Online education platform user authentication method and system

Abstract

The invention discloses a user authentication method and system for an online education platform, and solves the problem that the existing method adopts frame-by-frame analysis of a face image, can only simply perform independent processing on each frame, and is sensitive to interference information, and the method comprises the following steps: performing normalization processing on target image information to obtain normalized target image information; a multi-target recognition model is constructed in combination with a multi-layer space displacement sensing mechanism and a cascade attitude regression model, the multi-target recognition model carries out noise reduction processing on target image information and then segments and extracts feature points, and the confidence degree of the target image information and the face standard image is calculated; according to the method, the attention of a background information dispersion model can be overcome through normalization processing of the target image information, background interference factors can be rapidly removed, the multi-target recognition model approximates a real face shape and a feature point position through a clustering analysis mode, correction, noise reduction and optimization are carried out on a result of a previous level, and the accuracy of face recognition is improved. Therefore, the positioning precision of the feature points is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of face recognition, and in particular relates to a user authentication method and system for an online education platform. Background Art

[0002] Face recognition is a technology that identifies or verifies personal identity by analyzing and comparing facial features. It integrates computer image processing technology with biostatistics principles, and uses computer image processing technology to extract character feature points from videos. At the same time, with the popularization of personal computers, the application of face recognition has penetrated into many corners of people's daily lives. This is also reflected in education and training and examination activities. The application of face recognition technology on online education platforms, especially in sign-in authentication, has significant advantages.

[0003] Chinese patent CN112232206B discloses a face recognition method and a face recognition platform based on big data and artificial intelligence. First, the target image to be recognized is subjected to background segmentation processing to obtain a target background image and a target face image; secondly, the target background image is matched with each frame of the reference image in the first target database to obtain a target matching result; then, based on the target matching result, a target recognition rule is determined from a plurality of pre-formed recognition rules; finally, the target face image is recognized based on the target recognition rule. However, the existing method adopts frame-by-frame analysis of face images and can only simply process each frame independently, is sensitive to interference information, and cannot fully utilize the correlation and continuity between the previous and next frames, resulting in the accuracy of the recognition result being limited. In view of the above problems, we propose a user authentication method and system for an online education platform. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a user authentication method and system for an online education platform, which solves the problem that the existing method uses frame-by-frame analysis of facial images and can only simply process each frame independently, is sensitive to interference information, and cannot fully utilize the correlation and continuity between previous and subsequent frames, resulting in limited accuracy of recognition results.

[0005] The present invention is implemented in this way: an online education platform user authentication method, the online education platform user authentication method comprising: Collect target image information in the authentication scene in real time, normalize the target image information, and obtain normalized target image information; Based on the image acquisition device, standard face images are pre-collected, an image database is constructed through standard face images, the image database is traversed, standard face images are extracted from the image database, standard face images are processed based on different angles, brightness, and noise factors, a complex image set is created, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model, the multi-target recognition model is iteratively trained using a complex image set, and a converged multi-target recognition model is output; Taking the normalized target image information as input, the multi-target recognition model is executed. The multi-target recognition model performs noise reduction processing on the target image information and then extracts feature points by segmentation. The feature points are fused based on the layer space displacement perception mechanism, and a feature fusion set is output. The confidence of the target image information and the standard face image is calculated, and it is determined whether the confidence of the target image information and the standard face image meets the confidence threshold. If the confidence of the target image information and the standard face image meets the confidence threshold, it is determined that the target image information in the scene is successfully authenticated, and the target image information in the scene is entered to complete the education platform user authentication and identification.

[0006] Preferably, the method for normalizing the target image information specifically includes: Obtain target image information, process the target image information using a two-dimensional empirical mode decomposition algorithm, and generate a low-difference point set based on cardinality flip sampling; Among them, the base flip sampling converts the target image information into integer The exponential expansion of is: (1) is the input target image information, Cardinality expansion information representing target image information; The cardinality expansion information is sampled l times to generate a Hammersley sequence; The Hammersley sequence is represented as: (2) in, Indicates the number of sampling times, Represents the projection direction vector number; Calculate the average of the mean envelope in all projection directions to obtain a set of low-discrepancy points; (3) Obtain a low-difference point set, and perform grayscale normalization on the low-difference point set by combining histogram equalization and gamma correction to obtain a grayscale normalized set; Load the grayscale normalization set, combine it with the PP-HumanSeg algorithm, remove the background pigment in the grayscale normalization set, and realize the normalization processing of the target image information.

[0007] Preferably, the method for processing a standard face image based on different angles, brightness and noise factors specifically includes: Obtain a standard face image, randomly rotate the standard face image at a set rotation angle (-30°-30°), and mirror-flip the randomly rotated standard face image to generate a random angle set; Load a random angle set, adjust the brightness of the random angle set within a preset brightness range (10-150%) based on a multi-scale Retinex algorithm, and output the random angle set with adjusted brightness; Among them, the random angle set output is expressed as: (4) in, is the input representation of a random angle set, The lighting component representing the random angle set data, Represents the pixel value gain factor; Get the random angle set after brightness adjustment, and add preset proportions of salt and pepper noise and Gaussian noise to the random angle set to create a complex image set.

