain a training sample required by classification, wherein the training sample is expressed as x1= [ x11, x12, x13, …, x1n ], a corresponding result set y= { L1, L2}, L1 represents that image features can be correlated, and L2 represents that image features cannot be correlated;
the training samples are subjected to classification learning by using a two-classification algorithm, a labeling model Y=f (x) is established, for an unknown sample x, consistent images can be predicted according to the model, and the holding probability is calculated according to the probability, wherein the larger the holding probability is, the higher the consistency of the images is;
s6, optimizing a classifier;
training the classification model for multiple times according to a ten-fold cross-validation mode, and continuously optimizing the classifier model;
s7, generating a approval result;
according to the classification result of the classifier model, if the fitness reaches the standard, the image collected by the camera is considered to be the employee, and the image collection time is before the business-on time specified by the enterprise, the employee is considered to arrive at the post on time, the approval passes, and otherwise the approval does not pass.
2. An automatic attendance device of mending, its characterized in that includes: at least one memory and at least one processor;
the at least one memory for storing a machine readable program;
the at least one processor configured to invoke the machine readable program to perform the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210240073.2A CN114612068B (en) | 2022-03-10 | 2022-03-10 | Automatic attendance checking and supplementing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210240073.2A CN114612068B (en) | 2022-03-10 | 2022-03-10 | Automatic attendance checking and supplementing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114612068A CN114612068A (en) | 2022-06-10 |
| CN114612068B true CN114612068B (en) | 2024-02-02 |
Family
ID=81862403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210240073.2A Active CN114612068B (en) | 2022-03-10 | 2022-03-10 | Automatic attendance checking and supplementing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612068B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839301A (en) * | 2014-03-19 | 2014-06-04 | 山东大学 | Working method of intelligent attendance system based on video tracking and face recognition |
| CN208188897U (en) * | 2017-11-06 | 2018-12-04 | 北京上古视觉科技有限公司 | A kind of Work attendance device and attendance checking system |
| CN109003044A (en) * | 2018-06-29 | 2018-12-14 | 夏烬楚 | A kind of automatic measures and procedures for the examination and approval of attendance and system |
| CN109344745A (en) * | 2018-09-15 | 2019-02-15 | 孙建军 | A kind of facial image recognition method based on monitoring system |
| CN109840962A (en) * | 2018-12-27 | 2019-06-04 | 北京智慧云行科技有限责任公司 | Recognition of face movable attendance checking system and method |
| CN110517365A (en) * | 2019-08-30 | 2019-11-29 | 深圳壹账通智能科技有限公司 | Automation attendance recording method, device, equipment and storage medium based on AI |
| CN113888128A (en) * | 2021-10-08 | 2022-01-04 | 重庆紫光华山智安科技有限公司 | Non-inductive attendance checking method and system based on face recognition |
-
2022
- 2022-03-10 CN CN202210240073.2A patent/CN114612068B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839301A (en) * | 2014-03-19 | 2014-06-04 | 山东大学 | Working method of intelligent attendance system based on video tracking and face recognition |
| CN208188897U (en) * | 2017-11-06 | 2018-12-04 | 北京上古视觉科技有限公司 | A kind of Work attendance device and attendance checking system |
| CN109003044A (en) * | 2018-06-29 | 2018-12-14 | 夏烬楚 | A kind of automatic measures and procedures for the examination and approval of attendance and system |
| CN109344745A (en) * | 2018-09-15 | 2019-02-15 | 孙建军 | A kind of facial image recognition method based on monitoring system |
| CN109840962A (en) * | 2018-12-27 | 2019-06-04 | 北京智慧云行科技有限责任公司 | Recognition of face movable attendance checking system and method |
| CN110517365A (en) * | 2019-08-30 | 2019-11-29 | 深圳壹账通智能科技有限公司 | Automation attendance recording method, device, equipment and storage medium based on AI |
| CN113888128A (en) * | 2021-10-08 | 2022-01-04 | 重庆紫光华山智安科技有限公司 | Non-inductive attendance checking method and system based on face recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114612068A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| CN106998444B (en) | Big data face monitoring system | |
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN110751022A (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
| CN109657624A (en) | Monitoring method, the device and system of target object | |
| CN110688980B (en) | Human body posture classification method based on computer vision | |
| CN111539313A (en) | Examination cheating behavior detection method and system | |
| CN113807240A (en) | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition | |
| CN111784171A (en) | Municipal CIM environmental sanitation work distribution method based on artificial intelligence and image processing | |
| CN110728252A (en) | Face detection method applied to regional personnel motion trail monitoring | |
| Tung et al. | Large-scale object detection of images from network cameras in variable ambient lighting conditions | |
| CN111144749A (en) | Intelligent labeling crowdsourcing platform for power grid images and working method | |
| CN115620471A (en) | Image identification security system based on big data screening | |
| CN110930577A (en) | Method for analyzing unregistered but actually living in personnel based on entrance guard data | |
| CN113269903A (en) | Face recognition class attendance system | |
| CN111897993A (en) | Efficient target person track generation method based on pedestrian re-recognition | |
| CN114529751B (en) | Automatic screening method for intelligent identification sample data of power scene | |
| CN116259101A (en) | Method for inspection hall or classroom discipline inspection tour and inspection robot | |
| CN114612068B (en) | Automatic attendance checking and supplementing method and device | |
| CN117237925B (en) | Intelligent road disease inspection method and system based on computer vision | |
| CN214151721U (en) | Recognition all-in-one machine system based on face algorithm | |
| CN113160012A (en) | Computer online examination invigilation method based on deep learning | |
| Patil et al. | Smart Attendance Management System using IoT | |
| CN118097198B (en) | Automatic dressing compliance management and control system and method based on artificial intelligence | |
| CN113705499B (en) | Scenic spot automatic person searching method |
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 |