CN110992500B - Attendance checking method and device, storage medium and server - Google Patents

Attendance checking method and device, storage medium and server Download PDF

Info

Publication number
CN110992500B
CN110992500B CN201910969206.8A CN201910969206A CN110992500B CN 110992500 B CN110992500 B CN 110992500B CN 201910969206 A CN201910969206 A CN 201910969206A CN 110992500 B CN110992500 B CN 110992500B
Authority
CN
China
Prior art keywords
attendance
picture
information
target picture
staff
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
Application number
CN201910969206.8A
Other languages
Chinese (zh)
Other versions
CN110992500A (en
Inventor
饶琪
董超
陈励
张丹
金子文
裘金龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201910969206.8A priority Critical patent/CN110992500B/en
Publication of CN110992500A publication Critical patent/CN110992500A/en
Application granted granted Critical
Publication of CN110992500B publication Critical patent/CN110992500B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)
  • Time Recorders, Dirve Recorders, Access Control (AREA)

Abstract

The invention relates to the technical fields of image detection, image matching and similarity matching, and provides an attendance checking method, which comprises the following steps: responding to staff card punching operation, and receiving attendance information of staff and attendance pictures associated with the attendance information in a mapping relation; comparing the attendance picture with a target picture, and determining the similarity between the attendance picture and the target picture, wherein the shooting sites of the attendance picture and the target picture are the same; and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information. The attendance field picture shot by the staff is compared with the target picture, so that the staff can be more reliably prevented from checking in by preparing the finger model, the face image and the two-dimensional code artificial hand in advance for others, the attendance cheating is avoided, meanwhile, the attendance picture is associated with the attendance information, the confusion of the attendance result of the system is avoided, and the attendance result of each staff can be obtained rapidly.

