Face access control recognition system and method based on image processing and storage medium

Abstract

The invention discloses a face access control recognition system and method based on image processing and a storage medium, belongs to the technical field of access control, and solves the problems that local features in images cannot be effectively captured when face feature values are obtained by adopting Mobilefacenet to calculate face sub-images, and the perception ability on image details is insufficient in the existing method. The method comprises the following steps: acquiring at least one group of access control acquisition data, pre-processing the access control acquisition data, executing a face recognition model, judging whether a pre-processing set is a living target object or not, if the pre-processing set is the living target object, performing recognition detection on the pre-processing set by the face recognition model, and outputting a detection result; according to the human face recognition model, through combination of distributed displacement convolution and Segnet network construction, local features in an image can be more effectively captured, so that the perception ability of the model to image details is enhanced, deep features and shallow features can be combined through jump connection, and the recognition accuracy of the human face recognition model is improved. And the adaptability of the model to complex backgrounds and different illumination conditions is enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of access control recognition, and in particular relates to a face access control recognition system, method and storage medium based on image processing. Background Art

[0002] With the increasing development of modern information technology, biometric recognition technology has been widely used in access control systems, and face recognition technology is one of the more common ones. Face recognition technology has application advantages such as fast, intuitive, and non-contact. Traditional face recognition algorithms are mainly based on model matching and feature matching. Both of the above algorithms may be affected by various factors such as light, posture, and expression, and their accuracy and real-time performance need to be improved.

[0003] Chinese patent CN109903433B discloses an access control system and access control method based on face recognition. The system includes: a camera, which is used to send a face image to a micro control unit after obtaining a first session key with an intelligent gateway; a micro control unit, which is used to calculate a face feature value based on the received face image; a face recognition command is sent to a security element; the security element is used to compare the face feature value in the received face recognition command with the feature value in the face database, obtain a face recognition result according to the comparison result, and return the face recognition result to the micro control unit; the micro control unit is also used to receive the face recognition result and send an access control operation command to the intelligent access control; the intelligent access control is used to decrypt the received access control operation command with the second session key after obtaining a second session key, and perform access control operations according to the obtained face recognition results. However, the existing method uses Mobilefacenet to calculate the face subgraph, and when obtaining the face feature value, it cannot effectively capture the local features in the image, and the perception ability of the image details is insufficient. In view of the above problems, we propose a face access control recognition system, method and storage medium based on image processing. Summary of the invention

[0004] The purpose of the present invention is to provide a face access control recognition system, method and storage medium based on image processing in view of the shortcomings of the prior art, thereby solving the problem that when the existing method is executed, Mobilefacenet is used to calculate the face sub-graph, and when the face feature value is obtained, the local features in the image cannot be effectively captured, and the perception ability of the image details is insufficient.

[0005] The present invention is implemented in this way: a face access control recognition method based on image processing, the face access control recognition method based on image processing specifically includes: Acquire at least one set of access control collection data, pre-process the access control collection data, and obtain a pre-processed set; The face recognition model of the improved Segnet network is constructed by combining distributed displacement convolution, and the standard image set in the access control database is retrieved. The standard image set is divided into training set, test set and verification set. The training set is used to iteratively train the face recognition model, and the converged face recognition model is output. Load the preprocessing set, use the preprocessing set as input, execute the face recognition model, and determine whether the preprocessing set is a living target. If the preprocessing set is a living target, the face recognition model will perform recognition detection on the preprocessing set and output the detection result; If the preprocessing set is not a living target object, a re-verification instruction is triggered to collect real-time face data in real time, pre-process the real-time face data, and determine whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; Obtain the test results, determine whether the test results exceed the preset result threshold, trigger the access control opening and closing command based on the preset result threshold, and turn on / off the access control system.

[0006] Preferably, the method for preprocessing access control collected data specifically includes: Load access control data and extract facial feature images from the access control data; Extract the feature points of nose, eyebrows, eyes, mouth and ears in the facial feature image, and calculate the comprehensive grayscale value of the feature points in the facial feature image based on the Eigenfaces algorithm; Among them, the comprehensive gray value of the feature point is calculated by the following formula: (1) in, Represents the comprehensive grayscale value of the feature points of the facial feature image, Indicates the current feature point The gray value of Indicates the coordinate value of the current feature point in the face feature image, is the number of feature points; Integrate the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, perform equalization processing on the facial feature image based on the cumulative distribution function, and determine the pixel distribution range of the facial feature image; The pixel distribution range is calculated by the following formula: (2) in, represents the pixel distribution range, Represents the comprehensive grayscale value of the feature points of the facial feature image, is the controllable distribution range of pixels, represents the image recognition distance, is the distance correction factor, Indicates the frequency of image orientation recognition; Obtaining the pixel distribution range of the facial feature image, and judging whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold, and if it meets the preset range threshold, retaining the facial feature image after equalization processing; If it does not meet the preset range threshold, the facial feature image after equalization processing is deleted; At least one group of facial feature images that meet a preset range threshold is integrated, and the facial feature images are set as a preprocessing set.

[0007] Preferably, the method of iteratively training a face recognition model using a training set specifically includes: The Segnet network is used as the initial model of the face recognition model, wherein the initial model includes an encoder and a decoder, the encoder includes five groups of convolution modules, and each group of the convolution modules includes three groups of convolution layers and one group of BN layers, the decoder includes three groups of decoding modules, and each group of the decoding modules includes three groups of upsampling layers, convolution layers, and one group of BN layers; The feature classifier of FaceLivenessNet is introduced into the initial model, and the feature discriminator is used as the liveness discriminator. The liveness discriminator is placed in front of the encoder and connected to the encoder. Freeze the convolutional layers in the decoding module, replace them with distributed shifted convolutional structures, and replace the BN layers in the decoding module with cascaded Adaboost modules; Initialize and set the recognition node control indicators and hyperparameters of the feature classifier, encoder, and decoder in the initial model, introduce the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network, and adjust the position of the recognition node; Conduct ablation tests on feature classifiers, encoders, and decoders to complete the construction of the initial model; Get the training set, use the training set as input, set the training rounds, iteratively train the initial model, use forward propagation to calculate the loss value, update the model hyperparameters based on the backpropagation algorithm, and after each training, use the validation set to verify the performance of the initial model until the initial model converges; Get the test set, use the test set as input, execute the converged initial model, and get the model test results; Based on the preset model accuracy, verify whether the model test result exceeds the preset model accuracy. If it exceeds the preset model accuracy, output the trained face recognition model.

