CN114758208A

CN114758208A - Attendance checking equipment adjusting method and device, electronic equipment and storage medium

Info

Publication number: CN114758208A
Application number: CN202210663797.8A
Authority: CN
Inventors: 莫少锋; 段炼; 周波; 苗瑞; 邹小刚; 陈永刚
Original assignee: Shenzhen HQVT Technology Co Ltd
Current assignee: Shenzhen Haiqing Zhiyuan Technology Co ltd
Priority date: 2022-06-14
Filing date: 2022-06-14
Publication date: 2022-07-15
Anticipated expiration: 2042-06-14
Also published as: CN114758208B

Abstract

The invention relates to the technical field of attendance management, and provides an attendance device adjusting method, an attendance device adjusting device, electronic equipment and a storage medium, wherein the method is used for adjusting a plurality of attendance devices in a target scene, and the attendance devices carry out face recognition on users by continuously shooting at least one frame image of the users; the method comprises the following steps: for each attendance device in the attendance devices, carrying out face recognition on a plurality of users through the attendance device, and determining an image set shot in the process from each user entering a stable recognition state to successful recognition; determining target attendance equipment in the plurality of attendance equipment according to the corresponding acquaintance degree of the image set of each attendance equipment; and adjusting the installation modes of other attendance equipment in the plurality of attendance equipment according to the position information of the face detection frame corresponding to the target attendance equipment. Therefore, the attendance checking equipment can be located at a proper identification position, the face evaluation identification time is reduced, and the identification accuracy is improved.

Description

Attendance checking equipment adjusting method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of attendance management technologies, and in particular, to a method and an apparatus for adjusting attendance devices, an electronic device, and a storage medium.

Background

With the development of the artificial intelligence industry, the attendance modes become more diversified, and the face attendance technology is distinguished by the characteristics of high card punching speed, intelligent mode and the like, wherein a face access attendance machine is common attendance equipment, the card punching time is recorded after the face of a person is identified, the attendance record of the person can be calculated together with a schedule, and the improvement of the first image hit rate is one of comprehensive weighing factors of the access attendance machine.

In the prior art, when a face access control attendance machine is installed, in order to improve the acquisition accuracy of the face access control attendance machine, the installation angle, height and other requirements are generally set by equipment manufacturers, conditions such as backlight and backlight are kept away in scene installation, and approximate installation is carried out by depending on the experience of a constructor, so that equipment can normally work.

However, in the actual application process, the conditions of each scene are different, the equipment cannot achieve a definite installation standard in the installation process, the face evaluation and identification time of the access control attendance machine installed based on the method is long, and the identification accuracy is low.

Disclosure of Invention

The application provides an attendance checking equipment adjusting method, an attendance checking equipment adjusting device, electronic equipment and a storage medium, which are used for solving the problems that in the prior art, after the attendance checking equipment is installed, the face evaluation and recognition time is long, and the recognition accuracy is low.

In a first aspect, the present application provides an attendance device adjustment method for adjusting a plurality of attendance devices in a target scene, the attendance devices performing face recognition on a user by continuously shooting at least one frame image of the user; the method comprises the following steps:

for each attendance device in the attendance devices, carrying out face recognition on a plurality of users through the attendance device, and determining an image set shot in the process from each user entering a stable recognition state to successful recognition; in the stable recognition state, a face detection frame and an acquaintance in a shot image meet a preset condition;

determining target attendance equipment in the plurality of attendance equipment according to the corresponding acquaintance degree of the image set of each attendance equipment;

and adjusting the installation modes of other attendance equipment in the plurality of attendance equipment according to the position information of the face detection frame corresponding to the target attendance equipment.

Optionally, determining the set of images captured during the process from the time when each user enters the stable recognition state to the time when the recognition is successful, includes:

determining a corresponding target image when the user is successfully identified, and adding the target image to an image set;

K =0 is set, and the following steps are repeatedly performed:

determining a current image to be processed, wherein the difference between the current image to be processed and the target image is k frames;

calculating the intersection area of the face detection frames of the current image to be processed and the next frame of image and the difference value of the recognition degrees of the current image to be processed and the next frame of image;

judging whether the intersection area is larger than a first threshold value and the difference value is smaller than a second threshold value;

if yes, adding the current image to be processed to the image set, and adding 1 to k; if not, ending.

Optionally, determining a target attendance device of the multiple attendance devices according to the corresponding degree of acquaintance of the image set of each attendance device includes:

aiming at each attendance checking device, the following steps are executed: after image sets of a plurality of users corresponding to the attendance checking equipment are determined, calculating reciprocals of the acquaintance of all images in the image sets aiming at each image set, and adding the calculated reciprocals to obtain the hit probability corresponding to the image sets; calculating the average value of the hit probabilities of a plurality of image sets corresponding to the attendance checking equipment to obtain the hit probability corresponding to the attendance checking equipment;

And determining target attendance equipment in the plurality of attendance equipment according to the hit probability corresponding to each attendance equipment.

Optionally, the adjusting, according to the position information of the face detection frame corresponding to the target attendance device, the installation modes of other attendance devices in the plurality of attendance devices includes:

acquiring position information of a face detection frame of a corresponding target image when the target attendance equipment successfully identifies faces of a plurality of users; the position information comprises a central point position coordinate, a length and a width;

and determining a target position guide frame corresponding to the target attendance equipment based on the position information, and adjusting the installation modes of other attendance equipment in the plurality of attendance equipment based on the target position guide frame.