Description

Attendance checking method and device, storage medium and server
Technical Field
The invention relates to the technical fields of image detection, image matching and similarity matching, in particular to an attendance checking method and device, a storage medium and a server.
Background
Along with the development of electronic technology, equipment electronics increasingly permeates to the traditional field, and current attendance equipment generally adopts such as manual check-in, punch card, cell-phone check-in etc. and still can adopt face identification technique mode of punching card to carry out the statistics of attendance, and this kind of mode can't be uninteresting carries out the statistics of attendance, influences user experience degree. The electronic work card can not confirm whether the identity information in the electronic work card is consistent with the person actually holding the electronic work card or not because the electronic work card checking equipment can not confirm whether the electronic work card can replace the electronic work card of other people to check work attendance, and cannot prevent the phenomenon of checking work cheating; while the fingerprint identification attendance increases the difficulty of cheating during the attendance of staff, the staff can substitute the attendance through the fingerprint sleeve after copying the fingerprint through the fingerprint sleeve due to the appearance of products such as the fingerprint sleeve, thereby completing the attendance cheating. The card punching mode of the face recognition technology can avoid attendance cheating, if a single face is shot by adopting a camera device to be recognized, the attendance speed can be reduced, and the face images and the attendance information can not be associated easily in the recognition process by collecting the faces of a plurality of staff, so that the recognition result is disordered easily, namely, the image recognition can not be accurately performed, further, the attendance can not be realized rapidly, and the attendance result is inaccurate.
Disclosure of Invention
In order to solve the technical problems, in particular to the problems that the existing attendance method is easy to generate attendance cheating and the attendance speed is low and the attendance result is disordered through face recognition, the following technical scheme is provided:
the attendance checking method provided by the embodiment of the invention comprises the following steps:
responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day;
comparing the attendance picture with a pre-stored target picture, and determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff;
and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information.
Optionally, the comparing the attendance picture with the target picture, determining the similarity between the attendance picture and the target picture includes:
calculating the attendance picture and the target picture through multilayer forward operation of a neural network model, and respectively obtaining multilayer forward operation results of the attendance picture and the target picture;
And comparing the two multi-layer forward operation results to determine the similarity of the attendance picture and the target picture.
Optionally, the comparing the attendance picture with the target picture, determining the similarity between the attendance picture and the target picture includes:
comparing the attendance picture with the target picture, and determining a comparison area corresponding to the attendance picture in the target picture;
cutting the contrast area in the target picture to obtain a sub-target picture;
comparing the sub-target picture with the attendance picture, and determining the similarity between the attendance picture and the sub-target picture.
Optionally, before comparing the attendance picture with the target picture, the method includes:
and acquiring weather information of the current weather, and adjusting the brightness of the target picture according to the weather information.
Optionally, the neural network model is obtained by a method comprising:
acquiring weather information of the current weather, the brightness of the target picture determined based on the weather information, and a similarity sample of comparison between the target picture and the attendance picture;
training a neural network model by using weather information of the current weather, the brightness of the target picture determined based on the weather information and a similarity sample of the target picture compared with the attendance picture to obtain the neural network model for determining the similarity of the attendance picture and the target picture;
The neural network model is used for representing the association relation among weather information of the current weather, the brightness of the target picture determined based on the weather information and the similarity of the target picture and the attendance picture.
Optionally, before receiving the attendance information and the attendance picture with the same employee information, the method further includes:
starting a camera terminal according to a camera starting instruction triggered by staff card punching operation, and acquiring the attendance picture through the camera terminal;
and identifying employee information of the employee for the attendance picture.
The embodiment of the application also provides an attendance checking device, which comprises:
the receiving module is used for responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day;
the comparison module is used for comparing the attendance picture with a pre-stored target picture, determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff;
And the generation module is used for generating effective attendance information according to the attendance picture and the attendance information when the similarity is within a preset threshold value.
Optionally, the comparing module includes:
the calculating unit is used for calculating the attendance picture and the target picture through multilayer forward operation of the neural network model and respectively obtaining multilayer forward operation results of the attendance picture and the target picture;
and the first comparison unit is used for comparing the two multi-layer forward operation results and determining the similarity of the attendance picture and the target picture.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, and the program realizes the attendance checking method according to any technical scheme when being executed by a processor.
The embodiment of the invention also provides a server, which comprises:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the steps of the attendance checking method according to any of the claims.
Compared with the prior art, the invention has the following beneficial effects:
1. the attendance checking method provided by the embodiment of the application comprises the following steps: responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day; comparing the attendance picture with a target picture, and determining the similarity between the attendance picture and a pre-stored target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff; and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information. The attendance picture and the target picture that shoot through staff in this application contrast, and wherein, the place is the same with the target picture shooting to the attendance picture, and then can avoid the staff to carry out the attendance in other people through preparing finger die, face image and two-dimensional code artificial hand in advance more reliably, avoid the attendance cheating, through associatively attendance picture and attendance information simultaneously, avoided the confusion of system attendance result, can obtain the attendance result of each staff fast. Because the target image is compared with the single attendance image, the attendance image identification can be accurately carried out, and in a period of time, the target image is consistent and is processed in advance, so that the time for processing the target image in the comparison process is shortened, the attendance speed is accelerated, and the attendance result accuracy is improved.
2. The embodiment of the application provides an attendance checking method, comparing the attendance checking picture with a target picture, determining the similarity between the attendance checking picture and the target picture, including: comparing the attendance picture with the target picture, and determining a comparison area corresponding to the attendance picture in the target picture; cutting the contrast area in the target picture to obtain a sub-target picture; comparing the sub-target picture with the attendance picture, and determining the similarity between the attendance picture and the sub-target picture. In order to reduce the number of target pictures, more staff can use the same target picture, and the processing amount of the system to the target pictures is reduced. Then a target picture (e.g., a panoramic picture) of a larger scene may be taken, while the attendance pictures that may be taken by different employees are different. Therefore, the attendance picture and the target picture are integrally compared, the similar area of the attendance picture and the target picture is determined through the algorithm, the similar area is cut, the sub-target picture cut from the target picture can be further obtained, and the sub-target picture and the attendance picture are compared, namely, the picture information in the similar area of the attendance picture and the target picture is compared. The contrast of the features is reduced through the process, so that the calculated amount of the neural network model can be reduced, and the attendance rate is improved.
3. The attendance checking method provided by the embodiment of the application, before comparing the attendance checking picture with the target picture, includes: and acquiring weather information of the current weather, and adjusting the brightness of the target picture according to the weather information. Because the picture can lead to the picture luminance insufficient in shooting the in-process, if directly contrast attendance picture and target picture, then probably lead to the contrast incorrect for the staff can not punch the card successfully, can handle target picture earlier and contrast again, confirm the shooting regional luminance that target picture corresponds promptly according to weather information, and according to shooting regional luminance automatically regulated target picture's luminance under this weather, and then make the attendance picture after taking can directly contrast with target picture, reduce the throughput to the attendance picture, and then improved the speed of attendance.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of an implementation of an exemplary embodiment of an attendance method of the present invention;
FIG. 2 is a schematic diagram of an exemplary embodiment of an attendance device according to the present invention;
fig. 3 is a schematic structural diagram of an embodiment of a server according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, but do not preclude the presence or addition of one or more other features, integers, steps, operations.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