[0008] Preferably, the method of iteratively training a multi-target recognition model using a complex image set specifically comprises: The cascaded posture regression model is used as the initial model of the multi-target recognition model. The initial model consists of a shape estimation layer, a feature extraction layer, and a cascade regressor. The shape estimation layer is connected to the feature extraction layer, which is composed of the cascade regressor. The feature extraction layer includes three groups of convolutional layers, one group of pooling layers, one group of upsampling layers, and one group of feature fusion layers. Introduce a confusion matrix analysis module in the shape estimation layer, freeze the pooling layer in the feature extraction layer, and introduce a layer space displacement perception mechanism to replace the pooling layer; Load the complex image set, perform hybrid enhancement on the complex image set based on Mosaic and Mixup hybrid enhancement technology, obtain 40 groups of face posture images with an interval of 2, and divide the hybrid enhanced complex image set into a training set and a test set; Get the training set and set the initial model parameters, where the number of feature points of the initial model, the number of clustering iterations is 20, the number of random forest decision trees is 250, the feature point radius is selected as 2, and the pixel feature is 400-500; Taking the training set as input, the initial model is trained based on random forest local encoding and K-means clustering analysis until the initial model converges, and at least one set of initial models in the multi-view recognition mode is obtained; A test set is obtained, and the test set is used as input, and at least one set of initial models is used to perform posture evaluation and confidence evaluation on the test set to obtain a posture deflection angle and an image confidence; Preset the measurement standard threshold, calculate the model recognition accuracy of the initial model by combining the posture deflection angle and the image confidence, select the initial model whose model recognition accuracy meets the measurement standard threshold interval as the final multi-target recognition model, and output the converged multi-target recognition model; The model recognition accuracy is calculated by the following formula: (5) in, represents the model recognition accuracy, is the number of feature points, represents the attitude deflection angle, Represents the image confidence.

[0009] Preferably, the method of fusing feature points based on the layer space displacement perception mechanism and outputting a feature fusion set specifically includes: Taking the normalized target image information as input, the multi-target recognition model is executed. The shape estimation layer makes a preliminary estimate and judgment on the target image information based on the confusion matrix algorithm to determine whether the target image information is a living image. If the target image information is a living body image, the target image information is pushed to the feature extraction layer; The feature extraction layer obtains the target image information, introduces an equivalent weighted filter to perform low-pass filtering and noise reduction on the target image information, filters out the interference components of the target image information, and outputs a noise reduction information set; Obtain the denoising information set, segment and extract feature points after denoising the target image information in the feature extraction layer, use the domain classifier to extract the bounding box and facial feature information of the denoising information set, and perform ROI pooling with the feature map of the corresponding scale of the standard face image; Based on the layer space displacement perception mechanism, feature points are fused and processed, and a feature fusion set is output; Calculate the confidence of target image information and standard face image; Determine whether the confidence of the target image information and the standard face image meets the confidence threshold; Among them, the confidence of the target image information and the standard face image is calculated by the following formula: (9) in, Respectively represent the target image information and the fusion value of the face standard image feature, is the label confidence coefficient of the target image information; Wherein, the noise reduction information set is expressed as: (6) (7) (8) in, is the output representation of the denoised information set, represents the equivalent weighted filter, Represents the target image information input information, Indicates the number of times of filtering and removing impurities. is the amplitude response of the filter, represents the filter signal-to-noise ratio, represents the overlapping correlation coefficient, is the overlap proportionality constant.

[0010] On the other hand, the present invention also provides an online education platform user authentication system, the online education platform user authentication system specifically comprising: The data normalization module is used to collect the target image information in the authentication scene in real time, normalize the target image information, and obtain the normalized target image information; The recognition modeling module pre-collects standard face images based on the image acquisition device, builds an image database through standard face images, traverses the image database, extracts standard face images from the image database, processes standard face images based on different angles, brightness, and noise factors, creates a complex image set, combines the multi-layer spatial displacement perception mechanism and the cascade posture regression model to build a multi-target recognition model, uses the complex image set to iteratively train the multi-target recognition model, and outputs a converged multi-target recognition model; The face recognition module is used to execute the multi-target recognition model. The multi-target recognition model performs noise reduction processing on the target image information, then segments and extracts feature points, fuses the feature points based on the layer space displacement perception mechanism, outputs a feature fusion set, and calculates the confidence of the target image information and the standard face image; The authentication judgment module is used to judge whether the confidence of the target image information and the standard face image meets the confidence threshold. If the confidence of the target image information and the standard face image meets the confidence threshold, the authentication of the target image information in the scene is judged to be successful, and the target image information in the scene is entered to complete the education platform user authentication and identification.

[0011] Preferably, the data normalization module specifically includes: A mode decomposition unit is used to obtain target image information, process the target image information using a two-dimensional empirical mode decomposition algorithm, and generate a low-discrepancy point set based on cardinality flip sampling; A grayscale processing unit is used to obtain a low-difference point set, and normalize the grayscale of the low-difference point set by combining histogram equalization and gamma correction to obtain a grayscale normalized set; The background selection unit is used to load the grayscale normalization set, combine the PP-HumanSeg algorithm, remove the background pigment in the grayscale normalization set, and realize the normalization processing of the target image information.