Optionally, determining a target position guide frame corresponding to the target attendance device based on the position information includes:

sequencing center point position coordinates of face detection frames of target images corresponding to a plurality of users according to the sequence of the hit probabilities of the plurality of users corresponding to the target attendance equipment from large to small to obtain a first sequence, and sequencing the hit probabilities of a plurality of image sets in the target attendance equipment from small to large to obtain a second sequence;

Performing linear weighting calculation based on the first sequence and the second sequence to obtain the position coordinates of the central point of the target position guide frame;

and determining the target position guide frame corresponding to the target attendance checking equipment by using the calculated central point position coordinates of the target position guide frame and the average value of the length and the average value of the width of the face detection frame of the target image corresponding to the plurality of users.

Optionally, adjusting the installation manner of other attendance checking devices in the multiple attendance checking devices based on the target position guide frame includes:

aiming at each attendance checking device, acquiring a face detection frame for carrying out face recognition on a user after the attendance checking device is adjusted;

feeding back prompt information to the attendance checking equipment based on the face detection frame and the target position guide frame; the prompt information is used for indicating the angle and the direction of the attendance checking equipment to be adjusted;

and determining the installation modes of other attendance equipment in the plurality of attendance equipment based on the prompt information.

Optionally, the prompt information includes continuous adjustment information and successful adjustment information; feeding back prompt information to the attendance checking equipment based on the face detection frame and the target position guide frame, and the method comprises the following steps:

Judging whether the face detection frame meets the condition corresponding to the target position guide frame;

if yes, feeding back adjustment success information to the attendance checking equipment so that the attendance checking equipment can identify the face based on the face detection frame;

if not, feeding back continuous adjustment information to the attendance checking equipment so that the attendance checking equipment adjusts the angle and the orientation of the attendance checking equipment based on the continuous adjustment information until the adjusted face detection frame meets the condition corresponding to the target position guide frame.

In a second aspect, the application provides an attendance device adjusting apparatus, the apparatus is used for adjusting a plurality of attendance devices in a target scene, and the attendance devices perform face recognition on a user by continuously shooting at least one image of the user; the device comprises:

the identification module is used for carrying out face identification on a plurality of users through the attendance equipment aiming at each attendance equipment in the attendance equipment and determining an image set shot in the process that each user enters a stable identification state until the identification is successful; in the stable recognition state, a face detection frame and an acquaintance degree in a shot image meet a preset condition;

The determining module is used for determining target attendance equipment in the plurality of attendance equipment according to the corresponding acquaintance degree of the image set of each attendance equipment;

and the adjusting module is used for adjusting the installation modes of other attendance checking equipment in the plurality of attendance checking equipment according to the position information of the face detection frame corresponding to the target attendance checking equipment.

In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer execution instructions;

the processor executes computer-executable instructions stored by the memory to implement the method of any one of the first aspects.

In a fourth aspect, the present application provides a computer-readable storage medium storing computer-executable instructions for implementing the method of any one of the first aspects when executed by a processor.

In summary, the present application provides an attendance device adjustment method, an attendance device adjustment apparatus, an electronic device, and a storage medium, which can perform face recognition on a plurality of users through an attendance device for each of a plurality of attendance devices, and determine an image set photographed in a process from entering a stable recognition state to a successful recognition of each user; in the stable recognition state, a face detection frame and an acquaintance degree in a shot image meet preset conditions; further, determining a target attendance device in the plurality of attendance devices according to the corresponding acquaintance degree of the image set of each attendance device; therefore, the installation modes of other attendance equipment in the plurality of attendance equipment can be adjusted according to the position information of the face detection frame corresponding to the target attendance equipment, so that the plurality of attendance equipment are all located at proper identification positions, and further, when the attendance equipment identifies the face of a user, the face evaluation and identification time can be reduced, and the identification accuracy is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;

fig. 2 is a schematic structural diagram of a human face attendance checking device;

fig. 3 is a schematic view of a flow of face detection;

fig. 4 is a schematic flow chart of an attendance checking apparatus adjustment method according to an embodiment of the present application;

fig. 5 is a scene schematic diagram of an attendance checking apparatus determining a captured image set according to an embodiment of the present application;

fig. 6 is a scene schematic diagram of adjusting an installation manner of attendance checking equipment according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an attendance checking apparatus adjusting device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the claimed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The term "plurality" in this application means two or more. The term "and/or" in this application is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present application generally indicates that the preceding and following related objects are in an "or" relationship; in the formula, the character "/" indicates that the preceding and following related objects are in a relationship of "division". "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.

In the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same or similar items having substantially the same function and action. For example, the first device and the second device are only used for distinguishing different devices, and the sequence order thereof is not limited. Those skilled in the art will appreciate that the terms "first," "second," etc. do not denote any order or quantity, nor do the terms "first," "second," etc. denote any order or importance.

It is noted that, in the present application, words such as "exemplary" or "for example" are used to mean exemplary, illustrative, or descriptive. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

It is to be understood that the various numerical references referred to in the embodiments of the present application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of the present application.