It will be appreciated by those skilled in the art that references to "application," "application program," "application software," and similar concepts herein are intended to be equivalent concepts well known to those skilled in the art, and refer to computer software, organically constructed from a series of computer instructions and related data resources, suitable for electronic execution. Unless specifically specified, such naming is not limited by the type, level of programming language, nor by the operating system or platform on which it operates. Of course, such concepts are not limited by any form of terminal.
In one implementation manner, as shown in fig. 1, an attendance checking method provided in an embodiment of the present application includes: s100, S200, S300.
S100: responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day;
s200: comparing the attendance picture with a pre-stored target picture, and determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff;
S300: and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information.
In one embodiment provided by the application, in order to avoid false attendance of staff, an attendance system shoots an attendance scene picture through the staff and compares the picture with a preset target picture to judge whether the staff is truly on site, so that false attendance of the staff is avoided. Therefore, in the technical scheme, the staff information of the staff is stored in the attendance terminal, and the card punching operation mode related to the staff information is used for associating the staff information of the staff with the card punching time, the card punching place and the like of the staff attendance to form the attendance information of the staff when the staff punches a card; or associating the time and place of the staff to form staff attendance information, and identifying the staff information determined based on the operation of punching the card on the attendance information, so that the attendance information comprises the staff information or the identification with the staff information. And receiving the attendance information of the same employee and the attendance picture associated with the attendance information (such as having a mapping relation), wherein the attendance information comprises the card punching time of the employee and the employee information, and further, the employee information can also be the identification of the attendance information. In the process of establishing the attendance information and the attendance pictures, the process is carried out based on the same staff information, for example, after the staff punches a card at a first attendance terminal, the attendance information of the staff is uploaded to an attendance system, after the staff shoots the attendance pictures through a camera device, the attendance pictures shot by the staff are uploaded through a second attendance terminal, wherein the second attendance terminal comprises the staff information, the staff information can be used as the identification of the attendance pictures when the attendance pictures are uploaded, and then the staff information and the identification of the attendance pictures are obtained when the mapping relation between the attendance information and the attendance pictures is established, and when the identification of the attendance pictures and the staff information in the attendance information are the same, the mapping relation between the attendance information and the attendance pictures is established, namely, the attendance information and the attendance pictures are associated in the mapping relation, so that whether the corresponding staff is really on site is conveniently determined. In the embodiment provided by the application, the first attendance terminal and the second attendance terminal can be one terminal or two different terminals, and the steps of uploading the attendance information and the attendance pictures to the attendance system do not have sequence, and the steps of uploading the attendance information to the attendance system can be firstly uploading the attendance pictures to the attendance system or uploading the attendance pictures to the attendance system and uploading the attendance information to the attendance system. In one embodiment, the employee attendance information may be derived from face recognition, fingerprint recognition, two-dimensional code recognition of an employee mobile terminal, and the like. In one embodiment, the picture information of the attendance picture is obtained, wherein the picture information comprises picture shooting time and/or picture shooting geographic position information. In order to ensure timeliness of the attendance picture, when an employee sends the attendance picture through the terminal, shooting time and/or geographical position information of the attendance picture are simultaneously acquired, the shooting time ensures that the attendance time and the picture shooting time are in the same time period, namely, in the effective attendance time period, further, the effective attendance time period does not exceed the effective attendance time of the attendance day. For example, in one embodiment, if the effective attendance time period is 10min, the attendance time in the attendance information is the time of staff card punching, the staff card punching time is A, the shooting time of the attendance picture shot by the staff is the time of day attendance time B, the value of |A-B| is M, when M is less than or equal to 10min, the attendance picture is judged to be effective and can be used for subsequent comparison with a target picture, and when M is more than 10min, the section taking attendance picture is ineffective and cannot be used for subsequent comparison with the target picture. In one embodiment, the time of checking in of the enterprise is elastic work and rest, namely, the time of checking in before a certain time point is considered that the staff is not late, namely, the time of checking in before 10:00 am is considered that the staff is not late (9:59 minutes of checking in is not considered that the staff is late), the effective time period of checking in on the same day is the time before 10:00 am, the time of checking in the picture is considered that the picture is effective in 9:59 minutes of the same day, the picture can be used for the subsequent comparison with the target picture, the time of checking in the picture is considered as 10:00 minutes of the upper day, the picture is invalid, and the picture cannot be used for the subsequent comparison with the target picture; the method has the advantages that the situation that the employee uses the picture shot in advance for attendance checking is avoided, meanwhile, the effective work and rest time of the employee can be enhanced, and the picture shot geographic position information can be used for judging whether the employee is on the attendance checking site or not, wherein the geographic position information comprises longitude and latitude information and the like. It should be noted that, in the embodiment provided by the application, the target picture is prestored in the attendance terminal or the cloud end connected with the attendance terminal, and in the embodiment provided by the application, the target picture is updated every day, or a large number of pictures are prestored in the attendance terminal database/cloud end database, one picture is randomly selected in the database every day as the target picture, the target picture is disposable, the data is deleted after the use is finished, when the target picture is used for many times, the staff is prevented from using the same picture for attendance, the accuracy of attendance is ensured, and the staff is prevented from cheating in attendance.
In an embodiment provided by the application, the attendance picture is compared with the target picture, wherein the method comprises the step of comparing common articles, article backgrounds and the like in the attendance picture and the target picture, and determining the similarity between the two images, so that whether the attendance is effective or not is determined based on a preset similarity threshold value. Correspondingly, in the technical scheme, the similarity of the attendance picture and the target picture is calculated through the multilayer forward operation of the neural network model, and in a specific implementation process, the multilayer forward operation results of the attendance picture and the target picture are respectively obtained through the multilayer forward operation of the neural network model; the factors affecting the comparison of the two pictures in the target picture and the attendance picture are removed through the multi-layer forward operation result, for example, in order to improve the speed of the attendance process, two identical articles in the attendance picture and the target picture are screened out through a neural network, and then the similarity of the two pictures is determined by comparing the position relationship between the two articles, the line proportion and the like. Wherein, two objects screened from the same two objects in the attendance picture and the target picture are multilayer forward operation results.
In combination with the foregoing process, in the present application, after the similarity between the attendance picture and the target picture is determined through the foregoing process, when the similarity is within the preset threshold, it is stated that the employee is on the attendance scene, and effective attendance information is generated according to the attendance picture and the attendance information, for example, when the time of punching a card and the employee information in the attendance information on the corresponding date are recorded in the database, further, the attendance picture and the attendance information can be recorded simultaneously in association relation, so that the inquiry of the attendance data is convenient to be performed later. In the technical scheme, the mobile terminal of staff can be used for shooting the attendance picture, the target picture can be an existing camera device, so that the economic cost of enterprises is reduced, after the camera device shoots the target picture, the picture can be uploaded to the background, the similarity of the target picture and the attendance picture is calculated in the background, and the maintenance cost of the attendance equipment can be reduced due to the calculation in the background in the calculation process, and meanwhile, the updating, optimization and calculation of the attendance related algorithm by the background staff are facilitated.
Optionally, the comparing the attendance picture with the target picture, determining the similarity between the attendance picture and the target picture includes:
Calculating the attendance picture and the target picture through multilayer forward operation of a neural network model, and respectively obtaining multilayer forward operation results of the attendance picture and the target picture;
and comparing the two multi-layer forward operation results to determine the similarity of the attendance picture and the target picture.