[0012] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In the embodiment of the present invention, the problem that the background information distracts the model's attention and causes misidentification or missed identification can be overcome by normalizing the target image information. The background interference factors can be quickly removed by normalizing the target image information, so that the multi-target recognition model can be more focused on feature extraction of the face area, thereby improving the accuracy of recognition. At the same time, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model. The multi-target recognition model approximates the real face shape and feature point position by clustering analysis, and corrects, reduces noise and optimizes the results of the previous level, thereby improving the positioning accuracy of the feature points. The existing method overcomes the problem that the existing method uses frame-by-frame analysis of face images and can only simply process each frame independently, is sensitive to interference information, and cannot fully utilize the correlation and continuity between the previous and subsequent frames, resulting in the accuracy of the recognition results being limited.

[0013] In the embodiment of the present invention, two-dimensional empirical mode decomposition is performed on the target image information respectively, so as to generate a low-difference point set, and then extract facial features that are not affected by illumination. These features remain relatively stable under different illumination conditions, which can reduce the interference of illumination changes on face recognition and improve the accuracy and reliability of recognition. Then, the grayscale normalization processing of the low-difference point set is combined with histogram equalization and gamma correction, which can overcome the situation that some grayscale levels of the low-difference point set may be relatively concentrated. Histogram equalization can effectively widen the gap between these grayscale levels, thereby enhancing the overall contrast of the image, which makes the details in the face image clearer. Finally, the background pigment removal of the grayscale normalization concentration can highlight the main features of the face and reduce interference factors, thereby improving the robustness and efficiency of the multi-target recognition model.

[0014] In the embodiment of the present invention, a complex image set is created based on different angles, brightness, and noise factors, and a training image set with multiple angles, brightness, and noise factors is integrated, providing the model with comprehensive and rich learning materials, which helps the model to more accurately capture the key feature points and detail information of the face. In this way, the accuracy of the model in recognizing faces will be significantly improved, and at the same time, it can overcome the problems of differences in image quality, angle, and brightness that may be faced when the multi-target recognition model runs on different hardware devices, and also meet the needs of face recognition in strong light outdoors, dark light indoors, and during movement.

[0015] In an embodiment of the present invention, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model, and a confusion matrix analysis module is introduced into the multi-target recognition model, so that the changes of the face in different postures can be effectively processed. For example, when the face is in different postures such as sideways, looking up, and lowering the head, the multi-target recognition model can gradually correct the influence of the posture on the facial features, so that the model can more accurately extract the key features of the face, further improve the accuracy of recognition, and make the entire multi-target recognition model more robust under complex environmental factors. Whether it is a face image in the front or side, or a face image with expression changes or partial occlusion, the model can perform good recognition, which improves the application scope and reliability of face recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the implementation flow of the online education platform user authentication method provided by the present invention.

[0017] Figure 2 The invention shows a schematic diagram of the implementation process of the method for normalizing target image information.

[0018] Figure 3 The figure shows a schematic diagram of the implementation process of the method for processing standard face images based on different angles, brightness and noise factors.

[0019] Figure 4 The schematic diagram of the implementation process of the iterative training method for multi-target recognition model using complex image sets is shown.

[0020] Figure 5 The figure shows a schematic diagram of the implementation process of a method for fusing feature points based on a layer space displacement perception mechanism and outputting a feature fusion set.

[0021] Figure 6 It is a structural diagram of the online education platform user authentication system provided by the present invention. DETAILED DESCRIPTION

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0023] The existing methods use frame-by-frame analysis of facial images and can only simply process each frame independently. They are sensitive to interference information and cannot fully utilize the correlation and continuity between the previous and next frames, resulting in limited accuracy of the recognition results. To address the above problems, we propose an online education platform user authentication method and system. In short, when the online education platform user authentication method is executed, the target image information in the authentication scene is first collected in real time, the target image information is normalized to obtain the normalized target image information, and an image database is constructed through standard facial images. The standard facial images are processed based on different angles, brightness, and noise factors to create a complex image set. A multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model. The target image information is denoised by the multi-target recognition model and then segmented to extract feature points. The feature points are fused based on the layer spatial displacement perception mechanism to output a feature fusion set, and the confidence of the target image information and the standard facial image is calculated to determine whether the confidence of the target image information and the standard facial image meets the confidence threshold; if the confidence of the target image information and the standard facial image meets the confidence threshold, it is determined that the authentication of the target image information in the scene is successful, and the target image information in the scene is entered. In the embodiment of the present invention, the problem that the background information distracts the model's attention and causes misidentification or missed identification can be overcome by normalizing the target image information. The background interference factors can be quickly removed by normalizing the target image information, so that the multi-target recognition model can be more focused on feature extraction of the face area, thereby improving the accuracy of recognition. At the same time, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model. The multi-target recognition model approximates the real face shape and feature point position by clustering analysis, and corrects, reduces noise and optimizes the results of the previous level, thereby improving the positioning accuracy of the feature points. The existing method overcomes the problem that the existing method uses frame-by-frame analysis of face images and can only simply process each frame independently, is sensitive to interference information, and cannot fully utilize the correlation and continuity between the previous and subsequent frames, resulting in the accuracy of the recognition results being limited.

