CN112668383A

CN112668383A - Attendance checking method and system based on face recognition, electronic equipment and storage medium

Info

Publication number: CN112668383A
Application number: CN202010717901.8A
Authority: CN
Inventors: 夏春秋
Original assignee: Shenzhen Vision Technology Co Ltd
Current assignee: Shenzhen Vision Technology Co Ltd
Priority date: 2020-07-23
Filing date: 2020-07-23
Publication date: 2021-04-16

Abstract

The invention relates to an attendance checking method, an attendance checking system, electronic equipment and a storage medium based on face recognition, wherein the method comprises the following steps: the attendance machine acquires a first face image, stores the first face image, extracts first face features and generates a face feature database; the attendance machine acquires a second face image and additional information corresponding to the second face image, and extracts the face features and the additional feature information of the second face image; comparing the face features of the second face image with the face features in the face feature basic database, and updating the corresponding face feature database after successful recognition; and comparing the additional characteristic information and the face characteristics with the face characteristic database, and if the identification is successful, checking the attendance successfully. The multi-dimensional attendance recognition is carried out through various combinations such as face recognition, clothes, hairstyles, expressions and the like, the interest of attendance card punching is increased, the attendance precision is high, and the defects of error comparison and the like are avoided.

Description

Attendance checking method and system based on face recognition, electronic equipment and storage medium

Technical Field

The present invention relates to the field of face recognition technology, and more particularly, to a attendance checking method, system, electronic device and storage medium based on face recognition.

Background

The face recognition attendance machine is a novel storage attendance machine, only needs to collect face images of employees in advance and establish files, and when the employees stand on duty and stand in a recognition area of the face recognition attendance machine, the attendance machine can rapidly record attendance conditions and save records. In the prior art, only the face is scanned, the face information is stored in the attendance machine, the face is compared with the face information stored in the attendance machine, and if the face information passes the identification, the face information passes the identification. Like this when the user increases, have more and more similar face (net red face) now in addition, then this kind of attendance mode attendance inefficiency, compare the mode too simple, the effect that can not reach the attendance is compared to the easy mistake.

Thus, significant advances in the art are needed.

Disclosure of Invention

The technical problem to be solved by the invention is that the current attendance checking mode is too simple and is easy to compare the error attendance checking with the error attendance checking mode, and aiming at the defects in the prior art, the invention provides an attendance checking method based on face recognition on one hand, which comprises the following steps:

the attendance machine acquires a first face image, stores the first face image, extracts first face features and generates a face feature database;

the attendance machine acquires a second face image and additional information corresponding to the second face image, and extracts the face features and the additional feature information of the second face image;

comparing the face features of the second face image with the face features in the face feature basic database, and updating the corresponding face feature database after successful recognition;

and comparing the additional characteristic information and the face characteristics with the face characteristic database, and if the identification succeeds, checking the attendance successfully.

In the attendance checking method based on the face recognition, the first face image and the second face image are the same or different.

In the attendance checking method based on the face recognition, the additional information comprises clothing information, hair style information and expression information.

In the attendance checking method based on the face recognition, any one or more of clothing information, hair style information and expression information are combined and then compared with the face feature database, and if the recognition is successful, the attendance checking is successful.

On the other hand, the invention also provides an attendance system based on face recognition, which comprises: attendance machines and cameras; the camera is used for shooting a first face image and a second face image;

In the attendance system based on the face recognition, the first face image and the second face image are the same or different.

In the attendance system based on face recognition, the additional information comprises clothing information, hair style information and expression information.

In the attendance system based on the face recognition, any one or more of the clothing information, the hair style information and the expression information are combined and then compared with the face feature database, and if the recognition is successful, the attendance is successful.

On the other hand, the invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, wherein when the processor executes the program, the steps of the attendance checking method based on the face recognition are realized.

In another aspect, the present invention further provides a storage medium, where the storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps of the attendance checking method based on face recognition.

The attendance checking method, the attendance checking system, the electronic equipment and the storage medium based on the face recognition have the following beneficial effects that: the multi-dimensional attendance recognition is carried out through various combinations such as face recognition, clothes, hairstyles, expressions and the like, the interest of attendance card punching is increased, the attendance precision is high, and the defects of error comparison and the like are avoided.

Drawings

Various other advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be obtained from these drawings without inventive effort.

The invention will be further described with reference to the accompanying drawings and examples, in which:

fig. 1 is a flow chart of an attendance checking method based on face recognition.

Fig. 2 is a schematic structural diagram of an attendance system based on face recognition.

Fig. 3 is a schematic structural diagram of another attendance system based on face recognition.

Fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the drawings in the embodiments of the present application. It should be apparent that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.

The attendance checking method based on the face recognition can be applied to various server terminals and terminals. The server-side and terminal devices include, but are not limited to, personal computers, server computers, handheld or laptop devices, mobile devices (such as mobile phones, tablet computers, PDAs, media players, etc.), consumer electronics devices, vehicle-mounted computers, smart watches, televisions, and other terminal devices with display screens, etc.

Example one

Fig. 1 is a flowchart of an attendance checking method based on face recognition according to the present invention. As shown in fig. 1, the attendance checking method based on face recognition according to the first embodiment of the present invention at least includes the steps of,

s11, the attendance machine acquires a first face image, stores the first face image, extracts a first face feature and generates a face feature database;

the first face image is shot and captured by the camera, and multi-angle, multi-azimuth and multi-state image acquisition can be realized. And extracting first face features from the first face image to generate a face feature database.

S12, the attendance machine acquires a second face image and additional information corresponding to the second face image, and extracts the face features and the additional feature information of the second face image;

the second face image is shot and captured by the camera, and multi-angle, multi-azimuth and multi-state image acquisition can be realized. The first facial image and the second facial image may be the same or different. The additional information corresponding to the second face image, such as clothes information, hair style information, expression information, etc., is also collected together with the second face image.

S13, comparing the face features of the second face image with the face features in the face feature basic database, and updating the corresponding face feature database after successful recognition;

and if the identification is successful, storing the additional characteristic information extracted from the additional information corresponding to the second face image into a face characteristic database together, and updating the face characteristic database. And if the identification is unsuccessful, the new face information and the additional information are stored in the face feature database directly.

And S14, comparing the additional feature information and the face features with the face feature database, and checking the attendance successfully if the identification is successful.

And comparing the additional characteristic information and the face characteristics with the face characteristic database, and increasing comparison dimensionality, so that the attendance precision is higher, and the problems of high attendance difficulty and low efficiency such as net red face and the like are solved.

Any one or more of the clothing information, the hair style information and the expression information are combined and then compared with the facial features and the facial feature database, and if the identification is successful, the attendance is successful.

During the concrete implementation, consider that some attendance machine meet the outage and do not continue the electricity, the problem that system time is in disorder, then attendance machine is equipped with bluetooth module. When the face image acquisition device is normally used and a face image is acquired, the time of a handheld terminal used by a user, such as a mobile phone, can be acquired in a multi-thread mode. And after the time is collected in time, the attendance machine is automatically updated. The problem of manual setting time of the attendance machine during each outage is avoided like this.

The working process is as follows: the face recognition attendance checking machine is mainly used for counting attendance of employees of a company, when the employees sign, facial photos of the employees need to be collected through a camera, then characteristic values are obtained from the collected photos through a face recognition algorithm and are analyzed and compared with characteristic values of face photos of the employees stored in a database in advance, after the identification is successful, names of the employees are reported, and then the attendance checking is successful.

For example, the camera acquires a first face image of the user a, and the attendance machine stores the first face image of the user a and also stores information such as the name, age and corresponding identity data of the user a. And extracting the face features in the first face image of the user A by the attendance machine. After a plurality of user information are collected, a face feature database is generated. When a random user such as the user B performs attendance for the first time, the attendance machine can match the facial feature information of the user B from the facial feature database, then collect the information of the user B such as clothes, hair style, expression and the like, extract the characteristic information of the user B such as clothes, hair style, expression and the like, update the information of the user B stored in the facial feature database, and supplement the characteristic information of the user B such as clothes, hair style, expression and the like along with the facial image and the facial feature information of the user B. Therefore, when the user B checks attendance again, and single feature information of the user B such as clothes, hairstyle and expression is detected, the face feature of the user B or the single feature combination of the user B such as clothes, hairstyle and expression can be compared for the second time, whether the attendance information of the user B is accurate or not is confirmed again, and the attendance accuracy is improved.

Through face identification, dress, hairstyle, expression etc. many-sided combination carry out multidimension degree attendance discernment, increase the interest that the attendance was checked card, the attendance precision is high, avoids defects such as wrong comparison.

Example two

Fig. 1 is a schematic view of an attendance system based on face recognition according to the present invention. As shown in fig. 2, the attendance system based on face recognition according to the first embodiment of the present invention at least includes an attendance machine and a camera; the camera is used for shooting a first face image and a second face image;

And combining any one or more of the clothing information, the hair style information and the expression information, and comparing the combined information with the facial features and the facial feature database, wherein the attendance is successful if the identification is successful.

Firstly, image data including a human body front image, a human body side image and a human body head image, clothes, expressions and the like are acquired through an image acquisition tool such as a camera. And then, respectively preprocessing the images, and realizing the processing of illumination and noise problems by using methods such as an image enhancement algorithm, gray-scale image conversion, image illumination optimization and the like. Then processing an image containing human head information, obtaining an initial test image through image preprocessing, realizing the detection of the image usability according to a skin color detection algorithm, a Gaussian gradient method and a constructed covariance matrix, and realizing the positioning of human face characteristic points by using an ASM method on the usable basis. And finally, classifying hairstyle, determining an external bounding box of the head or the face by using a skin color detection algorithm and a face detection algorithm in the prior art in the face image, storing information of the position of five sense organs of the image according to the extraction method of the face characteristic points in the steps, segmenting the hair part by using a contour extraction method and a segmentation algorithm, and classifying various segmented hair styles by using a PCA + SVM method. After the front hairstyle category is obtained, the side image of the human body is processed, and the side hairstyle category is determined according to data information such as the corresponding proportion of the side image to the face or the height of the human body. And finally, integrating the data information of the front face image and the side face image of the human body and finally determining the hair style type of the test image.

Analyzing and judging the color and the style of the clothes, and storing the clothes and the clothes characteristic information of the user.

The facial expressions can be recognized by conventional methods. The static image presents the expression state of a single image when the expression occurs, and the dynamic image presents the motion process of the expression among a plurality of images. Therefore, the expression feature extraction algorithm is classified into a feature extraction method based on a static image and a feature extraction method based on a dynamic image, in general, according to the state when an expression occurs and the processing object. The feature extraction algorithm based on the static image can be divided into an integral method and a local method, and the feature extraction algorithm based on the dynamic image is divided into an optical flow method, a model method and a geometric method.

The feature extraction method based on the static image comprises the following steps:

(1) integral process

Facial expressions are reflected by the movement of muscles. The static image of the facial expression visually shows the changes of the facial form and texture caused by the movement of the muscles of the face when the expression occurs. On the whole, the change causes obvious deformation of facial organs, which can affect the global information of the facial image, so that a facial expression recognition algorithm considering expression characteristics from the whole point of view appears.

Classical algorithms in the ensemble method include Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA). The expression features are extracted by adopting the FastICA algorithm, the method not only inherits the characteristic that the ICA algorithm can extract hidden information among pixels, but also can quickly separate the expression features through iteration. By adopting a Support Vector Differential Analysis (SVDA) algorithm which is based on Fisher linear discriminant analysis and a support vector machine, the expression data can have the maximum class-to-class separation under the condition of small sample data, and a decision function required by the SVM algorithm does not need to be constructed. The face image is mapped through a frequency domain space by means of two-dimensional discrete cosine transform, and the classification of the expression characteristics is realized by combining a neural network.

(2) Local method

The facial expression on the static image not only changes integrally, but also changes locally. The information contained in local deformation such as texture and wrinkles of facial muscles is helpful for accurately judging the attribute of the expression. The classical methods of the local method are the Gabor wavelet method and the LBP operator method.

The feature extraction method based on the dynamic image comprises the following steps:

moving images differ from still images in that: the dynamic image reflects the process of occurrence of the facial expression. The expressive features of the dynamic image are therefore mainly manifested in the continuous deformation of the face and the muscle movements of different areas of the face. At present, the feature extraction method based on dynamic images is mainly divided into an optical flow method, a model method and a geometric method.

(1) Optical flow method

The optical flow method is a method for reflecting the gray scale change of corresponding objects between different frames in a dynamic image. The early human face expression recognition algorithm mostly adopts an optical flow method to extract expression characteristics of a dynamic image, and the optical flow method mainly has the advantages of highlighting human face deformation and reflecting human face motion trend. Therefore, the algorithm is still an important method for researching the expression recognition of the dynamic image in the traditional method. Respectively representing the space-time change of the image by adopting an optical flow field and a gradient field between continuous frames, and realizing the expression region tracking of each frame of face image; and then representing the movement of the facial muscles by the change of the movement direction of the characteristic region, thereby corresponding to different expressions.

(2) Method of modelling

The model method in facial expression recognition refers to a statistical method for carrying out parametric description on expression information of dynamic images. The commonly used algorithms mainly include an active shape model method (ASM) and an active appearance model method (AAM), both of which can be divided into two parts, a shape model and a subjective model. In terms of appearance models, ASM reflects local texture information of an image, while AAM reflects global texture information of an image. Recognizing facial actions and expressions by means of a topographic feature model of the image; tracking human face characteristic points by using an AAM and artificial marking method, and acquiring a human face expression area according to the characteristic points; and (3) obtaining the terrain features by calculating a terrain histogram of the facial expression area, thereby realizing expression recognition. And the extraction of the appearance features can be realized under the environment of human face position offset based on the AAM algorithm of the two-dimensional appearance features and the three-dimensional shape features.

(3) Method of geometry

In the expression feature extraction method, researchers consider that the generation and expression of expressions are reflected to a large extent by the changes of facial organs. The main organs of the human face and the fold parts thereof become areas in which expression characteristics are concentrated. Therefore, the method of extracting the facial expression in a geometric form is realized by marking the feature points in the facial organ region, and calculating the distance between the feature points and the curvature of the curve where the feature points are located. And performing gridding representation on the faces with different expressions by using a deformation grid, and taking grid node coordinate change between the first frame and the frame with the maximum expression of the sequence as a geometric feature to realize the identification of the expressions.

EXAMPLE III

Whether a human face exists or not is detected on the acquired and processed image based on the facial features of the human, then the position, the structure and the size of each human face and the position of each main facial organ are analyzed and calculated from the detected and recognized human face image, the feature information in the human face image is matched from a database according to the information, and the information is compared with the human face image recognized in real time, so that the identity information corresponding to each human face is confirmed. The face recognition attendance system is mainly divided into three modules: information input, face attendance and information inquiry. The information input comprises basic information input and face information input. The basic information comprises personnel names, ages and corresponding identity information, and the face information refers to face images for acquisition and processing and characteristic information extraction and storage; the human face attendance checking is that after collected attendance person images are detected and identified by an STM32 series single chip microcomputer, attendance information is confirmed and stored in a database, information inquiry can be carried out by using database systems such as SQL (structured query language) and MySQL (structured query language) on a cloud server to carry out information interaction with a terminal, and attendance record of inquirers and recorded basic information and human face information are implemented.

On the system, an attendance method based on face recognition is executed, and the attendance method based on face recognition at least comprises the following steps:

Example four

Fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. Based on the content of the above embodiment, as shown in fig. 4, the electronic device may include: a processor (processor)301, a memory (memory)302, and a bus 303; wherein, the processor 301 and the memory 302 complete the communication with each other through the bus 303; the processor 301 is configured to invoke computer program instructions stored in the memory 302 and executable on the processor 301 to perform the attendance checking method based on face recognition provided by the above-mentioned embodiments of the methods, for example, including:

and S14, comparing the additional feature information and the face features with the face feature database, and checking the attendance successfully if the identification is successful. Furthermore, the logic instructions in the memory 302 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the embodiments of the present invention may be substantially implemented or contributed to by the prior art, or may be implemented in a software product, which 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) to execute all or part of the steps of the method for generating a memo based on face recognition according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media storing program codes.

By adopting the embodiment, multi-dimensional attendance recognition is carried out through various combinations such as face recognition, clothes, hairstyle, expression and the like, the interest of attendance card punching is increased, the attendance precision is high, and the defects of error comparison and the like are avoided.

EXAMPLE five

Another embodiment of the present invention discloses a computer program product, where the computer program product includes a computer program stored on a non-transitory computer readable storage medium, and the computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the attendance checking method based on face recognition provided in the foregoing embodiments, for example, the method includes the following steps:

and S14, comparing the additional feature information and the face features with the face feature database, and checking the attendance successfully if the identification is successful. By adopting the embodiment, the multidimensional attendance recognition is carried out through the combination of the human face recognition, the clothes, the hair style, the expression and other multiple aspects, the interest of attendance card punching is increased, the attendance precision is high, and the defects of error ratio and the like are avoided.

EXAMPLE six

Another embodiment of the present invention provides a storage medium, where the storage medium stores computer instructions, and the computer instructions enable a computer to execute the attendance checking method based on face recognition provided in the foregoing method embodiments, for example, the method includes the steps of:

In summary, the invention has the beneficial effects that through the design of the above embodiments: the multi-dimensional attendance recognition is carried out through various combinations such as face recognition, clothes, hairstyles, expressions and the like, the interest of attendance card punching is increased, the attendance precision is high, and the defects of error comparison and the like are avoided.

While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.

Claims

1. An attendance checking method based on face recognition is characterized by comprising the following steps:

and comparing the additional characteristic information and the face characteristics with the face characteristic database, and if the identification is successful, checking the attendance successfully.

2. The attendance checking method based on the face recognition of claim 1, wherein the first face image is the same as or different from the second face image.

3. The attendance method based on the face recognition of claim 1, wherein the additional information comprises clothing information, hair style information, and facial expression information.

4. The attendance checking method based on the face recognition of the claim 3, characterized in that any one or more of the information of the clothes, the hair style and the expression information are combined and then compared with the face feature database, and the attendance checking is successful if the recognition is successful.

5. The utility model provides an attendance system based on face identification which characterized in that includes: attendance machines and cameras; the camera is used for shooting a first face image and a second face image;

6. The attendance system based on face recognition of claim 5 wherein the first face image is the same as or different from the second face image.

7. The attendance system based on face recognition as claimed in claim 5, wherein the additional information comprises clothing information, hair style information, expression information.

8. The attendance system based on the face recognition of claim 7, wherein the attendance system is characterized in that any one or more of the clothing information, the hair style information and the expression information are combined and then compared with the face feature database, and the attendance is successful if the identification is successful.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the face recognition-based attendance method according to any one of claims 1 to 4 when executing the program.

10. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the face recognition-based attendance method according to any one of claims 1 to 4.