Through an exemplary multi-layer forward operation process of the attendance pictures, gray processing is carried out on the attendance pictures to obtain first attendance gray images, m1 gray values of each pixel point in the first attendance gray images are obtained, m2 continuous gray values with the minimum gray value in the m1 gray values are extracted, m2 pixel points are removed from the first attendance gray images to obtain second attendance gray images, the second attendance gray images are recovered to obtain attendance pictures for comparison, R, G, B values (red color values, green color values and blue color values) of each pixel point in the attendance pictures for comparison are extracted, R, G, B values of each pixel point in the attendance pictures for comparison form an input data block [ CI1] [ H1] [ w1], the input data block [ CI1] [ H1] [ w1] is input into a neural network model as input data, and multi-layer convolution operation is carried out to obtain forward operation results. The above x2 is larger than a first set threshold (generally, the value is larger, for example, 1000, 2000, etc.). Wherein CI1 is the depth value of the input data block, H1 is the height value of the input data block, w1 is the width value of the input data block, m1, CI1, H1, w1 are integers greater than or equal to 10, and m2 is an integer greater than or equal to 103.
Further, in one embodiment, the method for calculating the similarity may further be performed by, for example: the local feature correlation algorithm SIFT, SURF algorithm and the like are widely applied to target detection, identification and matching positioning, and the two algorithms are used for constructing a Gaussian scale space by using a pyramid strategy.
The KAZE algorithm employs nonlinear diffusion filtering to improve repeatability and uniqueness over SIFT and SURF algorithms. However, the KAZE algorithm has the disadvantage of being computationally intensive, solving the nonlinear diffusion equation through the strategy of AOS numerical approximation, and although the AOS solution is stable and parallelizable, a large linear equation set needs to be solved, and real-time requirements are difficult to meet at the mobile end. Two points are mainly improved on the KAZE algorithm: 1. the advantage of nonlinear diffusion filtering is utilized to obtain the characteristic with low calculation requirement, and a fast display diffusion mathematical framework FED is introduced to rapidly solve the partial differential equation. The FED is used to build the scale space faster than other nonlinear modes are currently being built, and is more accurate than AOS. 2. An efficient improved local differential binary descriptor (M-LDB) is introduced, compared with the original LDB, the robustness of rotation and scale invariance is increased, and the uniqueness is increased by combining the scale space gradient information constructed by the FED. Compared with SIFT and SURF algorithms, AKAZE algorithm is faster, and compared with ORB and BRISK algorithm, repeatability and robustness are improved greatly. The corresponding features in the attendance picture and the target picture are extracted through the method, and compared, the similarity of the two pictures is determined, so that the robustness and the repeatability in the feature extraction process of the comparison picture are improved, and the improvement and the restoration of the algorithm for feature extraction for many times are avoided.
In combination with the foregoing description, in one embodiment, the feature information of the object in the target picture may be further processed in advance based on the foregoing algorithm, for example, the object in the target picture is identified according to the feature information, and the feature information and the object are stored in a mapping relationship, so that in a process of comparing the similarity between the target picture and the attendance picture, only the feature information of the object in the attendance picture may be extracted and identified, and based on the identification result, the feature information of the corresponding object in the mapping relationship is queried, and the feature information of the object and the feature information are compared and calculated to determine the similarity of the object and the attendance picture. In the process, the processing process of the characteristic information of the target picture in the attendance checking process is reduced, so that the attendance checking speed is accelerated, and the calculated amount of attendance checking in the attendance checking process is reduced. And by means of inquiry, the characteristic information for comparison can be quickly obtained, and the calculation rate of attendance is further improved.
Optionally, the comparing the attendance picture with the target picture, determining the similarity between the attendance picture and the target picture includes:
comparing the attendance picture with the target picture, and determining a comparison area corresponding to the attendance picture in the target picture;
Cutting the contrast area in the target picture to obtain a sub-target picture;
comparing the sub-target picture with the attendance picture, and determining the similarity between the attendance picture and the sub-target picture.
In one embodiment, the target picture may be a panoramic picture, and the attendance pictures that may be taken by different employees are different, so that the attendance pictures and the target picture are compared integrally, the similar area of the attendance pictures and the target picture is determined by the algorithm, the similar area is cut, the sub-target picture cut from the target picture can be obtained, and the sub-target picture and the attendance pictures are compared, namely, the picture information in the similar area of the attendance pictures and the target picture is compared. The contrast of the features is reduced through the process, so that the calculated amount of the neural network model can be reduced, and the attendance rate is improved.
Optionally, before comparing the attendance picture with the target picture, the method includes:
and acquiring weather information of the current weather, and adjusting the brightness of the target picture according to the weather information.
Because the picture can lead to the picture luminance insufficient in shooting the in-process, if directly contrast attendance picture and target picture, then probably lead to the contrast incorrect for the staff can not punch the card successfully, can handle target picture earlier and contrast again, correspondingly, if when weather is bad, obtain weather information, confirm the regional luminance of shooting that target picture corresponds according to weather information, adjust the luminance of target picture according to regional luminance of shooting, and then make the attendance picture after taking can directly contrast with target picture, reduce the throughput to the attendance picture, and then improved the speed of attendance. Optionally, in an embodiment provided in the present application, weather information of current weather may also be acquired, and a target picture corresponding to the weather information may be retrieved from a database. On the basis, different target pictures are selected through different weather, whether the target pictures are cut based on the attendance pictures or not is determined according to the target picture scenes (namely, the scene size of the target picture is judged), so that sub-target pictures are obtained, the similarity calculated through the model is more accurate, and the attendance accuracy is improved.
Optionally, the neural network model is obtained by a method comprising:
acquiring weather information of the current weather, the brightness of the target picture determined based on the weather information, and a similarity sample of comparison between the target picture and the attendance picture;
training a neural network model by using weather information of the current weather, the brightness of the target picture determined based on the weather information and a similarity sample of the target picture compared with the attendance picture to obtain the neural network model for determining the similarity of the attendance picture and the target picture;
the neural network model is used for representing the association relation among weather information of the current weather, the brightness of the target picture determined based on the weather information and the similarity of the target picture and the attendance picture.
And training a neural network model by taking weather information of the current weather, the brightness of the target picture determined based on the weather information and the similarity of the target picture compared with the attendance picture as samples, so as to obtain the neural network model for determining the similarity of the attendance picture and the target picture.
In order to more accurately adjust the brightness of the target picture based on weather information, the weather information when each employee is opened, the brightness of the target picture adjusted by the weather information and the similarity of the target picture compared with the attendance picture are taken as samples, a large amount of sample data can be collected to train the neural network model, the calculation accuracy of the neural network model can be adjusted based on the feedback result, the calculation error of the neural network model is reduced, and the accuracy of the attendance result is improved.
Optionally, before receiving the attendance information and the attendance picture with the same employee information, the method further includes:
starting a camera terminal according to a camera starting instruction triggered by staff card punching operation, and acquiring the attendance picture through the camera terminal;
and identifying employee information of the employee for the attendance picture.
In one embodiment, when the staff card-punching operation is completed, the starting instruction of opening the camera by the staff handheld terminal is triggered, so that the staff operation process is reduced, the staff can immediately shoot the attendance picture after opening, or the attendance picture is automatically acquired through the camera terminal, correspondingly, in the process of automatically acquiring the picture, the camera terminal detects whether the current camera is blocked, namely, the brightness value of a shooting scene of the camera terminal is detected, when the brightness value is lower than a preset threshold value, the camera terminal is closed, if the brightness value is within the preset shooting range, the image can be shot, the attendance picture is acquired, and because the camera terminal automatically acquires the attendance picture, after the picture is acquired, the picture is also required to be screened or a plurality of acquired pictures are corrected, the picture is synthesized into one picture, so that an object in the picture can be identified, and the attendance picture can be compared with a target picture, and then the information of the staff is correlated, so that the attendance information can be comprehensively determined, and the specific correlation process is not disclosed herein. Correspondingly, in the process of collecting the completion picture and uploading the completion picture to the attendance system, the uploaded attendance pictures are marked with employee information, wherein the employee information is obtained from a terminal of the employee uploading attendance picture, the attendance terminal can be an application program installed in the mobile terminal, the application program comprises the employee information, when the employee logs in the application program to upload the attendance picture, the employee information logged in the application program is used as the mark of the attendance picture, the attendance picture and the attendance information are conveniently associated based on the employee information, and after a plurality of pictures are combined into one attendance picture, the employee information on the attendance picture mark after the synthesis is also needed. After the attendance picture is associated with the staff attendance information, after the staff attendance is successfully checked according to the attendance picture, the attendance result of the staff can be quickly determined, and further the accuracy of the staff attendance can be improved, so that when the picture is not associated with the staff attendance information, the system needs to search the staff information again, and the recognition result of the attendance picture is determined as the attendance result of other staff, so that the situation of disordered attendance result is caused, and the recognition result cannot reflect the attendance result of the staff.