It should be understood that, in the embodiments of the present application, the size of the serial number of each process described below does not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Embodiments of the present application will be described with reference to the accompanying drawings. Fig. 1 is a schematic view of an application scenario provided by an embodiment of the present application, and an attendance device adjustment method provided by the present application may be applied to the application scenario shown in fig. 1, where the application scenario includes: attendance equipment and personnel of checking card on duty at a certain career unit in-process of checking card on duty, because the reason of attendance equipment installation angle, make attendance equipment just can normally accomplish one person's the flow of checking card for several seconds, delay a little, cause the condition that follow-up personnel of checking card were queued to take place, influence the efficiency of checking card, to this kind of situation, adjust this attendance equipment's angle through utilizing the attendance equipment adjustment method that this application provided, make attendance equipment be located suitable identification position and carry out face identification, reduce face assessment discernment time, improve the success rate of checking card, if first person is when face identification is carried out to attendance equipment is located suitable identification position, the degree of acquaintance can reach 0.9, stand horse can face identification succeed.

Exemplarily, fig. 2 is a schematic structural diagram of a human face attendance checking device, as shown in fig. 2, the human face attendance checking device is a typical human face access control attendance checking device, and includes a camera 201, a light shield 202, a processor 203, an angle adjusting bracket 204, a bracket fixing stud 205 and a display screen 206, wherein the angle adjusting bracket 204 can be adjusted to a certain angle, so as to change an angle of the attendance checking device for collecting a human face, the bracket fixing stud 205 is used for fixing the attendance checking device to reduce jitter, the camera 201 is used for collecting a human face image of a person who punches a card, the processor 203 is used for detecting a human face, and the display screen 206 is used for displaying a detection result of the attendance checking device.

The face recognition is composed of two parts, face image acquisition and face image detection, the camera 201 is used for face image acquisition, the processor 203 performs face image detection, and the corresponding flow of face image detection is as follows: fig. 3 is a schematic diagram of a flow of face detection, as shown in fig. 3, the whole flow of face image detection is a continuous identification process, specifically, a face attendance device collects a face image to further determine whether the face image is living, if so, the obtained face image is sent to a predefined algorithm to extract a feature value, further, the extracted feature value is compared with the existing person information in a white list stored by the face attendance device, and when the identity is greater than a threshold value, it can be determined that the card is successfully printed.

The method for judging whether the human body exists can be realized by judging whether the change of the micro expression exists in the obtained images or not, the method is not specifically limited in the embodiment of the application, the time of the human face attendance checking equipment for processing the process of detecting the human face image for one time is about 0.5 second, and if the human face identification for the first time is unsuccessful, the human face image is obtained again for repeated identification for many times until the human face identification is successful.

Therefore, the present application provides an attendance device adjustment method, a plurality of attendance devices in the same environment, if corresponding to similar recognition conditions, the face recognition results thereof can refer to each other, and therefore, the recognition efficiency of face recognition of a plurality of users by a plurality of attendance devices can be obtained, the angle adjustment mode of the attendance device is dynamically calculated, and then the adjustment of the installation angles of a plurality of attendance devices is semi-automatically completed under manual assistance, and in the continuous long-term use process, the repeated recognition efficiency of face recognition of a plurality of users by a plurality of attendance devices is performed, the angle adjustment mode of the attendance device in the same environment is optimized, so that the attendance device is in a proper position, and further, the accuracy of face acquisition is improved.

Exemplarily, fig. 4 is a schematic flow diagram of an attendance device adjustment method provided in an embodiment of the present application, and as shown in fig. 4, the method in the embodiment of the present application is configured to adjust multiple attendance devices in a target scene, where the attendance devices perform face recognition on a user by continuously shooting at least one frame of image of the user, and the method in the embodiment of the present application includes:

s401, for each attendance checking device in the attendance checking devices, carrying out face recognition on a plurality of users through the attendance checking device, and determining an image set shot in the process that each user enters a stable recognition state until the recognition is successful; and in the stable identification state, the face detection frame and the acquaintance degree in the shot image meet the preset conditions.

In this embodiment, the stable recognition state may refer to a state where the user is stationary or not swayed, and the attendance device may recognize a recognition state of a face of the user from the captured image, where in the stable recognition state, the face detection frame and the recognition degree in the captured image satisfy a preset condition, where the face detection frame may refer to a corresponding position frame of the captured image of the attendance device displayed on a display screen of the attendance device, the recognition degree may refer to a similarity between the captured image of the attendance device and an image pre-stored in the attendance device, and the preset condition may be a condition set to determine whether at least one captured image belongs to the same user, for example, the preset condition may be that an intersection area between the face detection frame in the captured current image and the face detection frame in a next frame of image is greater than a first threshold, and a difference between the recognition degree of the captured current image and the recognition degree of the next frame of image is smaller than a second threshold, the embodiment of the present application does not specifically limit the setting content of the preset condition.

In this step, the image set may refer to at least one frame of image corresponding to the process from the state that the attendance checking device can recognize the face of the user from the shot image to the successful recognition, and the image set is used to determine the hit probability that the user is successfully recognized by the attendance checking device.

For example, a plurality of attendance devices are installed in a large factory park, a plurality of users can perform face recognition through the attendance devices for each attendance device, and further, based on images shot when the attendance devices perform face recognition on the users, a set of images shot from each user in a stable recognition state to a successful recognition process is determined, the set of images is used for calculating the hit probability of each user successfully recognized by the attendance devices, and further, the hit probability corresponding to the plurality of attendance devices is determined.

S402, determining target attendance equipment in the plurality of attendance equipment according to the corresponding acquaintance degree of the image set of each attendance equipment.

In this step, the target attendance device may refer to an attendance device with the highest accuracy of face recognition among a plurality of attendance devices in a target scene, that is, an installation angle of the target attendance device is an optimal installation angle among the plurality of attendance devices, and other attendance devices in the plurality of attendance devices may be installed with reference to an installation manner of the target attendance device, where the target scene may refer to a scene in which the attendance devices are installed in the same or similar scene, for example, a scene in which the target scene may be a large-scale factory park or a small-scale business institution.

Specifically, according to an image set corresponding to a plurality of attendance devices installed in a large-scale factory park, the degree of acquaintance corresponding to the image set can be obtained, and then a target attendance device among the plurality of attendance devices can be determined.

And S403, adjusting the installation modes of other attendance checking equipment in the plurality of attendance checking equipment according to the position information of the face detection frame corresponding to the target attendance checking equipment.

In the embodiment of the application, the position information may include central point position coordinate, length and width for calculate the best face recognition position frame that target attendance equipment corresponds, face recognition position frame is a rectangle, if the position information of the face detection frame of a certain user that target attendance equipment corresponds is ((10, 12), 0.08, 0.06), the position information also may include central point position coordinate, radius, face recognition position frame is a circular this moment, the shape of this application embodiment to face recognition position frame is not specifically limited, the position information only is used for expressing the position of face recognition position frame.

In this step, the installation mode is used to indicate an installation angle of the attendance checking apparatus, that is, an angle at which the attendance checking apparatus performs face recognition, specifically, after the position information of the face detection frame corresponding to the target attendance checking apparatus is obtained, the optimal face recognition position frame corresponding to the target attendance checking apparatus may be calculated, and then the installation angles of other attendance checking apparatuses in the multiple attendance checking apparatuses in the target scene may be adjusted according to the optimal face recognition position frame, so that the multiple attendance checking apparatuses in the target scene are all in appropriate positions to recognize faces, that is, the multiple attendance checking apparatuses in the target scene all use the optimal face recognition position frame to perform face recognition on users.

Therefore, the attendance device adjusting method provided by the embodiment of the application can be used for carrying out face recognition on a plurality of users through the attendance devices aiming at each attendance device in the plurality of attendance devices and determining the image set shot in the process that each user enters a stable recognition state until the recognition is successful; in the stable recognition state, a face detection frame and an acquaintance degree in a shot image meet preset conditions; further, determining a target attendance device in the plurality of attendance devices according to the corresponding acquaintance degree of the image set of each attendance device; therefore, the installation modes of other attendance equipment in the plurality of attendance equipment can be adjusted according to the position information of the face detection frame corresponding to the target attendance equipment, so that the plurality of attendance equipment are all located at proper identification positions, and further, when the attendance equipment identifies the face of a user, the face evaluation and identification time can be reduced, and the identification accuracy is improved.

It should be noted that, the execution main body of the present application may be a backend server corresponding to a plurality of attendance devices in a target scene, the backend server is connected to the plurality of attendance devices, and is configured to acquire data from the plurality of attendance devices and process the data, and the execution main body may also be a certain attendance device among the plurality of attendance devices in the target scene, where the attendance device functions the same as the backend server, and the execution main body may also be a certain control module disposed in the cloud, that is, for each target scene, the cloud may allocate a control module in advance for executing a function the same as that of the backend server.

Optionally, determining the image set captured during the process from the time when each user enters the stable recognition state to the time when the recognition is successful, includes:

k =0 is set, and the following steps are repeatedly performed:

In this embodiment of the application, the target image may refer to a user face image successfully corresponding to the captured image when the attendance device performs face recognition on the captured image, the intersection area may refer to an overlapping area of a face detection frame of a current to-be-processed image and a next frame image recognized when the attendance device performs face recognition on the captured image, and the first threshold may refer to a threshold set for determining whether an intersection area of the face detection frame of the current to-be-processed image and the next frame image satisfies a condition, for example, the first threshold is 0.1m ²The second threshold may be used to determine the current image to be processed and the next frameThe threshold set as to whether the difference in the degree of recognition of the image satisfies the condition, for example, the second threshold is 0.2.

For example, fig. 5 is a scene schematic diagram of an attendance device determining a captured image set according to an embodiment of the present application, and as shown in fig. 5, in a successful detection performed by the attendance device on an identification number (ID) XXX, n times of detection cycles, for example, 4 detection cycles, are actually required, where the detected image set includes 4 captured images shown in fig. 5, and the captured image set is determined in a process from when the user XXX enters a stable recognition state to when recognition succeeds, including the following steps: and determining that the corresponding target image is an image with the identification degree of 0.85 when the user XXX is successfully identified, wherein the identification degree is greater than a set threshold value, so that the identification is successful, adding the target image into the image set, further determining that the attendance checking equipment successfully acquires the target image after carrying out face image identification for several times, and adding the image corresponding to the face image identification for which times into the image set.

Specifically, which number of times of images corresponding to the face image recognition is obtained through the following steps: setting k =0, and performing the following steps: acquiring an image with the recognition degree of 0.71 of the current image to be processed, and calculating whether the intersection area of a face detection frame of the image with the recognition degree of 0.71 and the image with the recognition degree of 0.76 of the next frame of image is larger than a first threshold value or not and whether the difference value of the image with the recognition degree of 0.71 and the image with the recognition degree of 0.76 is smaller than a second threshold value or not; if the judgment result is yes, adding an image with the identification degree of 0.71 to the image set, and adding 1 to k, wherein k = 1; further, acquiring an image with an acquaintance degree of 0.76, calculating whether the intersection area of the face detection frames of the image with the acquaintance degree of 0.76 and the image with the acquaintance degree of 0.82 is larger than a first threshold value, and whether the difference value between the image with the acquaintance degree of 0.76 and the image with the acquaintance degree of 0.82 is smaller than a second threshold value, if so, adding the image with the acquaintance degree of 0.76 to the image set, and adding 1 to k again, wherein k = 2; further, the similar process is repeatedly executed until the intersection area of the face detection frame of the current image to be processed and the next frame of image is smaller than a first threshold, and the difference value of the degree of identity between the current image to be processed and the next frame of image is larger than a second threshold, and then the process is ended, and the image set shot from the user XXX entering the stable recognition state to the successful recognition process is obtained as follows: an image with a recognition degree of 0.71, an image with a recognition degree of 0.76, an image with a recognition degree of 0.82, and an image with a recognition degree of 0.85.

It should be noted that, determining that the image sets captured in the process from the other users entering the stable identification state to the identification success are similar to the above process, and are not described herein again, the images included in the image set of each user may be the same or different, and the number of images included in the image set of each user is not specifically limited in this embodiment, which is determined according to specific situations.

It can be understood that, when determining a corresponding target image when the user is successfully identified, an optimization algorithm may be used, wherein when the image quality acquired by the optimization algorithm for face identification is relatively ideal, the identification accuracy rate is substantially consistent, the optimization algorithm may improve the identification rate, optimize the image effect of face acquisition, and further rapidly improve the face identification card-punching rate, and when determining a target image corresponding to the user is successfully identified, the face detection method illustrated in fig. 3 may be used, but the accuracy is relatively low, so that at least one frame of image photographed by the user may also be identified by using the pre-trained deep learning neural network model, the target image is determined by using the deep learning neural network model, even when the image quality is relatively unsatisfactory, the face identification effect is relatively good, and the identification accuracy is relatively high.

Therefore, the image set shot in the process from each user entering the stable identification state to the identification success can be determined through the set conditions and the set algorithm, the number of images contained in the image set can be accurately obtained, the target attendance equipment can be determined by using the determined image set, and the accuracy of determining the target attendance equipment is improved.

Optionally, determining a target attendance device of the multiple attendance devices according to the corresponding acquaintance degree of the image set of each attendance device includes:

aiming at each attendance checking device, the following steps are executed: after image sets of a plurality of users corresponding to the attendance checking equipment are determined, calculating reciprocals of the acquaintance degree of each image in the image sets aiming at each image set, and adding the calculated reciprocals to obtain a hit probability corresponding to the image sets; calculating the average value of the hit probabilities of a plurality of image sets corresponding to the attendance checking equipment to obtain the hit probability corresponding to the attendance checking equipment;

In the embodiment of the application, the hit probability is used for expressing the probability that the face recognition in the image set is successfully hit when the attendance checking equipment verifies, the smaller the hit probability is, the higher the hit rate is, the faster the hit rate is, and specifically, the hit probability can be determined by the following formula:

Wherein, E_iDenotes the firstiThe hit probability of a set of individual images,L _trepresenting the first in a set of imagestThe degree of acquaintance of the individual images,trepresenting the number of images in the image collection.

In practical application, the number of persons possibly passing through each attendance checking device is not equal, that is, the number of the image sets obtained by each attendance checking device is not equal, or one user can be identified by the attendance checking device for multiple times, so that for each attendance checking device, the user can obtain the E corresponding to the image set_iThe average value of the attendance checking devices corresponds to a plurality of average values, and further, the average values are sorted according to the size, and the attendance checking device target attendance checking device corresponding to the minimum value is taken.

For example, taking fig. 5 as an example, for the captured image set determined in fig. 5, a formula is used to obtain a hit probability corresponding to the image set as

Similarly, the corresponding relation of each image set in the attendance checking equipment can be calculatedAnd further, determining a target attendance device in the plurality of attendance devices according to the calculated hit probability corresponding to each attendance device.

Therefore, according to the embodiment of the application, the hit probability corresponding to the attendance equipment can be calculated by a set algorithm through the acquaintance degree of the image sets of the users corresponding to each attendance equipment, and then the target attendance equipment is determined through the hit probability obtained through calculation, so that the accuracy of calculating the hit probability corresponding to the attendance equipment is improved, the determined target attendance equipment is the highest in fitness, namely the determined target attendance equipment is the best in hit probability among the multiple attendance equipment.

Optionally, according to the position information of the face detection frame corresponding to the target attendance checking device, adjusting the installation modes of other attendance checking devices in the plurality of attendance checking devices, including:

In this step, the target position guide frame may refer to a face detection frame corresponding to an optimal face recognition position of the target attendance device, accuracy of face recognition performed by the user when the face of the user is in the target position guide frame is greatly improved, and an installation manner of other attendance devices in the plurality of attendance devices is adjusted based on the target position guide frame, that is, an installation angle of the other attendance devices in the plurality of attendance devices is adjusted, so that an effect of face recognition performed by display screens of the other attendance devices is the same as or similar to an effect of face recognition performed by display screens of the target attendance devices.

For example, in the application scenario of fig. 1, a target attendance device of attendance devices installed by the institution is determined, further, based on the position coordinates, the length, and the width of the center point of the face detection frame of the target image corresponding to the target attendance device when the face recognition of multiple users is successful, the position information of the target position guide frame corresponding to the target attendance device is calculated by using a predefined algorithm, and then the target position guide frame is determined, and further, the installation manner of the attendance device shown in fig. 1 may be adjusted based on the target position guide frame.

The predefined algorithm may be a weight algorithm determined based on the hit probability of the target image, that is, a corresponding weight value may be set for the center position coordinate based on the hit probability, and then the position information of the target position guide frame is calculated, and the predefined algorithm may also be other algorithms, such as a mode calculation algorithm, an average calculation algorithm, and the like.

It should be noted that, in the embodiment of the present application, the installation angle of the attendance checking apparatus is not specifically limited, and the installation angle may form various angles with the vertical horizontal plane, which is a reference according to the installation angle of the target attendance checking apparatus.

Therefore, according to the embodiment of the application, the optimal position corresponding to the target position guide frame can be obtained based on the position information of the face detection frame corresponding to the target attendance equipment, the installation modes of other attendance equipment in the plurality of attendance equipment are adjusted based on the target position guide frame, the plurality of attendance equipment are all at reasonable installation angles, the face of the user is identified based on the target position guide frame, and the accuracy of face identification is improved.

and determining the target position guide frame corresponding to the target attendance equipment by using the calculated central point position coordinates of the target position guide frame and the average value of the length and the average value of the width of the face detection frames of the target images corresponding to the plurality of users.

In the embodiment of the present application, a corresponding weight value is set for a corresponding center point position coordinate based on a hit probability of a user, the larger the hit probability corresponding to the center point position coordinate is, the smaller the occupied weight corresponding to the center point position coordinate is, the weight may be a value corresponding to the hit probability, or may be another value set by the user, which is not specifically limited in the embodiment of the present application.

Specifically, the central point position coordinate of the target position guide frame is calculated, the weight of the central point position coordinate of the face detection frame of the target image corresponding to the plurality of users is adjusted according to the hit probability of the plurality of users, the weighted sum of the central point position coordinate of the face detection frame of the target image corresponding to the plurality of users after adjustment is calculated, and further, the central point position coordinate of the target position guide frame is obtained by calculating the ratio of the weighted sum to the sum of the hit probability of the plurality of users.

Illustratively, taking 3 users identified by the target attendance device as an example, each user corresponds to an image set identified by the attendance device, the hit probabilities E corresponding to the image sets of the 3 users are (1.2, 1.4, 1.3), respectively, the coordinates of the center point of the face detection frame of the target image are represented by (X, y), the coordinates of the X are (10, 12, 14), respectively, and X is ₀1.2, X with E value of minimum =10₁1.4, X with E value of =12₂E value of 1.3 for =14, since X₀The corresponding E value is minimum (so the weighting is maximum), X₁If the value of E is the largest (and therefore the weight is the smallest) when =12, the first sequence is (12, 14, 10) and the second sequence is (1.2, 1.3, 1.4), and let X further be₀Multiplying by the maximum value of 1.4, X in the E value₁Multiplying by the minimum value of 1.2, X in the E value₂Multiplying by another value 1.3 in the E value to obtain the target position indexThe horizontal coordinate x '= (1.4 + 10+1.2 + 12+1.3 + 14)/(1.2 +1.4+ 1.3) ≈ 11.95) of the center point position of the guide frame, and the coordinate of the vertical coordinate y' of the center point position of the target position guide frame can be obtained by the same method, and the length and the width of the target position guide frame are the average values of the length and the width corresponding to the face detection frame of each target image.

Therefore, in the embodiment of the application, the position information of the target position guide frame corresponding to the target attendance checking device can be calculated by using the method, and then the target position guide frame is determined, wherein the larger the hit probability corresponding to the position coordinate of the central point of the face detection frame of the target image is, the smaller the occupied weight corresponding to the center point is, so that the position corresponding to the target position guide frame is closer to the optimal recognition position, and the higher the accuracy of the determined target position guide frame is.

In the embodiment of the present application, the angle may be used to indicate an adjusted angle, such as 30 degrees, and the orientation may be used to indicate an adjusted direction, such as right or up.

In this step, the prompt information is used to indicate the angle and the orientation of the attendance device that need to be adjusted, if a certain attendance device needs to be adjusted, the sent prompt information may be "adjusted to the right by 30 degrees", if a certain attendance device no longer needs to be adjusted, the sent prompt information may be "adjusted by 0 degree" or "angle and orientation do not need to be adjusted"; the prompt information may be displayed on a display screen of the attendance device in a form of a display frame for a user to view, or the content of the prompt information may be broadcasted on the attendance device in a voice prompt manner.

For example, in an application scenario shown in fig. 1, for the attendance device shown in fig. 1, a face detection frame for performing face recognition on a user after adjusting the attendance device may be first obtained, further, the obtained face detection frame and the calculated target position guide frame are compared, and prompt information is fed back to a display screen of the attendance device based on a comparison result, where if the prompt information is "adjust 10 degrees to the left", further, an installation manner of the attendance device may be determined based on the prompt information, that is, a corresponding adjustment operation may be manually performed.

Therefore, according to the embodiment of the application, prompt information can be fed back to the attendance equipment based on the information of the face detection frame and the target position guide frame after the attendance equipment is adjusted, so that whether the attendance equipment of a user needs to be adjusted continuously is prompted, whether other attendance equipment in the attendance equipment achieves the same effect of face recognition with the display screen of the target attendance equipment is determined, and the position of each attendance equipment is optimized.

if so, feeding back adjustment success information to the attendance checking equipment so that the attendance checking equipment identifies the face based on the face detection frame;

if not, feeding back continuous adjustment information to the attendance equipment so that the attendance equipment adjusts the angle and the direction of the attendance equipment based on the continuous adjustment information until the adjusted face detection frame meets the condition corresponding to the target position guide frame.

In the embodiment of the application, the continuous adjustment information is information indicating the angle and the direction of the continuous adjustment of the attendance equipment; if the continuous adjustment information is 'adjustment 10 degrees to the right'; the adjustment success information is information indicating that the attendance checking equipment succeeds, and if the adjustment success information is "angle and direction do not need to be adjusted" or "adjustment succeeds", the content of the continuous adjustment information and the adjustment success information is not specifically limited in the embodiment of the present application.

In this step, the condition corresponding to the target position guide frame may refer to whether the face detection frame and the target position guide frame are overlapped in a display screen of the same attendance device, or whether the overlap ratio is greater than a preset threshold, where the condition is used to determine whether the face detection frame is in the optimal recognition position when the attendance device performs face recognition.

Exemplarily, fig. 6 is a scene schematic diagram for adjusting an installation mode of an attendance checking apparatus provided in an embodiment of the present invention, as shown in fig. 6, taking adjusting an attendance checking apparatus as an example, a human face of a tester is placed in a human face detection frame 1 placed in a display screen of the attendance checking apparatus, whether the human face detection frame 1 is overlapped with a target position guide frame is determined, if yes, adjustment success information is fed back to the attendance checking apparatus to remind a user that an angle and an orientation of the attendance checking apparatus at this time are optimal positions, if not, continuous adjustment information is fed back to the attendance checking apparatus, if "adjust 10 degrees right", an angle and an orientation of the attendance checking apparatus are adjusted by manual operation based on the continuous adjustment information, a position of the human face is moved to a position of a human face detection frame 2, whether the human face detection frame 2 is overlapped with the position guide frame at this time is determined, if yes, adjustment success information is fed back to the attendance checking target apparatus, and if not, continuously feeding back continuous adjustment information to the attendance equipment so that the user continuously adjusts the angle and the orientation of the attendance equipment through manual operation based on the continuous adjustment information until the adjusted face detection frame meets the condition corresponding to the target position guide frame.

It can be understood that the above process is also performed by other attendance checking devices until all the attendance checking devices in the target scene are adjusted in angle and direction, so that a plurality of attendance checking devices in the target scene are all in the optimal recognition positions to recognize the face of the user.

Therefore, the method and the device can adjust the angle and the orientation of the attendance equipment based on semi-automatic manual correction, so that the attendance equipment is located at the optimal face recognition position, and the position of the attendance equipment in a target scene is optimized based on a coordination optimization method among multiple attendance equipment, so that the face acquisition accuracy is improved, and the face evaluation and recognition time is shortened.

It should be noted that the method for adjusting the attendance checking equipment provided by the embodiment of the application can repeatedly correct the angle and the orientation of the equipment in the continuous long-term use process, optimize the face acquisition accuracy, gradually improve the face recognition rate of the attendance checking equipment, and is not limited to the first installation of the attendance checking equipment.

In the foregoing embodiment, the attendance device adjusting method provided in the embodiment of the present application is described, but in order to implement each function in the method provided in the embodiment of the present application, the electronic device serving as an execution subject may include a hardware structure and/or a software module, and each function is implemented in a form of a hardware structure, a software module, or a hardware structure plus a software module. Whether any of the above functions is implemented as a hardware structure, a software module, or a combination of a hardware structure and a software module depends upon the particular application and design constraints imposed on the technical solution.