[0024] The embodiment of the present invention provides a method for authenticating users of an online education platform. Figure 1 The following is a schematic diagram of the implementation process of the online education platform user authentication method, which specifically includes: Step S10, collecting target image information in the authentication scene in real time, normalizing the target image information, and obtaining normalized target image information; It should be noted that the online education platform in the embodiment of the present invention includes but is not limited to a traffic platform, a vertical content platform, and a tool platform. The teaching mode of online education can be a recorded class, a live class, or a hybrid teaching platform. The target image information in the acquisition and authentication scene can be collected through a communicative mobile terminal, a mobile phone, a computer, a web page, and an attendance machine. For example, the image recognition technology of artificial intelligence is used to perform personnel authentication through a fingerprint machine and a face recognition machine, and the real-time acquisition and authentication scene through the web page can be used to track images captured by the camera in real time. At the same time, the data object being tracked can be a color or a human image. If the data object being tracked is a face image, the specific tracking detection target can also be set to be the eyes, nose, and mouth in the face image. When the target is detected to move or appear, the face recognition authentication instruction will be triggered.

[0025] Step S20, pre-collecting standard face images based on the image acquisition device, building an image database through the standard face images, traversing the image database, extracting standard face images from the image database, processing the standard face images based on different angles, brightness, and noise factors, creating a complex image set, combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model to build a multi-target recognition model, using the complex image set to iteratively train the multi-target recognition model, and outputting a converged multi-target recognition model; Step S30, taking the normalized target image information as input, executing the multi-target recognition model, the multi-target recognition model performs noise reduction processing on the target image information, segmenting and extracting feature points, fusing the feature points based on the layer space displacement perception mechanism, outputting a feature fusion set, and calculating the confidence of the target image information and the standard face image; Step S40, determining whether the confidence of the target image information and the standard face image meets the confidence threshold; It should be noted that the confidence threshold can be set to 0.98-1. The confidence threshold is used to comprehensively determine whether the face authentication is successful or not. It is a key parameter for determining whether two face images match. After the face image undergoes a series of processing processes such as feature extraction and comparison, a similarity score or probability value will be obtained. This value is the confidence level. If the confidence level is higher than the set threshold, the two faces are considered to be matched, that is, the recognition is successful; otherwise, it is considered not to match.

[0026] Step S50, if the confidence of the target image information and the standard face image meets the confidence threshold, it is determined that the authentication of the target image information in the scene is successful; If the confidence level of the target image information and the standard face image does not meet the confidence threshold, the education platform user authentication and recognition failure instruction is triggered, and the target image information is uploaded to the image database.

[0027] Step S60, input the target image information in the scene to complete the education platform user authentication and identification.

[0028] In the embodiment of the present invention, the problem that the background information distracts the model's attention and causes misidentification or missed identification can be overcome by normalizing the target image information. The background interference factors can be quickly removed by normalizing the target image information, so that the multi-target recognition model can be more focused on feature extraction of the face area, thereby improving the accuracy of recognition. At the same time, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model. The multi-target recognition model approximates the real face shape and feature point position by clustering analysis, and corrects, reduces noise and optimizes the results of the previous level, thereby improving the positioning accuracy of the feature points. The existing method overcomes the problem that the existing method uses frame-by-frame analysis of face images and can only simply process each frame independently, is sensitive to interference information, and cannot fully utilize the correlation and continuity between the previous and subsequent frames, resulting in the accuracy of the recognition results being limited.

[0029] The embodiment of the present invention provides a method for normalizing target image information. Figure 2 The following is a schematic diagram of the implementation process of a method for normalizing target image information. The method for normalizing target image information specifically includes: Step S101, obtaining target image information, processing the target image information using a two-dimensional empirical mode decomposition algorithm, and generating a low-discrepancy point set based on cardinality flip sampling; Among them, the base flip sampling converts the target image information into integer The exponential expansion of is: (1) is the input target image information, Cardinality expansion information representing target image information; The cardinality expansion information is sampled l times to generate a Hammersley sequence; The Hammersley sequence is represented as: (2) in, Indicates the number of sampling times, Represents the projection direction vector number; Calculate the average of the mean envelope in all projection directions to obtain a set of low-discrepancy points; (3) It should be noted that in formula (3), are the maximum and minimum values ​​of the Hammersley sequence respectively.

[0030] Step S102, obtaining a low-difference point set, and performing grayscale normalization processing on the low-difference point set by combining histogram equalization and gamma correction to obtain a grayscale normalized set; Step S103, loading the grayscale normalization set, combining with the PP-HumanSeg algorithm, removing the background pigment in the grayscale normalization set, and realizing normalization processing of the target image information.

[0031] In this embodiment, two-dimensional empirical mode decomposition is performed on the target image information through steps S101-S103, so as to generate a low-difference point set, and then extract facial features that are not affected by illumination. These features remain relatively stable under different illumination conditions, which can reduce the interference of illumination changes on face recognition and improve the accuracy and reliability of recognition. Then, the grayscale normalization of the low-difference point set is performed in combination with histogram equalization and gamma correction, which can overcome the situation that some grayscale levels are relatively concentrated in the low-difference point set. Histogram equalization can effectively widen the gap between these grayscale levels, thereby enhancing the overall contrast of the image, which makes the details in the face image clearer. Finally, background pigment removal in the grayscale normalization concentration can highlight the main features of the face and reduce interference factors, thereby improving the robustness and efficiency of the multi-target recognition model.