In one embodiment, after the similarity of the attendance picture and the target picture is obtained by comparison, when the similarity is determined to be not within the preset similarity threshold, reminding information is sent to the staff, so that the rights and interests of the staff on the attendance site can be ensured, and meanwhile false attendance of the staff not on the attendance site can be avoided. In addition, when the similarity is not within a preset threshold, reminding information is sent to staff so that the staff on the attendance site can check again, or staff not on the attendance site can report timely or ask for help to report to corresponding staff, and the like.
In one embodiment, deleting the target picture in a first preset time period, and taking a new picture as a target picture; in one embodiment, the target picture is randomly acquired from a database within a second preset time period. In combination with the foregoing description, in order to avoid employee false attendance, attendance pictures with the target pictures within the preset similarity are prepared in advance, the target pictures are updated every day, or a large number of pictures can be shot in advance in a pre-stored library, the system randomly selects one picture in the library every day as the target picture, the target picture is used once, and data is deleted after the use is completed.
In one embodiment, the generating the effective attendance information according to the attendance picture and the attendance information includes: and acquiring the attendance time in the attendance information and the time for uploading or shooting the attendance picture with the attendance picture, judging whether the attendance time and the time for uploading or shooting the attendance picture are within a preset time period, and generating effective attendance information according to the attendance picture and the attendance information when the attendance time and the time for shooting the attendance picture are within the preset time period. And acquiring/shooting a target picture according to the room number/room number information. The staff can conveniently shoot the attendance pictures, the attendance efficiency is improved, and the work time of the staff is prevented from being delayed by attendance. In order to facilitate the staff to find the position where the target picture is shot, the position information corresponding to the target picture is sent to the staff. In order to avoid staff attendance cheating, the attendance pictures uploaded by staff are compared to determine the similarity between the attendance pictures, and when the similarity of the two attendance pictures is within the range of the preset attendance cheating similarity (such as 90% -100%), reminding information is sent to the staff. The calculation of the similarity of the two attendance pictures mainly comprises the methods of shooting angles of the attendance pictures, gray information (pixel gray scale ratio), binary stream and the like.
The embodiment of the invention also provides an attendance checking device, in one implementation manner, as shown in fig. 2, the attendance checking device comprises: receiving module 100, comparing module 200, generating module 300:
the receiving module 100 is configured to receive, in response to an employee card punching operation, attendance information and an attendance picture with the same employee information, establish a mapping relationship between the attendance information and the attendance picture according to the same employee information, and enable the shooting time of the attendance picture not to exceed an effective attendance time period of an attendance current day;
the comparison module 200 is configured to compare the attendance picture with a pre-stored target picture, determine a similarity between the attendance picture and the target picture, and make the target picture of the employee be the same as a shooting place of the attendance picture shot by the employee;
a generating module 300, configured to generate effective attendance information according to the attendance picture and the attendance information when the similarity is within a preset threshold
Further, as shown in fig. 2, the attendance checking device provided in the embodiment of the present invention further includes: a calculating unit 210, configured to calculate the attendance picture and the target picture through a multi-layer forward operation of the neural network model, and obtain multi-layer forward operation results of the attendance picture and the target picture respectively; the first comparing unit 220 is configured to compare the two multi-layer forward operation results, and determine the similarity between the attendance picture and the target picture. A comparison area determining unit 230, configured to compare the attendance picture with the target picture, and determine a comparison area corresponding to the attendance picture in the target picture; a cutting unit 240, configured to cut the contrast area in the target picture to obtain a sub-target picture; and a second comparing unit 250, configured to compare the sub-target picture with the attendance picture, and determine the similarity between the attendance picture and the sub-target picture. The weather information acquisition module 201 is configured to acquire weather information of a current weather, and adjust brightness of the target picture according to the weather information. The sample obtaining module 301 is configured to obtain weather information of the current weather, the target picture brightness determined based on the weather information, and a similarity sample of comparison between the target picture and the attendance picture; the training module 302 is configured to train a neural network model on weather information of the current weather, the brightness of the target picture determined based on the weather information, and a similarity sample of the target picture compared with the attendance picture, to obtain a neural network model for determining similarity of the attendance picture and the target picture; the neural network model is used for representing the association relation among weather information of the current weather, the brightness of the target picture determined based on the weather information and the similarity of the target picture and the attendance picture. The starting module 101 is used for starting a camera shooting terminal according to a camera shooting starting instruction triggered by staff card punching operation, and collecting the attendance picture through the camera shooting terminal; and the identification module 102 is used for identifying employee information of the employee for the attendance picture.
The attendance checking device provided by the embodiment of the invention can realize the embodiment of the attendance checking method, and specific function realization is shown in the description of the embodiment of the method, and is not repeated here.
The embodiment of the invention provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and when the program is executed by a processor, the attendance checking method according to any one of the technical schemes is realized. The computer readable storage medium includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks, ROMs (Read-Only memories), RAMs (Random AcceSS Memory, random access memories), EPROMs (EraSable Programmable Read-Only memories), EEPROMs (Electrically EraSable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards. That is, a storage device includes any medium that stores or transmits information in a form readable by a device (e.g., computer, cell phone), and may be read-only memory, magnetic or optical disk, etc.
The embodiment of the invention can realize the embodiment of the attendance checking method, and the attendance checking field picture shot by staff is compared with the target picture in the method, so that the staff can be more reliably prevented from checking the attendance of the staff by preparing a finger model, a face image and a two-dimensional code artificial hand in advance, the attendance checking cheating is avoided, and meanwhile, the attendance checking picture is associated with the attendance checking information, the confusion of the system attendance checking result is avoided, and the attendance checking result of each staff can be rapidly obtained; the attendance checking method provided by the embodiment of the application comprises the following steps: responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day; comparing the attendance picture with a pre-stored target picture, determining the similarity between the attendance picture and the target picture, and determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff; and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information. In one embodiment provided by the application, in order to avoid false attendance of staff, an attendance scene picture is shot by the staff, and the picture is compared with a preset target picture to judge whether the staff is really on site, so that false attendance of the staff is avoided. Therefore, in the technical scheme, when the staff is subjected to card punching, the attendance information of the staff and the attendance picture associated with the attendance information are received, the attendance information comprises personal information of the staff and card punching time of the staff, and the attendance information is associated with the attendance picture so as to be convenient for determining whether the corresponding staff is really on the attendance site. In one embodiment, the employee attendance information may be derived from face recognition, fingerprint recognition, two-dimensional code recognition of an employee mobile terminal, and the like. In one embodiment, the picture information of the attendance picture is obtained, wherein the picture information comprises picture shooting time and/or picture shooting geographic position information. In order to ensure timeliness of the attendance picture, when an employee sends the attendance picture through the terminal, shooting time and/or geographical position information of the attendance picture are simultaneously acquired, the shooting time ensures that the attendance time and the picture shooting time are in the same time period, the situation that the employee uses the picture shot in advance for attendance is avoided, and the picture shooting geographical position information can also be used for judging whether the employee is on the attendance site or not, wherein the geographical position information comprises longitude and latitude information and the like. In an embodiment provided by the application, the attendance picture is compared with the target picture, wherein the method comprises the step of comparing common articles, article backgrounds and the like in the attendance picture and the target picture, and determining the similarity between the two images, so that whether the attendance is effective or not is determined based on a preset