[0008] Preferably, the method of introducing the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network specifically includes: Obtain the decoded feature map of the decoder, and introduce the SimAM attention mechanism into the pixel-level classification layer to infer the 3D attention weights of the facial feature points nose, eyebrows, eyes, mouth, and ears in the decoded feature map; The 3D attention weight calculation formula is as follows: (3) in, is the 3D attention weight of the feature point, represents the number of pixels in the decoded feature map, represents the total value of the decoded feature map phase map, is the initial weight of the feature point, Represents the attention coefficient of SimAM’s attention mechanism; (4) The energy function of the neurons in the pixel-level classification layer is defined based on the 3D attention weights of the feature points, and the mean and variance of the energy function are calculated through the energy function of the neurons; The energy function is defined as: (5) in, represents the number of neurons in the pixel-level classification layer, represents the activation function of the pixel-level classification layer; (6) represents the attention weight matrix of the decoded feature map, is the activation function hyperparameter, Represents the bias term of the activation function; Combined with the mean and variance of the energy function, the improved vector machine is used to establish the feature recognition space of the neurons in the pixel-level classification layer, and the difference vector of face feature recognition in the space is calculated; (7) in, is the vector calculation result, represents the output value of the energy function, represents the mean value of the energy function, represents the variance of the energy function; Obtain the vector calculation results and use them to comprehensively define the pixel-level classification layer of the Segnet network.

[0009] Preferably, the method of executing the face recognition model to determine whether the preprocessed set is a living target object specifically includes: Get the preprocessing set, and perform hybrid enhancement on the preprocessing set based on Mosaic+Mixup to obtain the image enhancement set; The image enhancement set is loaded, and the feature discriminator extracts the interactive feedback of the image enhancement set based on the FaceLivenessNet algorithm. The interactive feedback includes pixel motion mode, thermal imaging information of facial feature points, and RDB image information. Obtain interactive feedback of the image enhancement set and calculate the significance level of the interactive feedback based on principal component analysis; (8) in, represents the significance level of interactive feedback, They represent the weight coefficients of pixel motion mode, facial feature point thermal imaging information, and RDB image information in interactive feedback, respectively. is the number of samples in the image enhancement set, They represent pixel motion mode, facial feature point thermal imaging information, and RDB image information input values ​​respectively; A liveness significance threshold is preset to determine whether the significance level of the interactive feedback exceeds the liveness significance threshold. If it exceeds the liveness significance threshold, the preprocessing set is determined to be a liveness target.

[0010] Preferably, the method for the face recognition model to perform recognition detection on the preprocessing set specifically includes: The encoder obtains the preprocessing set, and the convolution module in the encoder performs a first-level convolution process on the preprocessing set to obtain a first-level convolution result, wherein the encoding convolution result extracts edges, lines, and angles in facial features; Obtain the first-level convolution result. The convolution module constructs a facial feature map based on the first-level convolution result, supplements the facial feature map with details based on the preset number of zero-padding layers, and outputs the facial feature map with the details supplemented. Load the facial feature map, and the convolution module performs secondary convolution on the facial feature map to increase the hole receptive field of the facial feature map and output the secondary convolution result; Obtain the secondary convolution result, and the decoding module performs feature fusion on the secondary convolution result to obtain a feature fusion set; Load the feature fusion set, and build the initial decoding feature graph based on the feature fusion set; The cascaded Adaboost module is used to process the initial decoding feature graph, the deviation of the identified initial decoding feature graph is corrected for secondary processing, and the decoding feature graph and graph confidence are output; Calculate the detection result value of the decoded feature graph based on the graph confidence, and output the detection result; The test result value is calculated by the following formula: (9) in, is the test result value, is the vector calculation result, Represents the graph confidence of the decoded feature map.

[0011] On the other hand, the present invention also provides a face access control recognition system based on image processing, and the face access control recognition system based on image processing specifically includes: A data collection module, used to obtain at least one set of access control collection data, pre-process the access control collection data, and obtain a pre-processed set; The model building module combines distributed displacement convolution to build an improved Segnet network face recognition model, retrieves the standard image set from the access control database, divides the standard image set into training set, test set and validation set, uses the training set to iteratively train the face recognition model, and outputs a converged face recognition model; The recognition and detection module loads the preprocessing set, takes the preprocessing set as input, executes the face recognition model, and determines whether the preprocessing set is a living target. If the preprocessing set is a living target, the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The secondary verification module is used to obtain the judgment result of whether the preprocessing set is a living target object. If the preprocessing set is not a living target object, a re-verification instruction is triggered to collect real-time face data in real time, preprocess the real-time face data, and judge whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The access control module is used to obtain the detection results, determine whether the detection results exceed the preset result threshold, trigger the access control opening and closing instructions based on the preset result threshold, and open / close the access control system.

[0012] Preferably, the data acquisition module specifically includes: A feature extraction unit is used to load access control data and extract facial feature images from the access control data; A comprehensive grayscale calculation unit is used to extract the feature points of the nose, eyebrows, eyes, mouth, and ears in the facial feature image, and calculate the comprehensive grayscale value of the feature points in the facial feature image based on the Eigenfaces algorithm; An equalization processing unit, used for integrating the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, performing equalization processing on the facial feature image based on the cumulative distribution function, and determining the pixel distribution range of the facial feature image; The preprocessing set output unit is used to obtain the pixel distribution range of the facial feature image, and determine whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold. If it meets the preset range threshold, the facial feature image after equalization processing is retained; if it does not meet the preset range threshold, the facial feature image after equalization processing is deleted, and at least one group of facial feature images that meet the preset range threshold are integrated, and the facial feature images are set as the preprocessing set.

[0013] The present invention also provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed, the face access control recognition method based on image processing is implemented.

[0014] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In an embodiment of the present invention, a face access control recognition method based on image processing is provided. By extracting the feature points of the nose, eyebrows, eyes, mouth, and ears in the face feature image, the comprehensive grayscale value of the feature points is calculated, so that the face recognition model can quickly detect and identify the access control collected data. At the same time, the face recognition model can more effectively capture the local features in the image by combining distributed displacement convolution and Segnet network construction, thereby enhancing the model's perception of image details, and can also combine deep features with shallow features through jump connections, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and overcoming the existing method that uses Mobilefacenet to calculate face subgraphs and obtains face feature values. The problem that the local features in the image cannot be effectively captured and the perception of image details is insufficient.

[0015] In an embodiment of the present invention, when recognizing an image, the comprehensive grayscale value of feature points in a facial feature image is calculated based on an Eigenfaces algorithm, and the facial feature image is equalized based on a cumulative distribution function, so that pixels originally concentrated in certain grayscale ranges are more evenly distributed within the grayscale range of the entire facial feature image, so that the contrast of the image can be significantly enhanced, and the details of the facial features can be highlighted. In addition, preprocessing of access control collected data in combination with the Eigenfaces algorithm and the cumulative distribution function can also improve the performance of a facial recognition model, ensure that the facial recognition model is more likely to determine a suitable threshold for segmentation, and thus improve the accuracy and reliability of facial recognition model detection.

[0016] In an embodiment of the present invention, a face recognition model and a training method for the model are provided. The face recognition model is based on a Segnet network and a distributed displacement convolution, and introduces a feature classifier of FaceLivenessNet, so as to realize the simultaneous detection of living target objects and face recognition detection, and introduces an attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network, so as to combine deep features with shallow features, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and the distributed displacement convolution and the Segnet network can be combined with the attention mechanism to form an integrated learning system, thereby further improving the accuracy and robustness of face recognition.

[0017] In the embodiment of the present invention, multimodal fusion of living object detection is achieved by combining pixel motion patterns in image enhancement, thermal imaging information of facial feature points, and RDB image information. By utilizing the advantages of various modalities in different environments and compensating for each other's shortcomings, the impact of abnormalities or errors in individual modal data on the entire detection system is reduced, thereby improving the robustness of the face recognition model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the implementation flow of the face access control recognition method based on image processing provided by the present invention.

[0019] Figure 2 A schematic diagram of the implementation flow of the access control data preprocessing method is shown.

[0020] Figure 3 A schematic diagram of the implementation process of the method for iteratively training a face recognition model using a training set is shown.

[0021] Figure 4 A schematic diagram of the implementation process of the method for introducing the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network is shown.

[0022] Figure 5 A schematic diagram of the implementation flow of the method for executing the face recognition model and determining whether the preprocessing set is a living target object is shown.

[0023] Figure 6 A schematic diagram of the implementation flow of the face recognition model for the recognition detection method of the preprocessing set is shown.

[0024] Figure 7 It is a structural schematic diagram of the face access control recognition system based on image processing provided by the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The existing method uses Mobilefacenet to calculate the face subgraph, and when obtaining the face feature value, it cannot effectively capture the local features in the image, and the perception ability of the image details is insufficient. To address the above problems, we propose a face access control recognition system, method and storage medium based on image processing. In short, when the method is executed, at least one set of access control collection data is first obtained, the access control collection data is preprocessed, and at the same time, a face recognition model of the improved Segnet network is constructed in combination with distributed displacement convolution, and then the preprocessing set is loaded, and the preprocessing set is used as input to execute the face recognition model to determine whether the preprocessing set is a living target. If the preprocessing set is a living target, the face recognition model identifies and detects the preprocessing set and outputs the detection result. In an embodiment of the present invention, a face access control recognition method based on image processing is provided. By extracting the feature points of the nose, eyebrows, eyes, mouth, and ears in the face feature image, the comprehensive grayscale value of the feature points is calculated, so that the face recognition model can quickly detect and identify the access control collected data. At the same time, the face recognition model can more effectively capture the local features in the image by combining distributed displacement convolution and Segnet network construction, thereby enhancing the model's perception of image details, and can also combine deep features with shallow features through jump connections, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and overcoming the existing method that uses Mobilefacenet to calculate face subgraphs and obtains face feature values. The problem that the local features in the image cannot be effectively captured and the perception of image details is insufficient.

[0028] The embodiment of the present invention provides a face access control recognition method based on image processing. Figure 1The figure shows a schematic diagram of the implementation process of the face access control recognition method based on image processing. The face access control recognition method based on image processing specifically includes: Step S10, obtaining at least one set of access control collected data, preprocessing the access control collected data, and obtaining a preprocessed set; It should be noted that the access control data is obtained through sensors built into the access control system. The access control data includes but is not limited to images, videos, sounds, and fingerprint data, and the sensors include but are not limited to infrared cameras, RGB cameras, optical fingerprint sensors, and sound collection sensors.

[0029] The access control system is composed of front-end hardware equipment (camera, display, access control lock, fingerprint reader), and the access control system can be vertical or wall-mounted.

[0030] Step S20, constructing a face recognition model of an improved Segnet network in combination with distributed displacement convolution, retrieving a standard image set from the access control database, dividing the standard image set into a training set, a test set, and a validation set, iteratively training the face recognition model using the training set, and outputting a converged face recognition model; It should be noted that the data volume ratio of the samples in the training set, test set, and validation set is 3:1:1, and the access control database is stored in a face access control recognition system based on image processing, and at least one set of access control data directories is set up in the system. Each folder in the directory is named after the name, and the image parameter specifications in the access control data directory are consistent. When a picture with the same name is entered into the database, the original directory data will be automatically overwritten.

[0031] Step S30, loading the preprocessing set, taking the preprocessing set as input, executing the face recognition model, and determining whether the preprocessing set is a living target object; Step S40, if the preprocessed set is a living target object, the face recognition model performs recognition detection on the preprocessed set and outputs the detection result; Step S50, if the preprocessing set is not a living target object, trigger a re-verification instruction, collect real-time face data in real time, pre-process the real-time face data, and determine whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set, outputs the detection result, and executes step S60; It should be noted that the real-time facial data collected in real time is when it is determined that the first facial recognition is not a living target, the secondary collection instruction is triggered, and the access control system re-enters the collected real-time facial data through voice prompts, and the preprocessing method of the real-time facial data is the same as the method of collecting access control data.

[0032] If the real-time face data is a living target, the real-time face data detection result is fed back, the door is not opened, and the face recognition task is ended; Step S60, obtaining the detection result, determining whether the detection result exceeds a preset result threshold, triggering a door opening and closing instruction based on the preset result threshold, and turning on / off the door control system.

[0033] In this embodiment, the preset result threshold can be set to 0.9-1, and when the detection result is greater than or equal to the result threshold, the access control system unlocks the access control lock.

[0034] In an embodiment of the present invention, a face access control recognition method based on image processing is provided. By extracting the feature points of the nose, eyebrows, eyes, mouth, and ears in the face feature image, the comprehensive grayscale value of the feature points is calculated, so that the face recognition model can quickly detect and identify the access control collected data. At the same time, the face recognition model can more effectively capture the local features in the image by combining distributed displacement convolution and Segnet network construction, thereby enhancing the model's perception of image details, and can also combine deep features with shallow features through jump connections, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and overcoming the existing method that uses Mobilefacenet to calculate face subgraphs and obtains face feature values. The problem that the local features in the image cannot be effectively captured and the perception of image details is insufficient.

[0035] The embodiment of the present invention provides a method for preprocessing access control collected data. Figure 2 The schematic diagram of the implementation process of the method for preprocessing access control data is shown. The method for preprocessing access control data specifically includes: Step S101, loading access control data, and extracting facial feature images from the access control data; Step S102, extracting the feature points of the nose, eyebrows, eyes, mouth, and ears in the facial feature image, and calculating the comprehensive grayscale values ​​of the feature points in the facial feature image based on the Eigenfaces algorithm; Among them, the comprehensive gray value of the feature point is calculated by the following formula: (1) in, Represents the comprehensive grayscale value of the feature points of the facial feature image, Indicates the current feature point The gray value of Indicates the coordinate value of the current feature point in the face feature image, is the number of feature points. In this embodiment, the number of feature points is 5; Step S103, integrating the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, performing equalization processing on the facial feature image based on the cumulative distribution function, and determining the pixel distribution range of the facial feature image; It should be noted that when equalization processing is performed on a facial feature image based on the cumulative distribution function, the histogram of the facial feature image is first calculated. For a color image, the three channels (red, green, and blue) can be processed separately. Then, based on the cumulative distribution function, the sum of the occurrence probabilities of all pixels under a certain grayscale value is calculated. Then, the equalization formula is used to map the pixel values ​​of the original image, and finally, the images are recombined to achieve equalization processing of the facial feature image.

[0036] The pixel distribution range is calculated by the following formula: (2) in, represents the pixel distribution range, Represents the comprehensive grayscale value of the feature points of the facial feature image, is the controllable distribution range of pixels, represents the image recognition distance, is the distance correction factor, Indicates the frequency of image orientation recognition. In this embodiment, the frequency of image orientation recognition is 2-15; Step S104, obtaining the pixel distribution range of the facial feature image, and determining whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold; Step S105, if it meets the preset range threshold, retain the facial feature image after equalization processing; Step S106, if it does not meet the preset range threshold, delete the facial feature image after equalization processing; Step S107, integrating at least one group of facial feature images that meet a preset range threshold, and setting the facial feature images as a pre-processing set.

[0037] In an embodiment of the present invention, when recognizing an image, the comprehensive grayscale value of feature points in a facial feature image is calculated based on an Eigenfaces algorithm, and the facial feature image is equalized based on a cumulative distribution function, so that pixels originally concentrated in certain grayscale ranges are more evenly distributed within the grayscale range of the entire facial feature image, so that the contrast of the image can be significantly enhanced, and the details of the facial features can be highlighted. In addition, preprocessing of access control collected data in combination with the Eigenfaces algorithm and the cumulative distribution function can also improve the performance of a facial recognition model, ensure that the facial recognition model is more likely to determine a suitable threshold for segmentation, and thus improve the accuracy and reliability of facial recognition model detection.

[0038] The embodiment of the present invention provides a method for iteratively training a face recognition model using a training set. Figure 3 The following is a schematic diagram of the implementation process of the method for iteratively training a face recognition model using a training set. The method for iteratively training a face recognition model using a training set specifically includes: Step S201, using the Segnet network as the initial model of the face recognition model, wherein the initial model includes an encoder and a decoder, the encoder includes five groups of convolution modules, and each group of the convolution modules includes three groups of convolution layers and one group of BN layers, the decoder includes three groups of decoding modules, and each group of the decoding modules includes three groups of upsampling layers, convolution layers, and one group of BN layers; It should be noted that the convolution kernel size of the three groups of convolution layers in the convolution module is 3*3, and the convolution layer contains 128 neurons, and the activation function of the convolution module can be a RELU activation function.

[0039] Step S202, introducing the feature classifier of FaceLivenessNet into the initial model, using the feature discriminator as the liveness discriminator, placing the liveness discriminator in front of the encoder, and connecting the liveness discriminator to the encoder; Step S203, freezing the convolutional layer in the decoding module, replacing the convolutional layer with a distributed shifted convolutional structure, and replacing the BN layer in the decoding module with a cascaded Adaboost module; Step S204, initializing and setting the recognition node control indicators and hyperparameters of the feature classifier, encoder, and decoder in the initial model, introducing the attention mechanism to comprehensively define the Segnet network pixel-level classification layer, and adjusting the recognition node position; Step S205, performing ablation tests on the feature classifier, encoder, and decoder to complete the construction of the initial model; In this embodiment, when performing ablation tests, only one component in the feature classifier, encoder, and decoder is changed each time, so that the impact of each component on the model performance can be accurately determined. At the same time, the training process and results of each test should be recorded for subsequent analysis and comparison. This embodiment selects loss value and running time as evaluation indicators to ensure the accuracy and reliability of the test results.

[0040] Step S206, obtain a training set, use the training set as input, set training rounds, iteratively train the initial model, use forward propagation to calculate the loss value, update the model hyperparameters based on the back propagation algorithm, and after each training, use the validation set to verify the performance of the initial model until the initial model converges; in this embodiment, the training rounds can be 200-1000 times.

[0041] Step S207, obtaining a test set, taking the test set as input, executing the converged initial model, and obtaining a model test result; Step S208, verifying whether the model test result exceeds the preset model accuracy based on the preset model accuracy; Step S209: If the model accuracy exceeds the preset value, the trained face recognition model is output.

[0042] If the preset model accuracy is not exceeded, return to step S206 to continue iterative training of the model.

[0043] In this embodiment, the preset model accuracy may be 0.9-0.98.

[0044] In an embodiment of the present invention, a face recognition model and a training method for the model are provided. The face recognition model is based on a Segnet network and a distributed displacement convolution, and introduces a feature classifier of FaceLivenessNet, so as to realize the simultaneous detection of living target objects and face recognition detection, and introduces an attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network, so as to combine deep features with shallow features, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and the distributed displacement convolution and the Segnet network can be combined with the attention mechanism to form an integrated learning system, thereby further improving the accuracy and robustness of face recognition.

[0045] The embodiment of the present invention provides a method for introducing an attention mechanism to comprehensively define a pixel-level classification layer of a Segnet network. Figure 4 The schematic diagram of the implementation process of the method for introducing the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network is shown. The method for introducing the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network specifically includes: Step S301, obtain the decoded feature map of the decoder, and introduce the SimAM attention mechanism into the pixel-level classification layer to infer the 3D attention weights of the facial feature points nose, eyebrows, eyes, mouth, and ears in the decoded feature map; It should be noted that the attention weights determined by the attention mechanism can provide guidance for 3D modeling, allowing the model to pay more attention to the accurate position and shape of key feature points when reconstructing faces, thereby generating a more realistic and detailed 3D face model.

[0046] The 3D attention weight calculation formula is as follows: (3) in, is the 3D attention weight of the feature point, represents the number of pixels in the decoded feature map, represents the total value of the decoded feature map phase map, is the initial weight of the feature point, represents the attention coefficient of the SimAM attention mechanism. In this embodiment, the initial weight of the feature point can be set based on principal component analysis, linear component analysis, and expert consultation method; (4) Step S302, defining the energy function of the neurons in the pixel-level classification layer based on the 3D attention weights of the feature points, and calculating the mean and variance of the energy function through the energy function of the neurons; The energy function is defined as: (5) in, represents the number of neurons in the pixel-level classification layer, represents the activation function of the pixel-level classification layer; (6) represents the attention weight matrix of the decoded feature map, is the activation function hyperparameter. In this embodiment, the activation function hyperparameter may be 0.002-0.005. Represents the bias term of the activation function; Step S303, combining the mean and variance of the energy function, using the improved vector machine to establish a feature recognition space of the neurons in the pixel-level classification layer, and calculating the difference vector of face feature recognition in the space; (7) in, is the vector calculation result, represents the output value of the energy function, represents the mean value of the energy function, represents the variance of the energy function; Step S304, obtaining vector calculation results, and comprehensively defining the Segnet network pixel-level classification layer based on the vector calculation results.

[0047] It should be noted that in 3D face modeling, complex background scenes may be encountered. The vector calculation results can help the SegNet network better distinguish between foreground faces and backgrounds, improve the accuracy of pixel-level classification, and thus provide a cleaner data basis for subsequent 3D modeling. At the same time, vector calculation can overcome the limitations of a single feature to a certain extent, comprehensively consider multiple factors, and make the classification results more stable and reliable.

[0048] The embodiment of the present invention provides a method for executing a face recognition model to determine whether a preprocessing set is a living target object. Figure 5The schematic diagram of the implementation flow of the method for executing the face recognition model and determining whether the preprocessing set is a living target object is shown. The method for executing the face recognition model and determining whether the preprocessing set is a living target object specifically includes: Step S401, obtaining a preprocessing set, and performing hybrid enhancement on the preprocessing set based on Mosaic+Mixup to obtain an image enhancement set; Step S402, loading the image enhancement set, and extracting interactive feedback of the image enhancement set by the feature discriminator based on the FaceLivenessNet algorithm, wherein the interactive feedback includes pixel motion mode, thermal imaging information of facial feature points, and RDB image information; It should be noted that interactive feedback refers to establishing an interactive index with the image enhancement set. The image enhancement set is based on the pixel motion pattern, thermal imaging information of facial feature points, and RDB image information fed back by the interactive index. The pixel motion pattern is obtained by analyzing the video sequence using the optical flow method, while the thermal imaging information of facial feature points is obtained through an infrared camera, and the RDB image information can be collected through an RDB camera.

[0049] Step S403, obtaining interactive feedback of the image enhancement set, and calculating the significance level of the interactive feedback based on principal component analysis; (8) in, represents the significance level of interactive feedback, They represent the weight coefficients of pixel motion mode, facial feature point thermal imaging information, and RDB image information in interactive feedback, respectively. is the number of samples in the image enhancement set, They represent pixel motion mode, facial feature point thermal imaging information, and RDB image information input values ​​respectively; Step S404: preset a living body significance threshold, determine whether the significance level of the interactive feedback exceeds the living body significance threshold, and if it exceeds the living body significance threshold, determine that the preprocessed set is a living body target.

[0050] In this embodiment, the living body saliency threshold may be set to 0.8-0.85.

[0051] In the embodiment of the present invention, multimodal fusion of living object detection is achieved by combining pixel motion patterns in image enhancement, thermal imaging information of facial feature points, and RDB image information. By utilizing the advantages of various modalities in different environments and compensating for each other's shortcomings, the impact of abnormalities or errors in individual modal data on the entire detection system is reduced, thereby improving the robustness of the face recognition model.

[0052] The embodiment of the present invention provides a method for a face recognition model to perform recognition detection on a preprocessing set. Figure 6The figure shows a schematic diagram of the implementation process of the face recognition model for the recognition detection method of the preprocessing set. The method of the face recognition model for the recognition detection of the preprocessing set specifically includes: Step S501, the encoder obtains a preprocessing set, and the convolution module in the encoder performs a first-level convolution process on the preprocessing set to obtain a first-level convolution result, wherein the encoding convolution result extracts edges, lines, and angles in facial features; Step S502, obtaining the first-level convolution result, the convolution module constructs a facial feature map based on the first-level convolution result, supplements the facial feature map with details based on a preset number of zero-padding layers, and outputs the facial feature map with the details supplemented; Step S503, loading the facial feature map, the convolution module performs secondary convolution on the facial feature map, increases the hole receptive field of the facial feature map, and outputs the secondary convolution result.

[0053] Step S504, obtaining the secondary convolution result, and the decoding module performs feature fusion on the secondary convolution result to obtain a feature fusion set; Step S505, loading the feature fusion set, and constructing a decoding feature initial graph based on the feature fusion set; Step S506, using a cascaded Adaboost module to process the initial decoding feature graph, performing secondary correction processing on the identified initial decoding feature graph deviation, and outputting the decoding feature graph and the graph confidence; Step S507, calculating the detection result value of the decoded feature graph based on the graph confidence, and outputting the detection result; The test result value is calculated by the following formula: (9) in, is the test result value, is the vector calculation result, Represents the graph confidence of the decoded feature map.

[0054] It should be noted that the present embodiment uses the cascaded Adaboost modules to process the initial decoding feature graph, which can correct the initial decoding feature graph, thereby avoiding recognition errors to the greatest extent and ensuring the accuracy and stability of recognition.

[0055] The embodiment of the present invention provides a face access control recognition system based on image processing. Figure 7 The structure diagram of the face access control recognition system based on image processing is shown. The face access control recognition system based on image processing specifically includes: The data collection module 100 is used to obtain at least one set of access control collection data, pre-process the access control collection data, and obtain a pre-processed set; The model building module 200 combines the distributed displacement convolution to build an improved Segnet network face recognition model, retrieves a standard image set from the access control database, divides the standard image set into a training set, a test set, and a validation set, uses the training set to iteratively train the face recognition model, and outputs a converged face recognition model; The recognition and detection module 300 loads the preprocessing set, takes the preprocessing set as input, executes the face recognition model, and determines whether the preprocessing set is a living target object. If the preprocessing set is a living target object, the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The secondary verification module 400 is used to obtain the judgment result of whether the preprocessing set is a living target object. If the preprocessing set is not a living target object, a re-verification instruction is triggered to collect real-time face data in real time, pre-process the real-time face data, and judge whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The access control module 500 is used to obtain the detection result, determine whether the detection result exceeds a preset result threshold, trigger the access control opening and closing instruction based on the preset result threshold, and open / close the access control system.

[0056] It should be noted that it is understandable that the face access control recognition system based on image processing provided by the embodiment of the present invention corresponds to the face access control recognition method based on image processing, and the explanation, examples, beneficial effects and other parts of the relevant contents can refer to the corresponding contents in the face access control recognition method based on image processing, which will not be repeated here. The data acquisition module 100, the model building module 200, the recognition detection module 300, the secondary verification module 400, the access control module 500 and the access control database are connected by Bluetooth, DTU or communication interaction.

[0057] In this embodiment, the data acquisition module 100 specifically includes: The feature extraction unit 110 is used to load the access control collected data and extract the facial feature image in the access control collected data; The comprehensive grayscale calculation unit 120 is used to extract the feature points of the nose, eyebrows, eyes, mouth, and ears in the facial feature image, and calculate the comprehensive grayscale values ​​of the feature points in the facial feature image based on the Eigenfaces algorithm; An equalization processing unit 130 is used to integrate the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, perform equalization processing on the facial feature image based on the cumulative distribution function, and determine the pixel distribution range of the facial feature image; The preprocessing set output unit 140 is used to obtain the pixel distribution range of the facial feature image, and determine whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold. If it meets the preset range threshold, the facial feature image after equalization processing is retained; if it does not meet the preset range threshold, the facial feature image after equalization processing is deleted, and at least one group of facial feature images that meet the preset range threshold are integrated, and the facial feature images are set as the preprocessing set.

[0058] 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 one of the above embodiments is implemented.

[0059] Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. As an example and not by way of limitation, a non-volatile 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 (DDRSDRAM), 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.

[0060] In summary, the present invention provides a face access control recognition system, method and storage medium based on image processing. In an embodiment of the present invention, a face access control recognition method based on image processing is provided. By extracting the feature points of the nose, eyebrows, eyes, mouth and ears in the face feature image, the comprehensive grayscale value of the feature points is calculated, so that the face recognition model can quickly detect and identify the access control collection data. At the same time, the face recognition model can more effectively capture the local features in the image by combining distributed displacement convolution and Segnet network construction, thereby enhancing the model's perception of image details, and can also combine deep features with shallow features through jump connections, thereby enhancing the model's adaptability to complex backgrounds and different lighting conditions, and overcoming the existing method that uses Mobilefacenet to calculate face subgraphs and obtains face feature values. The problem of being unable to effectively capture local features in the image and insufficient perception of image details.

[0061] 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.

[0062] 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. A face access control recognition method based on image processing, characterized in that: The face access control recognition method based on image processing specifically includes: Acquire at least one set of access control collection data, pre-process the access control collection data, and obtain a pre-processed set; The face recognition model of the improved Segnet network is constructed by combining distributed displacement convolution, and the standard image set in the access control database is retrieved. The standard image set is divided into training set, test set and verification set. The training set is used to iteratively train the face recognition model, and the converged face recognition model is output. Load the preprocessing set, use the preprocessing set as input, execute the face recognition model, and determine whether the preprocessing set is a living target. If the preprocessing set is a living target, the face recognition model will perform recognition detection on the preprocessing set and output the detection result; If the preprocessing set is not a living target object, a re-verification instruction is triggered to collect real-time face data in real time, pre-process the real-time face data, and determine whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; Obtain the test results, determine whether the test results exceed the preset result threshold, trigger the access control opening and closing command based on the preset result threshold, and turn on / off the access control system.

2. The face access control recognition method based on image processing as claimed in claim 1, characterized in that: The method for preprocessing access control collected data specifically includes: Load access control data and extract facial feature images from the access control data; Extract the feature points of nose, eyebrows, eyes, mouth and ears in the facial feature image, and calculate the comprehensive grayscale value of the feature points in the facial feature image based on the Eigenfaces algorithm; Among them, the comprehensive gray value of the feature point is calculated by the following formula: （1） in, Represents the comprehensive grayscale value of the feature points of the facial feature image, Indicates the current feature point The gray value of Indicates the coordinate value of the current feature point in the face feature image, is the number of feature points; Integrate the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, perform equalization processing on the facial feature image based on the cumulative distribution function, and determine the pixel distribution range of the facial feature image; The pixel distribution range is calculated by the following formula: （2） in, represents the pixel distribution range, Represents the comprehensive grayscale value of the feature points of the facial feature image, is the controllable distribution range of pixels, represents the image recognition distance, is the distance correction factor, Indicates the frequency of image orientation recognition; Obtaining the pixel distribution range of the facial feature image, and judging whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold, and if it meets the preset range threshold, retaining the facial feature image after equalization processing; If it does not meet the preset range threshold, the facial feature image after equalization processing is deleted; At least one group of facial feature images that meet a preset range threshold is integrated, and the facial feature images are set as a preprocessing set.

3. The face access control recognition method based on image processing as claimed in claim 1, characterized in that: The method of iteratively training a face recognition model using a training set specifically includes: The Segnet network is used as the initial model of the face recognition model, wherein the initial model includes an encoder and a decoder, the encoder includes five groups of convolution modules, and each group of the convolution modules includes three groups of convolution layers and one group of BN layers, the decoder includes three groups of decoding modules, and each group of the decoding modules includes three groups of upsampling layers, convolution layers, and one group of BN layers; The feature classifier of FaceLivenessNet is introduced into the initial model, and the feature discriminator is used as the liveness discriminator. The liveness discriminator is placed in front of the encoder and connected to the encoder. Freeze the convolutional layers in the decoding module, replace them with distributed shifted convolutional structures, and replace the BN layers in the decoding module with cascaded Adaboost modules; Initialize and set the recognition node control indicators and hyperparameters of the feature classifier, encoder, and decoder in the initial model, introduce the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network, and adjust the position of the recognition node; Conduct ablation tests on feature classifiers, encoders, and decoders to complete the construction of the initial model; Get the training set, use the training set as input, set the training rounds, iteratively train the initial model, use forward propagation to calculate the loss value, update the model hyperparameters based on the backpropagation algorithm, and after each training, use the validation set to verify the performance of the initial model until the initial model converges; Get the test set, use the test set as input, execute the converged initial model, and get the model test results; Based on the preset model accuracy, verify whether the model test result exceeds the preset model accuracy. If it exceeds the preset model accuracy, output the trained face recognition model.

4. The face access control recognition method based on image processing as claimed in claim 3, characterized in that: The method of introducing the attention mechanism to comprehensively define the pixel-level classification layer of the Segnet network specifically includes: Obtain the decoded feature map of the decoder, and introduce the SimAM attention mechanism into the pixel-level classification layer to infer the 3D attention weights of the facial feature points nose, eyebrows, eyes, mouth, and ears in the decoded feature map; The 3D attention weight calculation formula is as follows: （3） in, is the 3D attention weight of the feature point, represents the number of pixels in the decoded feature map, represents the total value of the decoded feature map phase map, is the initial weight of the feature point, Represents the attention coefficient of SimAM’s attention mechanism; （4） The energy function of the neurons in the pixel-level classification layer is defined based on the 3D attention weights of the feature points, and the mean and variance of the energy function are calculated through the energy function of the neurons; The energy function is defined as: （5） in, represents the number of neurons in the pixel-level classification layer, represents the activation function of the pixel-level classification layer; （6） represents the attention weight matrix of the decoded feature map, is the activation function hyperparameter, Represents the bias term of the activation function; Combined with the mean and variance of the energy function, the improved vector machine is used to establish the feature recognition space of the neurons in the pixel-level classification layer, and the difference vector of face feature recognition in the space is calculated; （7） in, is the vector calculation result, represents the output value of the energy function, represents the mean value of the energy function, represents the variance of the energy function; Obtain the vector calculation results and use them to comprehensively define the pixel-level classification layer of the Segnet network.

5. The face access control recognition method based on image processing as claimed in claim 4, characterized in that: The method of executing the face recognition model to determine whether the preprocessing set is a living target object specifically includes: Get the preprocessing set, and perform hybrid enhancement on the preprocessing set based on Mosaic+Mixup to obtain the image enhancement set; The image enhancement set is loaded, and the feature discriminator extracts the interactive feedback of the image enhancement set based on the FaceLivenessNet algorithm. The interactive feedback includes pixel motion mode, thermal imaging information of facial feature points, and RDB image information. Obtain interactive feedback of the image enhancement set and calculate the significance level of the interactive feedback based on principal component analysis; （8） in, represents the significance level of interactive feedback, They represent the weight coefficients of pixel motion mode, facial feature point thermal imaging information, and RDB image information in interactive feedback, respectively. is the number of samples in the image enhancement set, They represent pixel motion mode, facial feature point thermal imaging information, and RDB image information input values ​​respectively; A liveness significance threshold is preset to determine whether the significance level of the interactive feedback exceeds the liveness significance threshold. If it exceeds the liveness significance threshold, the preprocessing set is determined to be a liveness target.

6. The face access control recognition method based on image processing as claimed in claim 5, characterized in that: The method for the face recognition model to perform recognition detection on the preprocessing set specifically includes: The encoder obtains the preprocessing set, and the convolution module in the encoder performs a first-level convolution process on the preprocessing set to obtain a first-level convolution result, wherein the encoding convolution result extracts edges, lines, and angles in facial features; Obtain the first-level convolution result. The convolution module constructs a facial feature map based on the first-level convolution result, supplements the facial feature map with details based on the preset number of zero-padding layers, and outputs the facial feature map with the details supplemented. The face feature map is loaded, and the convolution module performs secondary convolution on the face feature map to increase the hole receptive field of the face feature map and output the secondary convolution result.

7. The face access control recognition method based on image processing as claimed in claim 6, characterized in that: The method for the face recognition model to perform recognition detection on the preprocessing set specifically includes: Obtain the secondary convolution result, and the decoding module performs feature fusion on the secondary convolution result to obtain a feature fusion set; Load the feature fusion set, and build the initial decoding feature graph based on the feature fusion set; The cascaded Adaboost module is used to process the initial decoding feature graph, the deviation of the identified initial decoding feature graph is corrected for secondary processing, and the decoding feature graph and graph confidence are output; Calculate the detection result value of the decoded feature graph based on the graph confidence, and output the detection result; The test result value is calculated by the following formula: （9） in, is the test result value, is the vector calculation result, Represents the graph confidence of the decoded feature map.

8. A face access control recognition system based on image processing, used to implement the face access control recognition method based on image processing as claimed in any one of claims 1 to 7, characterized in that: The face access control recognition system based on image processing specifically includes: A data collection module, used to obtain at least one set of access control collection data, pre-process the access control collection data, and obtain a pre-processed set; The model building module combines distributed displacement convolution to build an improved Segnet network face recognition model, retrieves the standard image set from the access control database, divides the standard image set into training set, test set and validation set, uses the training set to iteratively train the face recognition model, and outputs a converged face recognition model; The recognition and detection module loads the preprocessing set, takes the preprocessing set as input, executes the face recognition model, and determines whether the preprocessing set is a living target. If the preprocessing set is a living target, the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The secondary verification module is used to obtain the judgment result of whether the preprocessing set is a living target object. If the preprocessing set is not a living target object, a re-verification instruction is triggered to collect real-time face data in real time, preprocess the real-time face data, and judge whether the real-time face data is a living target object based on the face recognition model. If the real-time face data is a living target object, the real-time face data is replaced with the associated preprocessing set, and the face recognition model performs recognition detection on the preprocessing set and outputs the detection result; The access control module is used to obtain the detection results, determine whether the detection results exceed the preset result threshold, trigger the access control opening and closing instructions based on the preset result threshold, and open / close the access control system.

9. The face access control recognition method based on image processing as claimed in claim 8, characterized in that: The data acquisition module specifically includes: A feature extraction unit is used to load access control data and extract facial feature images from the access control data; A comprehensive grayscale calculation unit is used to extract the feature points of the nose, eyebrows, eyes, mouth, and ears in the facial feature image, and calculate the comprehensive grayscale value of the feature points in the facial feature image based on the Eigenfaces algorithm; An equalization processing unit, used for integrating the facial feature image and the comprehensive grayscale values ​​of the feature points corresponding to the facial feature image, performing equalization processing on the facial feature image based on the cumulative distribution function, and determining the pixel distribution range of the facial feature image; The preprocessing set output unit is used to obtain the pixel distribution range of the facial feature image, and determine whether the pixel distribution range of the facial feature image meets the preset range threshold based on the preset range threshold. If it meets the preset range threshold, the facial feature image after equalization processing is retained; if it does not meet the preset range threshold, the facial feature image after equalization processing is deleted, and at least one group of facial feature images that meet the preset range threshold are integrated, and the facial feature images are set as the preprocessing set.

10. A computer-readable storage medium, characterized in that: Computer program instructions are stored, and when the computer program instructions are executed, the face access control recognition method based on image processing as described in any one of claims 1 to 7 is implemented.

Images