[0032] The embodiment of the present invention provides a method for processing a standard face image based on different angles, brightness, and noise factors. Figure 3 The following is a schematic diagram of the implementation process of a method for processing a standard face image based on different angles, brightness, and noise factors. The method for processing a standard face image based on different angles, brightness, and noise factors specifically includes: Step S201, obtaining a standard face image, randomly rotating the standard face image at a set rotation angle (-30°-30°), and mirror-flipping the randomly rotated standard face image to generate a random angle set; In this embodiment, the rotation angle (-30°-30°) is set to meet the recognition requirements of target image information acquired at different angles, while also helping to improve the generalization ability and robustness of the model.

[0033] At the same time, the standard face image is pre-collected based on the image acquisition device, which includes but is not limited to ordinary cameras, professional face acquisition cameras, 3D cameras, smart attendance machines, self-service terminals, and handheld 3D scanners. The image database constructed by the standard face image can be SQL Server, MySQL database, etc., and the database server is built using Oracle Database Link technology and database connection. Finally, the file server is used to provide file storage services for users.

[0034] Step S202, loading a random angle set, adjusting the brightness of the random angle set within a preset brightness range (10-150%) based on a multi-scale Retinex algorithm, and outputting the random angle set with adjusted brightness; Among them, the random angle set output is expressed as: (4) in, is the input representation of a random angle set, represents the illumination component of the random angle set data, represents a pixel value gain factor. In this embodiment, the pixel value gain factor may be 0.1-0.5; Step S203, obtaining a random angle set after brightness adjustment, and synchronously adding salt and pepper noise and Gaussian noise of preset proportions to the random angle set to create a complex image set.

[0035] In this embodiment, the robustness of the model to noise interference can be enhanced by synchronously adding preset proportions of salt and pepper noise and Gaussian noise to the random angle set. At the same time, in order to further improve the performance of the model, the color distortion, geometric transformation and generative adversarial network enhancement of the image set can also be performed when creating a complex image set.

[0036] In the embodiment of the present invention, a complex image set is created based on different angles, brightness, and noise factors, and a training image set with multiple angles, brightness, and noise factors is integrated, providing the model with comprehensive and rich learning materials, which helps the model to more accurately capture the key feature points and detail information of the face. In this way, the accuracy of the model in recognizing faces will be significantly improved, and at the same time, it can overcome the problems of differences in image quality, angle, and brightness that may be faced when the multi-target recognition model runs on different hardware devices, and also meet the needs of face recognition in strong light outdoors, dark light indoors, and during movement.

[0037] The embodiment of the present invention provides a method for iteratively training a multi-target recognition model using a complex image set. Figure 4 The following is a schematic diagram of the implementation process of the iterative training method for a multi-target recognition model using a complex image set. The method of iterative training for a multi-target recognition model using a complex image set specifically includes: Step S301, using a cascaded posture regression model as the initial model of the multi-target recognition model, the initial model consists of a shape estimation layer, a feature extraction layer, and a cascade regressor, the shape estimation layer is connected to the feature extraction layer, the feature extraction layer is composed of the cascade regressor, and the feature extraction layer includes three groups of convolutional layers, one group of pooling layers, one group of upsampling layers, and one group of feature fusion layers; It should be noted that the convolution kernel size of the convolution layer in the feature extraction layer is 3*3, the number of channels of the convolution layer is 128, the number of channels of the pooling layer is 256, and the number of channels of the upsampler is 512, the parameter = 5, and the number of channels of the feature fusion layer is 512.

[0038] Step S302, introducing a confusion matrix analysis module into the shape estimation layer, freezing the pooling layer in the feature extraction layer, and introducing a layer space displacement perception mechanism to replace the pooling layer; Step S303, loading a complex image set, performing hybrid enhancement on the complex image set based on Mosaic and Mixup hybrid enhancement technology, obtaining 40 groups of face posture images with an interval of 2, and dividing the hybrid enhanced complex image set into a training set and a test set; In this embodiment, the ratio of the training set to the test set may be 4:1 or 3:1, and the training set and the test set may be randomly allocated in a K-fold cross-validation manner.

[0039] Step S304, obtaining a training set and setting initial model parameters, wherein the number of feature points of the initial model, the number of clustering iterations is 20, the number of random forest decision trees is 250, the feature point radius is selected as 2, and the pixel feature is 400-500; Step S305, taking the training set as input, training the initial model based on random forest local coding and K-means clustering analysis until the initial model converges, and obtaining at least one set of initial models in a multi-view recognition mode; Step S306, obtaining a test set, taking the test set as input, and performing posture evaluation and confidence evaluation on the test set using at least one set of initial models to obtain a posture deflection angle and an image confidence; Step S307, preset a measurement standard threshold, and calculate the model recognition accuracy of the initial model in combination with the posture deflection angle and the image confidence; In this embodiment, the measurement standard threshold can be 0.05-0.055. If the model recognition accuracy of the initial model calculated by the posture deflection angle and the image confidence meets the measurement standard threshold, the corresponding initial model is set as the multi-target recognition model. If there are multiple initial models, the initial model with the highest model recognition accuracy is selected as the multi-target recognition model.

[0040] Step S308, selecting an initial model whose model recognition accuracy meets the measurement standard threshold interval as the final multi-target recognition model, and outputting a converged multi-target recognition model.

[0041] In this embodiment, the model recognition accuracy is calculated by the following formula: (5) in, represents the model recognition accuracy, is the number of feature points. In this embodiment, the feature points may be 5-10, including but not limited to the mouth, eyes, nose, ears, and forehead feature points of the face. represents the attitude deflection angle, Represents the image confidence.