similarity threshold value. Correspondingly, in the technical scheme, the similarity of the attendance picture and the target picture is calculated through the multilayer forward operation of the neural network model, and in a specific implementation process, the multilayer forward operation results of the attendance picture and the target picture are respectively obtained through the multilayer forward operation of the neural network model; the factors affecting the comparison of the two pictures in the target picture and the attendance picture are removed through the multi-layer forward operation result, for example, in order to improve the speed of the attendance process, two identical articles in the attendance picture and the target picture are screened out through a neural network, and then the similarity of the two pictures is determined by comparing the position relationship between the two articles, the line proportion and the like. Wherein, two objects screened from the same two objects in the attendance picture and the target picture are multilayer forward operation results. In combination with the foregoing process, in the present application, after the similarity between the attendance picture and the target picture is determined through the foregoing process, when the similarity is within the preset threshold, it is stated that the employee is on the attendance scene, and effective attendance information is generated according to the attendance picture and the attendance information, for example, when the time of punching a card and the employee information in the attendance information on the corresponding date are recorded in the database, further, the attendance picture and the attendance information can be recorded simultaneously in association relation, so that the inquiry of the attendance data is convenient to be performed later. In the technical scheme, the mobile terminal of staff can be used for shooting the attendance picture, the target picture can be an existing camera device, so that the economic cost of enterprises is reduced, after the camera device shoots the target picture, the picture can be uploaded to the background, the similarity of the target picture and the attendance picture is calculated in the background, and the maintenance cost of the attendance equipment can be reduced due to the calculation in the background in the calculation process, and meanwhile, the updating, optimization and calculation of the attendance related algorithm by the background staff are facilitated.
In addition, in another embodiment, the present invention further provides a server, as shown in fig. 3, where the server processor 503, the memory 505, the input unit 507, the display unit 509, and other devices. Those skilled in the art will appreciate that the structural elements shown in fig. 3 do not constitute a limitation on all servers, and may include more or fewer components than shown, or may combine certain components. The memory 505 may be used to store an application 501 and various functional modules, and the processor 503 runs the application 501 stored in the memory 505 to perform various functional applications and data processing of the device. The memory 505 may be an internal memory or an external memory, or include both internal and external memories. The internal memory may include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, floppy disk, ZIP disk, U-disk, tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The memory 505 of the present disclosure is by way of example only and not by way of limitation.
The input unit 507 is used for receiving input of signals, and personal information (employee information) and related attendance information input by employees. The input unit 507 may include a touch panel and other input devices. The touch panel can collect touch operations on or near the client (such as operations of the client on or near the touch panel using any suitable object or accessory such as a finger, a stylus, etc.), and drive the corresponding connection device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, mouse, joystick, etc. The display unit 509 may be used to display information input by a client or information provided to the client and various menus of the computer device. The display unit 509 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 503 is the control center of the computer device, connecting the various parts of the overall computer using various interfaces and lines, performing various functions and processing data by running or executing software programs and/or modules stored in the memory 503, and invoking data stored in the memory. The one or more processors 503 shown in fig. 3 are capable of performing, implementing, the functions of the receiving module 100, the comparing module 200, the generating module 300, the calculating unit 210, the first comparing unit 220, the comparing area determining unit 230, the cutting unit 240, the second comparing unit 250, the weather information acquiring module 201, the sample acquiring module 301, the training module 302, the starting module 101, and the identifying module 102 shown in fig. 2.
In one embodiment, the server includes one or more processors 503 and one or more memories 505, one or more applications 501, wherein the one or more applications 501 are stored in the memory 505 and configured to be executed by the one or more processors 503, and the one or more applications 301 are configured to perform the attendance method described in the above embodiments.
The embodiment of the invention can realize the embodiment of the attendance checking method, and the attendance checking field picture shot by the staff is compared with the target picture in the embodiment of the invention, so that the staff can be more reliably prevented from checking the attendance of other people by preparing a finger model, a face image and a two-dimension code artificial hand in advance, the attendance checking cheating is avoided, and meanwhile, the attendance checking picture is associated with the attendance checking information, the confusion of the attendance checking result of the system is avoided, and the attendance checking result of each staff can be obtained rapidly; the attendance checking method provided by the embodiment of the application comprises the following steps: responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day; comparing the attendance picture with a pre-stored target picture, and determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff; and when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information. In one embodiment provided by the application, in order to avoid false attendance of staff, an attendance scene picture is shot by the staff, and the picture is compared with a preset target picture to judge whether the staff is really on site, so that false attendance of the staff is avoided. Therefore, in the technical scheme, when the staff is subjected to card punching, the attendance information of the staff and the attendance picture associated with the attendance information are received, the attendance information comprises the staff information and the card punching time of the staff, and the attendance information is associated with the attendance picture, so that whether the corresponding staff is really on the attendance field or not is conveniently determined. In one embodiment, the employee attendance information may be derived from face recognition, fingerprint recognition, two-dimensional code recognition of an employee mobile terminal, and the like. In one embodiment, the picture information of the attendance picture is obtained, wherein the picture information comprises picture shooting time and/or picture shooting geographic position information. In order to ensure timeliness of the attendance picture, when an employee sends the attendance picture through the terminal, shooting time and/or geographical position information of the attendance picture are simultaneously acquired, the shooting time ensures that the attendance time and the picture shooting time are in the same time period, the situation that the employee uses the picture shot in advance for attendance is avoided, and the picture shooting geographical position information can also be used for judging whether the employee is on the attendance site or not, wherein the geographical position information comprises longitude and latitude information and the like. In an embodiment provided by the application, the attendance picture is compared with the target picture, wherein the method comprises the step of comparing common articles, article backgrounds and the like in the attendance picture and the target picture, and determining the similarity between the two images, so that whether the attendance is effective or not is determined based on a preset similarity threshold value. Correspondingly, in the technical scheme, the similarity of the attendance picture and the target picture is calculated through the multilayer forward operation of the neural network model, and in a specific implementation process, the multilayer forward operation results of the attendance picture and the target picture are respectively obtained through the multilayer forward operation of the neural network model; the factors affecting the comparison of the two pictures in the target picture and the attendance picture are removed through the multi-layer forward operation result, for example, in order to improve the speed of the attendance process, two identical articles in the attendance picture and the target picture are screened out through a neural network, and then the similarity of the two pictures is determined by comparing the position relationship between the two articles, the line proportion and the like. Wherein, two objects screened from the same two objects in the attendance picture and the target picture are multilayer forward operation results. In combination with the foregoing process, in the present application, after the similarity between the attendance picture and the target picture is determined through the foregoing process, when the similarity is within the preset threshold, it is described that the employee is on the attendance site, and effective attendance information is generated according to the attendance picture and the attendance information. For example, when the time of punching the card and the employee information in the attendance information of the corresponding date are recorded in the database, further, the attendance picture and the attendance information can be recorded simultaneously in an association relationship, so that the inquiry of the attendance data can be conveniently carried out at a later stage. In the technical scheme, the mobile terminal of staff can be used for shooting the attendance picture, the target picture can be an existing camera device, so that the economic cost of enterprises is reduced, after the camera device shoots the target picture, the picture can be uploaded to the background, the similarity of the target picture and the attendance picture is calculated in the background, and the maintenance cost of the attendance equipment can be reduced due to the calculation in the background in the calculation process, and meanwhile, the updating, optimization and calculation of the attendance related algorithm by the background staff are facilitated.
The server provided by the embodiment of the present invention can implement the embodiment of the attendance checking method provided above, and specific function implementation is described in the method embodiment and is not repeated herein.
The foregoing is only a partial embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.