For example, fig. 7 is a schematic structural diagram of an attendance device adjusting apparatus provided in an embodiment of the present application, and as shown in fig. 7, the apparatus is configured to adjust multiple attendance devices in a target scene, where the attendance devices perform face recognition on a user by continuously shooting at least one frame of image of the user; the device comprises: the system comprises an identification module 710, a determination module 720 and an adjustment module 730, wherein the identification module 710 is configured to perform face identification on multiple users through the attendance checking equipment for each attendance checking equipment in the multiple attendance checking equipments, and determine an image set shot in a process from each user entering a stable identification state to successful identification; in the stable recognition state, a face detection frame and an acquaintance degree in a shot image meet a preset condition;

the determining module 720 is configured to determine a target attendance device of the multiple attendance devices according to the corresponding acquaintance degrees of the image sets of the attendance devices;

the adjusting module 730 is configured to adjust the installation modes of other attendance devices in the multiple attendance devices according to the position information of the face detection frame corresponding to the target attendance device.

Optionally, the identification module 710 includes a determination unit and a judgment unit;

Specifically, the determining unit is configured to determine a corresponding target image when the user is successfully identified, and add the target image to an image set;

the judging unit is used for setting k =0 and repeatedly executing the following steps:

Optionally, the determining module 720 is specifically configured to:

Optionally, the adjusting module 730 includes an obtaining unit and an adjusting unit;

specifically, the acquiring unit is configured to acquire position information of a face detection frame of a corresponding target image when the target attendance checking device successfully performs face recognition on multiple users; the position information comprises a central point position coordinate, a length and a width;

the adjusting unit is used for determining a target position guide frame corresponding to the target attendance equipment based on the position information and adjusting the installation modes of other attendance equipment in the plurality of attendance equipment based on the target position guide frame.

Optionally, the adjusting unit includes a calculating unit and a guiding unit; the computing unit is configured to:

Optionally, the guiding unit is configured to:

Optionally, the prompt information includes continuous adjustment information and successful adjustment information; the guiding unit is specifically configured to:

The specific implementation principle and effect of the attendance checking device adjustment apparatus provided in the embodiment of the present application may refer to the corresponding relevant description and effect in the above embodiment, which are not described here in too much detail.

For example, an embodiment of the present application further provides a schematic structural diagram of an electronic device, and fig. 8 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, as shown in fig. 8, the electronic device may include: a processor 801 and a memory 802 communicatively coupled to the processor; the memory 802 stores a computer program; the processor 801 executes the computer program stored in the memory 802, so that the processor 801 executes the method according to any of the above embodiments.

The memory 802 and the processor 801 may be connected by a bus 803.

The embodiment of the present application further provides a computer-readable storage medium, where a computer program executing instruction is stored, and the computer executing instruction is used for implementing the attendance device adjusting method in any one of the foregoing embodiments of the present application when the computer executing instruction is executed by a processor.

The embodiment of the present application further provides a chip for running the instruction, where the chip is configured to execute the method for adjusting the attendance checking device executed by the electronic device in any of the embodiments of the present application.

The embodiment of the present application further provides a computer program product, which includes a program code, and when a computer runs the computer program, the program code executes the attendance checking device adjustment method executed by the electronic device in any of the embodiments of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a logical division, and other divisions may be realized in practice, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or modules, and may be in an electrical, mechanical or other form.

Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to implement the solution of the embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware mode, and can also be realized in a mode of hardware and a software functional unit.

The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor to execute some steps of the methods described in the embodiments of the present application.

It should be understood that the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the methods disclosed in the incorporated application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

The memory may include a Random Access Memory (RAM), and may further include a non-volatile memory (NVM), such as at least one magnetic disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic disk or an optical disk.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.

The above description is only a specific implementation of the embodiments of the present application, but the scope of the embodiments of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the embodiments of the present application should be covered within the scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application shall be subject to the protection scope of the claims.

Claims

1. The method is characterized in that the method is used for adjusting a plurality of attendance devices in a target scene, and the attendance devices perform face recognition on a user by continuously shooting at least one frame image of the user; the method comprises the following steps:

and adjusting the installation modes of other attendance checking equipment in the plurality of attendance checking equipment according to the position information of the face detection frame corresponding to the target attendance checking equipment.

2. The method of claim 1, wherein determining the set of images captured during the period from each user entering a stable recognition state to successful recognition comprises:

k =0 is set, and the following steps are repeatedly performed:

3. The method of claim 1, wherein determining a target attendance device of the plurality of attendance devices according to the corresponding degree of acquaintance of the image set of each attendance device comprises:

4. The method of any one of claims 1 to 3, wherein adjusting the installation mode of other attendance devices of the plurality of attendance devices according to the position information of the face detection frame corresponding to the target attendance device comprises:

5. The method of claim 4, wherein determining a target location guidance box corresponding to a target attendance device based on the location information comprises:

6. The method of claim 5, wherein adjusting the installation of other attendance devices in the plurality of attendance devices based on the target location guide box comprises:

7. The method of claim 6, wherein the prompt message comprises a continue adjustment message and an adjustment success message; feeding back prompt information to the attendance checking equipment based on the face detection frame and the target position guide frame, and the method comprises the following steps:

8. An attendance device adjusting device is characterized in that the device is used for adjusting a plurality of attendance devices in a target scene, and the attendance devices perform face recognition on a user by continuously shooting at least one frame image of the user; the device comprises:

9. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer execution instructions;

The processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1-7.

10. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, perform the method of any one of claims 1-7.