[0042] In an embodiment of the present invention, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model, and a confusion matrix analysis module is introduced into the multi-target recognition model, so that the changes of the face in different postures can be effectively processed. For example, when the face is in different postures such as sideways, looking up, and lowering the head, the multi-target recognition model can gradually correct the influence of the posture on the facial features, so that the model can more accurately extract the key features of the face, further improve the accuracy of recognition, and make the entire multi-target recognition model more robust under complex environmental factors. Whether it is a face image in the front or side, or a face image with expression changes or partial occlusion, the model can perform good recognition, which improves the application scope and reliability of face recognition.

[0043] The embodiment of the present invention provides a method for fusing feature points based on a layer space displacement perception mechanism and outputting a feature fusion set. Figure 5 The schematic diagram of the implementation process of the method for fusing feature points based on the layer space displacement perception mechanism and outputting a feature fusion set is shown. The method for fusing feature points based on the layer space displacement perception mechanism and outputting a feature fusion set specifically includes: Step S401, taking the normalized target image information as input, executing the multi-target recognition model, and the shape estimation layer preliminarily estimates and determines the target image information based on the confusion matrix algorithm; Step S402, determining whether the target image information is a living body image; It should be noted that when the confusion matrix algorithm makes a preliminary estimate of the target image information, it can use SIFT (Scale Invariant Feature Transform) and HOG (Histogram of Oriented Gradients) methods to extract the features of the image, which can include color, texture, shape, edge, etc., and then construct a confusion matrix to predict whether each image is a living image or a non-living image. According to the real category label and the prediction result, the rows of the confusion matrix represent the actual category (living / non-living), and the columns represent the predicted category (living / non-living).

[0044] Step S403, if the target image information is a living body image, push the target image information to the feature extraction layer; Step S404: if the target image information is not a living body image, the face recognition authentication task is terminated.

[0045] Step S405, the feature extraction layer obtains the target image information, introduces an equivalent weighted filter to perform low-pass filtering and noise reduction processing on the target image information, filters out the interference components of the target image information, and outputs a noise reduction information set.

[0046] It should be noted that the noise reduction information set is expressed as: (6) (7) (8) in, is the output representation of the denoised information set, represents the equivalent weighted filter, Represents the target image information input information, Indicates the number of times of filtering and removing impurities. In this embodiment, the number of times of filtering and removing impurities can be 2-15. is the amplitude response of the filter, represents the filter signal-to-noise ratio, represents the overlapping correlation coefficient, is the overlap ratio constant. In this embodiment, the overlap ratio constant may be 0.1-0.9.

[0047] Step S406, obtaining a denoising information set, segmenting and extracting feature points after denoising the target image information at the feature extraction layer, extracting the bounding box and facial feature information of the denoising information set using a domain classifier, and performing ROI pooling with a feature map of a scale corresponding to a standard face image; Step S407, performing fusion processing on the feature points based on the layer space displacement perception mechanism, and outputting a feature fusion set; Step S408, calculating the confidence of the target image information and the standard face image; Step S409, determining whether the confidence of the target image information and the standard face image meets the confidence threshold; Among them, the confidence of the target image information and the standard face image is calculated by the following formula: (9) in, Respectively represent the target image information and the fusion value of the face standard image feature, is the label confidence coefficient of the target image information. In this embodiment, the label confidence coefficient can be evaluated by domain experts based on their experience. Experts can give a confidence value based on factors such as image quality and feature prominence. The label confidence coefficient is 0.1-1.

[0048] The embodiment of the present invention also provides an online education platform user authentication system. Figure 6The structure diagram of the online education platform user authentication system is shown, and the online education platform user authentication system specifically includes: The data normalization module 100 is used to collect target image information in the authentication scene in real time, normalize the target image information, and obtain normalized target image information; The recognition modeling module 200 pre-collects standard face images based on the image acquisition device, builds an image database through the standard face images, traverses the image database, extracts standard face images from the image database, processes the standard face images based on different angles, brightness, and noise factors, creates a complex image set, combines the multi-layer spatial displacement perception mechanism and the cascade posture regression model to build a multi-target recognition model, uses the complex image set to iteratively train the multi-target recognition model, and outputs a converged multi-target recognition model; The face recognition module 300 is used to execute a multi-target recognition model, which performs noise reduction processing on the target image information, then segments and extracts feature points, fuses the feature points based on a layer space displacement perception mechanism, outputs a feature fusion set, and calculates the confidence of the target image information and the standard face image; The authentication judgment module 400 is used to judge whether the confidence of the target image information and the standard face image meets the confidence threshold. If the confidence of the target image information and the standard face image meets the confidence threshold, it is judged that the authentication of the target image information in the scene is successful, and the target image information in the scene is entered to complete the education platform user authentication and identification.

[0049] In an embodiment of the present invention, an online education platform user authentication system is composed of a data normalization module 100, a recognition modeling module 200, a face recognition module 300, and an authentication judgment module 400. The data normalization module 100, the recognition modeling module 200, the face recognition module 300, and the authentication judgment module 400 can be connected and data interaction can be achieved by static linking, dynamic linking at loading time, and dynamic linking at runtime.

[0050] In this embodiment, the data normalization module 100 specifically includes: A mode decomposition unit 110 is used to obtain target image information, process the target image information using a two-dimensional empirical mode decomposition algorithm, and generate a low-discrepancy point set based on cardinality flip sampling; A grayscale processing unit 120 is used to obtain a low-difference point set, and perform grayscale normalization processing on the low-difference point set in combination with histogram equalization and gamma correction to obtain a grayscale normalized set; The background selection unit 130 is used to load the grayscale normalization set, and in combination with the PP-HumanSeg algorithm, remove the background pigment in the grayscale normalization set to achieve normalization processing of the target image information.

[0051] It should be noted that the online education platform user authentication system provided by the embodiment of the present invention corresponds to the above-mentioned online education platform user authentication method. The explanations, examples, beneficial effects and other parts of its relevant contents can refer to the corresponding contents in the online education platform user authentication system and will not be repeated here.

[0052] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program instructions, and the computer program instructions can be executed by a processor. When the computer program instructions are executed, the method of any of the above embodiments is implemented.

[0053] The computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0054] At the same time, an embodiment of the present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the method of any one of the above embodiments is implemented.

[0055] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the online education platform user authentication method in the embodiment of the present application. The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by the use of the online education platform user authentication method, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0056] In summary, the present invention provides a user authentication method and system for an online education platform. In an embodiment of the present invention, the problem of background information distracting the model's attention, resulting in misidentification or missed identification, can be overcome by normalizing the target image information. By normalizing the target image information, background interference factors can be quickly removed, so that the multi-target recognition model can be more focused on feature extraction of the face area, thereby improving recognition accuracy. At the same time, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model. The multi-target recognition model approximates the real face shape and feature point position by clustering analysis, and corrects, de-noises and optimizes the results of the previous level, thereby improving the positioning accuracy of the feature points. The existing method overcomes the problem that it can only simply process each frame independently by analyzing the face image frame by frame, is sensitive to interference information, and cannot fully utilize the correlation and continuity between the previous and subsequent frames, resulting in the accuracy of the recognition results being limited.

[0057] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0058] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. An online education platform user authentication method, characterized in that: The online education platform user authentication method comprises: Collect target image information in the authentication scene in real time, normalize the target image information, and obtain normalized target image information; Based on the image acquisition device, standard face images are pre-collected, an image database is constructed through standard face images, the image database is traversed, standard face images are extracted from the image database, standard face images are processed based on different angles, brightness, and noise factors, a complex image set is created, a multi-target recognition model is constructed by combining a multi-layer spatial displacement perception mechanism and a cascaded posture regression model, the multi-target recognition model is iteratively trained using a complex image set, and a converged multi-target recognition model is output; Taking the normalized target image information as input, the multi-target recognition model is executed. The multi-target recognition model performs noise reduction processing on the target image information and then extracts feature points by segmentation. The feature points are fused based on the layer space displacement perception mechanism, and a feature fusion set is output. The confidence of the target image information and the standard face image is calculated, and it is determined whether the confidence of the target image information and the standard face image meets the confidence threshold. If the confidence of the target image information and the standard face image meets the confidence threshold, it is determined that the target image information in the scene is successfully authenticated, and the target image information in the scene is entered to complete the education platform user authentication and identification.

2. The online education platform user authentication method according to claim 1, characterized in that: The method for normalizing target image information specifically includes: Obtain target image information, process the target image information using a two-dimensional empirical mode decomposition algorithm, and generate a low-difference point set based on cardinality flip sampling; Among them, the base flip sampling converts the target image information into integer The exponential expansion of is: （1） is the input target image information, Cardinality expansion information representing target image information; The cardinality expansion information is sampled l times to generate a Hammersley sequence; The Hammersley sequence is represented as: （2） in, Indicates the number of sampling times, Represents the projection direction vector number; Calculate the average of the mean envelope in all projection directions to obtain a set of low-discrepancy points; （3） Obtain a low-difference point set, and perform grayscale normalization on the low-difference point set by combining histogram equalization and gamma correction to obtain a grayscale normalized set; Load the grayscale normalization set, combine it with the PP-HumanSeg algorithm, remove the background pigment in the grayscale normalization set, and realize the normalization processing of the target image information.

3. The online education platform user authentication method according to claim 1, characterized in that: The method for processing a standard face image based on different angles, brightness, and noise factors specifically includes: Obtain a standard face image, randomly rotate the standard face image at a set rotation angle (-30°-30°), and mirror-flip the randomly rotated standard face image to generate a random angle set; Load a random angle set, adjust the brightness of the random angle set within a preset brightness range (10-150%) based on a multi-scale Retinex algorithm, and output the random angle set with adjusted brightness; Among them, the random angle set output is expressed as: （4） in, is the input representation of a random angle set, represents the illumination component of the random angle set data, Represents the pixel value gain factor; Get the random angle set after brightness adjustment, and add preset proportions of salt and pepper noise and Gaussian noise to the random angle set to create a complex image set.

4. The online education platform user authentication method according to claim 3, characterized in that: The method for iteratively training a multi-target recognition model using a complex image set specifically includes: The cascaded posture regression model is used as the initial model of the multi-target recognition model. The initial model consists of a shape estimation layer, a feature extraction layer, and a cascade regressor. The shape estimation layer is connected to the feature extraction layer, which is composed of the cascade regressor. The feature extraction layer includes three groups of convolutional layers, one group of pooling layers, one group of upsampling layers, and one group of feature fusion layers. Introduce a confusion matrix analysis module in the shape estimation layer, freeze the pooling layer in the feature extraction layer, and introduce a layer space displacement perception mechanism to replace the pooling layer; Load the complex image set, perform hybrid enhancement on the complex image set based on Mosaic and Mixup hybrid enhancement technology, obtain 40 groups of face posture images with an interval of 2, and divide the hybrid enhanced complex image set into a training set and a test set; Get the training set and set the initial model parameters, where the number of feature points of the initial model, the number of clustering iterations is 20, the number of random forest decision trees is 250, the feature point radius is selected as 2, and the pixel feature is 400-500; Taking the training set as input, the initial model is trained based on random forest local encoding and K-means clustering analysis until the initial model converges, and at least one set of initial models in the multi-view recognition mode is obtained; A test set is obtained, and the test set is used as input, and at least one set of initial models is used to perform posture evaluation and confidence evaluation on the test set to obtain a posture deflection angle and an image confidence; The measurement standard threshold is preset, and the model recognition accuracy of the initial model is calculated by combining the posture deflection angle and the image confidence. The initial model whose model recognition accuracy meets the measurement standard threshold interval is selected as the final multi-target recognition model, and the converged multi-target recognition model is output.

5. The online education platform user authentication method according to claim 4, characterized in that: The model recognition accuracy is calculated by the following formula: （5） in, represents the model recognition accuracy, is the number of feature points, represents the attitude deflection angle, Represents the image confidence.

6. The online education platform user authentication method according to claim 5, characterized in that: The method of fusing feature points based on the layer space displacement perception mechanism and outputting a feature fusion set specifically includes: Taking the normalized target image information as input, the multi-target recognition model is executed. The shape estimation layer makes a preliminary estimate and judgment on the target image information based on the confusion matrix algorithm to determine whether the target image information is a living image. If the target image information is a living body image, the target image information is pushed to the feature extraction layer; The feature extraction layer obtains the target image information, introduces an equivalent weighted filter to perform low-pass filtering and denoising on the target image information, filters out the interference components of the target image information, and outputs a denoised information set.

7. The online education platform user authentication method according to claim 6, characterized in that: The method of fusing feature points based on the layer space displacement perception mechanism and outputting a feature fusion set specifically includes: Obtain the denoising information set, segment and extract feature points after denoising the target image information in the feature extraction layer, use the domain classifier to extract the bounding box and facial feature information of the denoising information set, and perform ROI pooling with the feature map of the corresponding scale of the standard face image; Based on the layer space displacement perception mechanism, feature points are fused and processed, and a feature fusion set is output; Calculate the confidence of target image information and standard face image; Determine whether the confidence of the target image information and the standard face image meets the confidence threshold; Among them, the confidence of the target image information and the standard face image is calculated by the following formula: （9） in, Respectively represent the target image information and the fusion value of the standard face image features, is the label confidence coefficient of the target image information.

8. The online education platform user authentication method according to claim 6, characterized in that: The denoising information set is expressed as: （6） （7） （8） in, is the output representation of the denoised information set, represents the equivalent weighted filter, Represents the target image information input information, Indicates the number of times of filtering and removing impurities. is the amplitude response of the filter, represents the filter signal-to-noise ratio, represents the overlapping correlation coefficient, is the overlap proportionality constant.

9. An online education platform user authentication system, used to implement the online education platform user authentication method as described in any one of claims 1 to 8, characterized in that: The online education platform user authentication system specifically includes: The data normalization module is used to collect the target image information in the authentication scene in real time, normalize the target image information, and obtain the normalized target image information; The recognition modeling module pre-collects standard face images based on the image acquisition device, builds an image database through standard face images, traverses the image database, extracts standard face images from the image database, processes standard face images based on different angles, brightness, and noise factors, creates a complex image set, combines the multi-layer spatial displacement perception mechanism and the cascade posture regression model to build a multi-target recognition model, uses the complex image set to iteratively train the multi-target recognition model, and outputs a converged multi-target recognition model; The face recognition module is used to execute the multi-target recognition model. The multi-target recognition model performs noise reduction processing on the target image information, then segments and extracts feature points, fuses the feature points based on the layer space displacement perception mechanism, outputs a feature fusion set, and calculates the confidence of the target image information and the standard face image; The authentication judgment module is used to judge whether the confidence of the target image information and the standard face image meets the confidence threshold. If the confidence of the target image information and the standard face image meets the confidence threshold, the authentication of the target image information in the scene is judged to be successful, and the target image information in the scene is entered to complete the education platform user authentication and identification.

10. The online education platform user authentication system according to claim 9, characterized in that: The data normalization module specifically includes: A mode decomposition unit is used to obtain target image information, process the target image information using a two-dimensional empirical mode decomposition algorithm, and generate a low-discrepancy point set based on cardinality flip sampling; A grayscale processing unit is used to obtain a low-difference point set, and normalize the grayscale of the low-difference point set by combining histogram equalization and gamma correction to obtain a grayscale normalized set; The background selection unit is used to load the grayscale normalization set, combine the PP-HumanSeg algorithm, remove the background pigment in the grayscale normalization set, and realize the normalization processing of the target image information.

Images