Claims (10)

1. An attendance method, comprising:
responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, and establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day;
comparing the attendance picture with a pre-stored target picture, and determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff;
when the similarity is within a preset threshold, generating effective attendance information according to the attendance picture and the attendance information;
Before comparing the attendance picture with the target picture, the method comprises the following steps:
and acquiring weather information of the current weather, and calling the target pictures corresponding to the weather information from a database, wherein a plurality of target pictures corresponding to different weather respectively are stored in the database.
2. The method of checking-in according to claim 1, wherein comparing the checking-in picture with a target picture, determining the similarity between the checking-in picture and the target picture, comprises:
calculating the attendance picture and the target picture through multilayer forward operation of a neural network model, and respectively obtaining multilayer forward operation results of the attendance picture and the target picture;
and comparing the two multi-layer forward operation results to determine the similarity of the attendance picture and the target picture.
3. The method of checking-in according to claim 1, wherein comparing the checking-in picture with a target picture, determining the similarity between the checking-in picture and the target picture, comprises:
comparing the attendance picture with the target picture, and determining a comparison area corresponding to the attendance picture in the target picture;
Cutting the contrast area in the target picture to obtain a sub-target picture;
comparing the sub-target picture with the attendance picture, and determining the similarity between the attendance picture and the sub-target picture.
4. The method of checking-in according to claim 2, characterized in that before comparing the checking-in picture with a target picture, it comprises:
and acquiring weather information of the current weather, and adjusting the brightness of the target picture according to the weather information.
5. The attendance method of claim 4, wherein the neural network model is obtained by a method comprising:
acquiring weather information of the current weather, the brightness of the target picture determined based on the weather information, and a similarity sample of comparison between the target picture and the attendance picture;
training a neural network model by using weather information of the current weather, the brightness of the target picture determined based on the weather information and a similarity sample of the target picture compared with the attendance picture to obtain the neural network model for determining the similarity of the attendance picture and the target picture;
the neural network model is used for representing the association relation among weather information of the current weather, the brightness of the target picture determined based on the weather information and the similarity of the target picture and the attendance picture.
6. The method according to any one of claims 1 to 4, further comprising, before receiving the attendance information and the attendance picture with the same employee information:
starting a camera terminal according to a camera starting instruction triggered by staff card punching operation, and acquiring the attendance picture through the camera terminal;
and identifying employee information of the employee for the attendance picture.
7. An attendance device, comprising:
the receiving module is used for responding to staff card punching operation, receiving attendance information and attendance pictures with the same staff information, establishing a mapping relation between the attendance information and the attendance pictures according to the same staff information, wherein the shooting time of the attendance pictures does not exceed the effective attendance time period of the attendance day;
the comparison module is used for comparing the attendance picture with a pre-stored target picture, determining the similarity between the attendance picture and the target picture, wherein the target picture of the staff is the same as the shooting place of the attendance picture shot by the staff;
the generation module is used for generating effective attendance information according to the attendance picture and the attendance information when the similarity is within a preset threshold value;
Before comparing the attendance picture with the target picture, the method comprises the following steps:
and acquiring weather information of the current weather, and calling the target pictures corresponding to the weather information from a database, wherein a plurality of target pictures corresponding to different weather respectively are stored in the database.
8. The attendance device of claim 7, wherein the comparison module comprises:
the calculating unit is used for calculating the attendance picture and the target picture through multilayer forward operation of the neural network model and respectively obtaining multilayer forward operation results of the attendance picture and the target picture;
and the first comparison unit is used for comparing the two multi-layer forward operation results and determining the similarity of the attendance picture and the target picture.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the attendance method of any one of claims 1 to 6.
10. A server, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the steps of the attendance method of any one of claims 1 to 6.
CN201910969206.8A 2019-10-12 2019-10-12 Attendance checking method and device, storage medium and server Active CN110992500B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910969206.8A CN110992500B (en) 2019-10-12 2019-10-12 Attendance checking method and device, storage medium and server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910969206.8A CN110992500B (en) 2019-10-12 2019-10-12 Attendance checking method and device, storage medium and server

Publications (2)

Publication Number Publication Date
CN110992500A CN110992500A (en) 2020-04-10
CN110992500B true CN110992500B (en) 2023-04-25

Family

ID=70081890

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910969206.8A Active CN110992500B (en) 2019-10-12 2019-10-12 Attendance checking method and device, storage medium and server

Country Status (1)

Country Link
CN (1) CN110992500B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113920606A (en) * 2021-10-09 2022-01-11 中国银行股份有限公司 Attendance card punching method, background server and employee mobile terminal
CN115514893B (en) * 2022-09-20 2023-10-27 北京有竹居网络技术有限公司 Image uploading method, image uploading device, readable storage medium and electronic equipment
CN116452878B (en) * 2023-04-20 2024-02-02 广东工业大学 Attendance checking method and system based on deep learning algorithm and binocular vision

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0535996A (en) * 1991-07-31 1993-02-12 Sumitomo Electric Ind Ltd Vehicle detecting system
CN1254145A (en) * 1999-11-12 2000-05-24 成都银晨网讯科技有限公司 Face image identification entrance guard and work attendance checking system
CN108171224A (en) * 2018-03-07 2018-06-15 北京上古视觉科技有限公司 A kind of electron album and attendance recorder
CN109872406A (en) * 2019-01-23 2019-06-11 北京影谱科技股份有限公司 A kind of gradual judgement update method, device and face punch card system
CN208969738U (en) * 2018-11-23 2019-06-11 广东缀术智能监测科技有限公司 Hand-held tour terminal for safety monitoring

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105678232B (en) * 2015-12-30 2019-01-22 中通服公众信息产业股份有限公司 A kind of face picture feature extraction and control methods based on deep learning
CN106780804A (en) * 2016-11-23 2017-05-31 南京军理科技股份有限公司 Register method, apparatus and system
CN107170068B (en) * 2017-05-18 2019-08-30 中冶华天工程技术有限公司 Movable attendance checking method based on scene and image recognition
CN107767476A (en) * 2017-08-09 2018-03-06 安徽斯百德信息技术有限公司 A kind of quick method of registering based on mobile Internet with antifraud measure
CN108765352B (en) * 2018-06-01 2021-07-16 联想(北京)有限公司 Image processing method and electronic device
CN110163816B (en) * 2019-04-24 2021-08-31 Oppo广东移动通信有限公司 Image information processing method and device, storage medium and electronic equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0535996A (en) * 1991-07-31 1993-02-12 Sumitomo Electric Ind Ltd Vehicle detecting system
CN1254145A (en) * 1999-11-12 2000-05-24 成都银晨网讯科技有限公司 Face image identification entrance guard and work attendance checking system
CN108171224A (en) * 2018-03-07 2018-06-15 北京上古视觉科技有限公司 A kind of electron album and attendance recorder
CN208969738U (en) * 2018-11-23 2019-06-11 广东缀术智能监测科技有限公司 Hand-held tour terminal for safety monitoring
CN109872406A (en) * 2019-01-23 2019-06-11 北京影谱科技股份有限公司 A kind of gradual judgement update method, device and face punch card system

Also Published As

Publication number Publication date
CN110992500A (en) 2020-04-10

Similar Documents

Publication Publication Date Title
CN110992500B (en) Attendance checking method and device, storage medium and server
CN109076198A (en) Based on video to image tracing sheltering detection system, process and equipment
CN113065558A (en) Lightweight small target detection method combined with attention mechanism
CN109934847B (en) Method and device for estimating posture of weak texture three-dimensional object
CN110210276A (en) A kind of motion track acquisition methods and its equipment, storage medium, terminal
CN107977633A (en) Age recognition methods, device and the storage medium of facial image
CN106844492B (en) A kind of method of recognition of face, client, server and system
CN107622252B (en) Information generation method and device
CN109829381A (en) A kind of dog only identifies management method, device, system and storage medium
CN105426827A (en) Living body verification method, device and system
CN104063686B (en) Crop leaf diseases image interactive diagnostic system and method
CN109740662A (en) Image object detection method based on YOLO frame
CN112651333B (en) Silence living body detection method, silence living body detection device, terminal equipment and storage medium
CN109635634A (en) A kind of pedestrian based on stochastic linear interpolation identifies data enhancement methods again
CN111104813A (en) Two-dimensional code image key point detection method and device, electronic equipment and storage medium
CN103428537A (en) Video processing method and video processing device
WO2019090901A1 (en) Image display selection method and apparatus, intelligent terminal and storage medium
CN112561973A (en) Method and device for training image registration model and electronic equipment
CN111263955A (en) Method and device for determining movement track of target object
CN116229528A (en) Living body palm vein detection method, device, equipment and storage medium
CN107479715A (en) The method and apparatus that virtual reality interaction is realized using gesture control
CN112528978B (en) Face key point detection method and device, electronic equipment and storage medium
CN112700568B (en) Identity authentication method, equipment and computer readable storage medium
CN117115595A (en) Training method and device of attitude estimation model, electronic equipment and storage medium
CN115797451A (en) Acupuncture point identification method, device and equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant