A face-scanning payment management method and system

Abstract

The present invention relates to the field of payment management technology, and specifically discloses a face-swiping payment management method and system, which includes: collecting humidity sensor data, light sensor data, and facial images; inputting the humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model to output environmental markers; marking corresponding positions on the facial image according to the environmental markers to obtain the original image; performing image restoration based on the original image to obtain a clear portrait; structurally extracting the clear portrait to obtain a complete feature point set; inputting the complete feature point set and a database template into a pre-built payment permission determination model to obtain a liveness determination value and a similarity score. The present invention ensures recognition accuracy by integrating intelligent restoration methods such as sensing technology, image processing algorithms, and deep learning models, thereby solving the water-oil interference problem that may be encountered in facial recognition payment systems.

Description

Technical Field

[0001] The present application relates to the field of payment management technology, and in particular to a face-scanning payment management method and system. Background Art

[0002] In the current digital payment landscape, especially in mobile and contactless payment systems, user experience and transaction security are crucial considerations. With technological advancements, biometrics, particularly facial recognition, has become an important means of secure payment due to its convenience and difficulty in counterfeiting. For example, the Chinese patent specification with publication number CN113657903B provides a facial recognition payment method, device, electronic device, and storage medium. The method comprises: collecting image information; identifying user behavior information of at least one user based on the image information, where the user behavior information includes facial recognition information, or the user behavior information includes facial recognition information and gesture information; if at least one gesture information is identified, generating a willingness-to-pay value for each user based on the user behavior information of the at least one user; and if a target user is identified from the at least one user based on the willingness-to-pay value of each user, performing facial recognition payment on the target user. This embodiment of the specification activates the facial recognition payment process by identifying gesture information, determines the target user by generating a willingness-to-pay value based on the facial recognition information and gesture information, and performs facial recognition payment on the target user identified based on the willingness-to-pay value. This avoids misidentification of the target user, thereby improving the security of facial recognition payment. However, facial recognition technology is often affected by multiple factors in actual environments. In particular, in outdoor payment environments, it is extremely susceptible to interference from water and oil. For example, in a cafeteria, when students wash their hands after eating and use facial recognition to pay, some water and oil may be contaminated on the camera of the facial consumption machine, causing the facial recognition payment system to fail payment verification. Summary of the Invention

[0003] In order to solve the above problems, an embodiment of the present invention provides a face-scanning payment management method, which includes:

[0004] Collect humidity sensor data, light sensor data, and facial images;

[0005] Input humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model and output environmental signs;

[0006] Mark the corresponding position of the face image according to the environmental mark to obtain the original image;

[0007] Perform image restoration based on the original image to obtain a clear portrait;

[0008] Perform structure extraction on clear portraits to obtain a complete set of feature points;

[0009] Input the complete feature point set and database template into the pre-built payment permission determination model to obtain the liveness determination value and similarity score;

[0010] The payment result is output based on the liveness determination value and similarity score.

[0011] The oil-water detection model includes an oil-water interference identification model and a frequency domain analysis mathematical model;

[0012] The frequency domain analysis mathematical model includes:

[0013] Convert the face image into a grayscale image f(x,y); obtain the frequency domain representation F(u,v) of the image by calculating the grayscale image f(x,y). The calculation method of F(u,v) includes:

[0014]

[0015] Where f(x,y) is the grayscale value of the image in the time domain; F(u,v) is the complex value in the frequency domain, representing the frequency component; M and N are the width and height of the image; u and v are the frequency domain coordinates, corresponding to the horizontal and vertical frequencies respectively; j is the imaginary unit;

[0016] Generate a spectrum based on the frequency domain representation F(u,v) and perform logarithmic transformation to enhance the contrast;

[0017] Perform high-pass filtering on the spectrum graph, and then inversely transform it back into a face image, that is, filter the face image, input the filtered face image into the database, and perform threshold segmentation on the filtered face image to obtain an image containing only high-frequency features, that is, a time series highlight image;

[0018] The inverse transform calculation method includes:

[0019]

[0020] The training method of the oil-water interference recognition model includes:

[0021] All time series highlight images are used as input to the oil-water interference recognition model. The oil-water interference recognition model uses the environmental signs corresponding to each group of time series highlight images as output, the actual environmental signs corresponding to each group of time series highlight images as prediction targets, and minimizing the sum of the first prediction accuracies of all predicted environmental signs as a training target. The oil-water interference recognition model is trained until the sum of the first prediction accuracies reaches convergence, and training is stopped. The oil-water interference recognition model is a convolutional neural network model.

[0022] The method for obtaining a clear portrait includes:

[0023] Analyze and repair the marked areas on the original image:

[0024] Environmental markers include no interference, water interference, oil interference and oil-water mixed interference; if the marked environmental marker is no interference, no operation is performed; if the marked environmental marker is water interference, the area marked as water interference, i.e. the water interference area, is input into the pre-built adversarial network model, and a clear area map is output; if the marked environmental marker is oil interference, the filtered face image at the corresponding position is output from the database; if the marked environmental marker is oil-water mixed interference, the filtered face image at the corresponding position in the database is input into the pre-built adversarial network model, and a clear area map is output; when all marked areas on the original image are analyzed and repaired, a clear portrait is obtained.

[0025] The adversarial network model includes a generator and a discriminator;

[0026] The generator consists of an initial layer, a downsampling layer, a residual block, an upsampling layer, and a first output layer. The generator adopts a U-Net architecture. The initial layer consists of the first convolutional layer and an activation layer. The downsampling layer achieves downsampling through convolution with a step size greater than 1. The residual block consists of the second and third convolutional layers with skip connections. The second and third convolutional layers are followed by batch normalization and ReLU activation. The upsampling layer consists of a transposed convolutional layer, followed by batch normalization and ReLU. The first output layer consists of the fourth convolutional layer and the Tanh activation function.

[0027] The discriminator includes an input layer, a feature extraction layer, an intermediate layer and a second output layer; the input layer is used to input images; the feature extraction layer includes multiple convolutional layers and LeakyReLU activation functions; the intermediate layer is located in the middle of the feature extraction layer and is a batch normalization layer; the second output layer includes multiple fully connected layers and output neurons.

[0028] The training method of the adversarial network model includes:

[0029] The discriminator and generator are trained in a loop. When both the generator loss function and the discriminator loss function converge, the loop ends and the training is completed.

[0030] The training method of the payment permission determination model includes:

[0031] All complete feature point sets and database templates are used as inputs of a payment permission determination model. The payment permission determination model uses the liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as outputs, uses the actual liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as prediction targets, and uses minimizing the sum of the second prediction accuracies of all predicted liveness determination values ​​and similarity scores as a training target. The payment permission determination model is trained until the sum of the second prediction accuracies reaches convergence, and training is stopped. The payment permission determination model is a convolutional neural network model.

[0032] On the other hand, this application also provides a face-scanning payment management system, including:

[0033] A collection module, the collection module is used to collect humidity sensor data, light sensor data and face images;

[0034] A pre-labeling module, which is used to input humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model and output an environmental sign;

[0035] A marking module is used to mark corresponding positions of the face image according to the environmental markers to obtain the original image;

[0036] An image restoration module is used to restore the original image to obtain a clear portrait.

[0037] A feature extraction module, which is used to extract the clear human portrait and obtain a complete feature point set;

[0038] A liveness determination module, which inputs the complete feature point set and the database template into a pre-built payment permission determination model to obtain a liveness determination value and a similarity score;

[0039] The payment output module is used to output the payment result according to the liveness determination value and the similarity score.

[0040] The technical effects and advantages of the face-scanning payment management method and system provided by the present invention are as follows:

[0041] The present invention ensures recognition accuracy by integrating intelligent repair methods such as sensing technology, image processing algorithms and deep learning models, and solves the water and oil interference problem that may be encountered in facial recognition payment systems. In addition, through intelligent repair and precise liveness detection technology, it greatly enhances the user's payment security, reduces the risk of fraud, and improves the user's payment experience; integrates humidity and light sensors to monitor environmental changes in real time and quickly identify possible interference conditions, such as high humidity may indicate water droplet interference, and abnormal light enhancement may be due to oil film reflection; uses deep learning algorithms, combines sensor data and image analysis, accurately calibrates the interfered area, and distinguishes the interference type (water, oil or mixed); transforms and analyzes the frequency domain characteristics of the interfered image, It effectively identifies and isolates high-frequency interference, such as light spots caused by oil film. It uses a generative adversarial network, specifically the U-Net architecture, to perform targeted repairs on damaged areas, ensuring accurate facial recognition. It uses feature extraction technology to obtain a detailed set of facial feature points, leveraging depth information for reconstruction even when some feature points are damaged. It combines liveness detection values ​​and similarity scores to accurately determine payment authorization, and through efficient comparison with database templates, ensures that only legitimate and authentic users can execute payments. All technologies and models are integrated in a way that is imperceptible to the user, without interfering with user operations and improving the user experience. All processing steps, such as interference detection, image restoration, and feature analysis, are completed within seconds, enabling rapid feedback and rapid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a face-scanning payment management method in Example 1;

[0043] Figure 2 This is a schematic diagram of the connection of the adversarial network model in Example 1;

[0044] Figure 3 This is a connection diagram of a face-scanning payment management system in Example 2. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] Example 1:

[0047] See also Figure 1 As shown, the face-scanning payment management method described in this embodiment includes:

[0048] Collect humidity sensor data, light sensor data, and facial images;

[0049] Input humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model, and output environmental signs;

[0050] Mark the corresponding position of the face image according to the environmental mark to obtain the original image;

[0051] Perform image restoration based on the original image to obtain a clear portrait;

[0052] Perform structure extraction on clear portraits to obtain a complete set of feature points;

[0053] Input the complete feature point set and database template into the pre-built payment permission determination model to obtain the liveness determination value and similarity score;

[0054] The payment result is output based on the liveness determination value and similarity score.

[0055] Humidity sensor data and light sensor data are obtained by the sensors of the face consumption machine. Humidity sensor data is used to quickly filter out the possibility of water interference and reduce the burden of subsequent analysis. Light sensor data is used to capture abnormal reflections and preliminarily judge whether oil or water may exist. For example, high humidity (for example, >70%): there may be water interference; low humidity (for example, <40%): the possibility of water interference is low; abnormal reflected light intensity (increased local light spots and reflections): it may be caused by oil film reflection or water droplet focusing; no obvious reflection abnormality: the reflection characteristics are normal, and there is no oil or water interference; the face image is used as the original data to verify the interference type, which is used to accurately determine the specific interference type (oil, water, oil and water mixture); due to the difference between water droplet characteristics and oil film characteristics, the oil and water detection model is a mixed recognition.

[0056] Water droplet characteristics:

[0057] Local image blur: The convex lens effect of water droplets will cause local areas to be blurred and distorted.

[0058] Optical properties of water droplet edges: A scattered light halo may appear around the water droplets.

[0059] Oil film characteristics:

[0060] Local highlights in the image: The mirror reflection effect of the oil film will cause strong reflective highlights to appear in some areas of the image.

[0061] Global image blur: A thin oil film may cause overall light scattering, making the image edges unclear.

[0062] Environmental labels include no interference, water interference, oil interference and oil-water mixed interference.

[0063] The oil-water detection model includes the oil-water interference identification model and the frequency domain analysis (FFT) mathematical model.

[0064] Frequency domain analysis (FFT) mathematical models include:

[0065] Convert the face image into a grayscale image f(x,y); obtain the frequency domain representation F(u,v) of the image by calculating the grayscale image f(x,y). The calculation method of F(u,v) includes:

[0066]

[0067] Where f(x,y) is the grayscale value (pixel value) of the image in the time domain; F(u,v) is the complex value in the frequency domain, representing the frequency component; M and N are the width and height of the image; u and v are the frequency domain coordinates, corresponding to the horizontal and vertical frequencies respectively; j is the imaginary unit.

[0068] Generate a spectrum based on the frequency domain representation F(u,v) and perform logarithmic transformation to enhance the contrast;

[0069] The formula for enhancing contrast is as follows:

[0070] Spectrum(u,v)=log(1+|F(u,v)|);

[0071] Structure code example:

[0072]

[0073]

[0074] The spectrum graph is high-pass filtered and then inversely transformed back into a face image, i.e., a filtered face image. The filtered face image is input into the database, and the filtered face image is threshold segmented to obtain an image containing only high-frequency features, i.e., a time series highlight image.

[0075] The inverse transform calculation method includes:

[0076]

[0077] The operation method of high-pass filtering is to create a mask with a "center-shielded low-frequency area", setting the low-frequency components in the frequency domain to zero and retaining only the high-frequency components on the periphery.

[0078] High-frequency features describe details with high-frequency changes in the image, such as edges, textures, and bright spots. They can be used to assist in interference classification in subsequent machine learning models (such as distinguishing between oil, water, and oil-water mixtures). The recognition logic is:

[0079] Water Droplets:

[0080] Local blur and diffuse halo.

[0081] The high-frequency characteristics are distributed more dispersedly, and the boundaries of the bright spot area are blurred.

[0082] Oil film:

[0083] Highlight areas caused by strong reflections.

[0084] The high-frequency characteristics are concentrated, and the bright spot areas are dot-shaped or strip-shaped.

[0085] It is worth noting that the time series highlight image can be segmented by thresholding to detect and identify the highlight reflection area.

[0086] Structure code example:

[0087]

[0088]

[0089] The training methods for the oil-water interference recognition model include:

[0090] All time series highlight images are used as input to the oil-water interference recognition model. The oil-water interference recognition model predicts the corresponding environmental signs for each group of time series highlight images as output, and the actual environmental signs corresponding to each group of time series highlight images as prediction targets. The training goal is to minimize the sum of the first prediction accuracies of all predicted environmental signs.

[0091] Among them, the calculation formula for the first prediction accuracy is: EW v =(EQ v -ET v ) 2 , where v is the number of each set of time series highlight images, EW v is the first prediction accuracy, EQ v is the predicted environmental symbol corresponding to the vth group of time series highlight images, ET v is the actual environmental sign corresponding to the vth group of time series highlight images; the oil-water interference recognition model is trained until the sum of the first prediction accuracy reaches convergence; the oil-water interference recognition model is a convolutional neural network model.

[0092] Methods for obtaining clear portraits include:

[0093] Analyze and repair the marked areas on the original image:

[0094] If the marked environmental sign is no interference, no operation is performed; if the marked environmental sign is water interference, the area marked as water interference, i.e. the water interference area, is input into the pre-built adversarial network model, and a clear area map is output; if the marked environmental sign is oil interference, the filtered face image at the corresponding position is output from the database; if the marked environmental sign is oil-water mixed interference, the filtered face image at the corresponding position in the database is input into the pre-built adversarial network model, and a clear area map is output; when all the marked areas on the original image are analyzed and repaired, a clear portrait is obtained.

[0095] like Figure 2 As shown, the adversarial network model includes a generator and a discriminator;

[0096] The generator includes the initial layer, downsampling layer, residual block, upsampling layer and the first output layer; the generator adopts the U-Net architecture; the initial layer includes the first convolution layer and the activation layer, the convolution layer is used to extract the features of the image, and the activation layer uses the ReLU activation function to increase the nonlinear processing capability; the downsampling layer achieves downsampling through convolution with a step size greater than 1, reducing the spatial dimension of the feature map while increasing the number of channels; the residual block includes the second convolution layer, the third convolution layer and the jump connection, and the second and third convolution layers are followed by batch normalization and ReLU Activation, batch normalization and ReLU are standard activation and normalization methods; skip connections can help information propagate in the network and reduce information loss during training; the upsampling layer includes a transposed convolution layer, which is followed by batch normalization and ReLU. The transposed convolution layer is used to gradually enlarge the feature map and restore the image dimension; the first output layer includes the fourth convolution layer and the Tanh activation function. The fourth convolution layer uses a convolution layer with a smaller convolution kernel size to produce the final image. The Tanh activation function ensures that the pixel values ​​of the output image are within an appropriate range.

[0097] The discriminator includes an input layer, a feature extraction layer, an intermediate layer and a second output layer; the input layer is used to input images; the feature extraction layer includes multiple convolutional layers and LeakyReLU activation functions. The number of convolutional layers depends on the complexity of the data and is not fixed. After each convolution layer, the spatial dimension of the feature map is gradually reduced (using convolution with a step size greater than 1) and the number of channels is increased. The LeakyReLU activation function provides a slight negative slope to help the model learn more features; the intermediate layer is located in the middle of the feature extraction layer and is a batch normalization layer. Batch normalization is added to deeper convolutional layers to help stabilize the training process and improve the effect; the second output layer includes multiple fully connected layers and output neurons. After flattening the convolved feature map, it is processed through one or more fully connected layers, that is, multiple fully connected layers. The number of multiple fully connected layers depends on the complexity of the data. The neurons use the Sigmoid activation function to output a value in the range of [0, 1], indicating the probability that the input image is real.

[0098] In particular, data complexity refers to the diversity, dimension, size, and structural complexity of the input data. These factors directly affect the design of the model structure and the training strategy. If the labeled environment is less interference-free, that is, the image is more complex, the more processing elements, that is, the greater the data complexity, the larger the number of layers;

[0099] Training methods for adversarial network models include:

[0100] The discriminator and generator are trained in a loop. When both the generator loss function and the discriminator loss function converge, the loop ends and the training is completed.

[0101] Discriminator training: Use the filtered face image generated by the generator, the water interference area generated by the generator, the real filtered face image and the real water interference area to train the discriminator, and update the discriminator parameters (weights and biases) to maximize the discriminator loss function.

[0102] Generator training: Freeze the discriminator parameters and update the generator parameters (weights and biases) by trying to "fool" the discriminator to minimize the generator loss function.

[0103] Generator loss function L G The calculation methods include:

[0104] L G = -log(D(G(z)));

[0105] Where D(G(z)) is the discriminator’s discrimination result on the image generated by the generator.

[0106] Discriminator loss function L D The calculation methods include:

[0107] L D =-[d·log(D(l))+(1-d)log(1-D(G[z]))];

[0108] Where d is the label, which is 11 for the real filtered face image and water interference area, and 10 for the filtered face image and water interference area generated by the generator; l is the real filtered face image and water interference area; G(z) is the filtered face image and water interference area generated by the generator.

[0109] Code example:

[0110]

[0111]

[0112]

[0113] Feature extraction uses image recognition technology to extract feature points (nose, mouth, eyes, etc.). If the feature points are missing, depth information (infrared or ToF) is used to reconstruct the feature points of the occluded area. Although the feature points of the face have been supplemented and clarified in the previous steps, there may still be omissions or places that cannot be repaired. Therefore, the places where there is a very small possibility of missing information are reconstructed here, but the loss of such reconstructed information will be very serious. If the depth information is used directly for reconstruction at the beginning, the authenticity of the entire face image will be seriously questioned, and information extraction will be seriously interfered with.

[0114] A database template is a pre-set or collected facial image library that contains facial feature data of registered users. In a facial recognition system, these templates are used as a benchmark for comparison with newly captured facial data.

[0115] The training method for the payment permission determination model includes:

[0116] All complete feature point sets and database templates are used as inputs to the payment permission determination model. The payment permission determination model uses the liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as outputs, the actual liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as prediction targets, and minimizing the sum of the second prediction accuracies of all predicted liveness determination values ​​and similarity scores as the training target.

[0117] Among them, the calculation formula for the second prediction accuracy is: FY H =(FV H -FP H ) 2 , where H is the number of each set of complete feature points and database templates, FY H is the second prediction accuracy, FV H is the predicted liveness judgment value and similarity score corresponding to the Hth set of complete feature point sets and the database template, FP H is the actual liveness determination value and similarity score corresponding to the Hth group of complete feature point sets and the database template; the payment permission determination model is trained until the sum of the second prediction accuracy reaches convergence; the payment permission determination model is a convolutional neural network model.

[0118] The liveness determination value is 100 and 111, 100 means it is not a live person, and 111 means it is a live person; this prevents the situation of face payment using pictures; the similarity score range is [0, 1], 0 means it is not a real face at all, and 1 means it is a database template; the payment result is granting payment authorization or denying payment authorization; if the liveness determination value is 111 and the similarity score is greater than or equal to the preset threshold, the payment result is granting payment authorization, and all other payment results are denying payment authorization and returning an error.

[0119] Example 2:

[0120] like Figure 3 As shown, based on the same inventive concept as the face-scanning payment management method in the aforementioned embodiment, this application provides a face-scanning payment management system. The system and method embodiments in the embodiments of this application are based on the same inventive concept. The system includes:

[0121] Collection module, used to collect humidity sensor data, light sensor data and face images;

[0122] A pre-labeling module is used to input humidity sensor data, light sensor data, and face images into a pre-built oil-water detection model and output environmental labels;

[0123] The annotation module is used to mark the corresponding position of the face image according to the environmental mark to obtain the original image;

[0124] Image restoration module, used to perform image restoration based on the original image to obtain a clear portrait;

[0125] Feature extraction module, used to extract clear portraits and obtain a complete set of feature points;

[0126] The liveness determination module inputs the complete feature point set and database template into the pre-built payment permission determination model to obtain the liveness determination value and similarity score;

[0127] The payment output module is used to output the payment result based on the liveness determination value and the similarity score.

[0128] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0129] The above is only a preferred specific implementation method of the embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes based on the technical solution and concept of the present application within the technical scope disclosed in the present application, and they should be covered by the scope of protection of the present application.

Claims

1. A facial recognition payment management method, characterized in that: Methods include: Collect humidity sensor data, light sensor data, and facial images; Input humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model and output environmental signs; The oil-water detection model includes an oil-water interference identification model and a frequency domain analysis mathematical model; The frequency domain analysis mathematical model includes: Convert face images to grayscale ; By calculating the grayscale image Get the frequency domain representation of the image , Calculation methods include: ； Where, is the gray value of the image in the time domain; is a complex value in the frequency domain, representing the frequency component; and is the width and height of the image; and are frequency domain coordinates, corresponding to horizontal and vertical frequencies respectively; is an imaginary unit; According to the frequency domain Generate a spectrum and perform logarithmic transformation to enhance the contrast; Perform high-pass filtering on the spectrum graph, and then inversely transform it back into a face image, that is, filter the face image, input the filtered face image into the database, and perform threshold segmentation on the filtered face image to obtain an image containing only high-frequency features, that is, a time series highlight image; The inverse transform calculation method includes: ； Mark the corresponding position of the face image according to the environmental mark to obtain the original image; Perform image restoration based on the original image to obtain a clear portrait; The method for obtaining a clear portrait includes: Analyze and repair the marked areas on the original image: Environmental markers include no interference, water interference, oil interference, and oil-water mixed interference; if the marked environmental marker is no interference, no operation is performed; if the marked environmental marker is water interference, the area marked as water interference, i.e., the water interference area, is input into the pre-built adversarial network model, and a clear area map is output; if the marked environmental marker is oil interference, the filtered face image at the corresponding position is output from the database; if the marked environmental marker is oil-water mixed interference, the filtered face image at the corresponding position in the database is input into the pre-built adversarial network model, and a clear area map is output; When all marked areas on the original image are analyzed and repaired, a clear portrait is obtained; Perform structure extraction on clear portraits to obtain a complete set of feature points; Input the complete feature point set and database template into the pre-built payment permission determination model to obtain the liveness determination value and similarity score; The payment result is output based on the liveness determination value and similarity score.

2. A facial recognition payment management method as claimed in claim 1, characterized in that: The training method of the oil-water interference recognition model includes: All time series highlight images are used as input to the oil-water interference recognition model. The oil-water interference recognition model uses the environmental signs corresponding to each group of time series highlight images as output, the actual environmental signs corresponding to each group of time series highlight images as prediction targets, and minimizing the sum of the first prediction accuracies of all predicted environmental signs as a training target. The oil-water interference recognition model is trained until the sum of the first prediction accuracies reaches convergence, and training is stopped. The oil-water interference recognition model is a convolutional neural network model.

3. A facial recognition payment management method according to claim 1, characterized in that: The adversarial network model includes a generator and a discriminator; The generator consists of an initial layer, a downsampling layer, a residual block, an upsampling layer, and a first output layer. The generator adopts a U-Net architecture. The initial layer consists of the first convolutional layer and an activation layer. The downsampling layer achieves downsampling through convolution with a step size greater than 1. The residual block consists of the second and third convolutional layers with skip connections. The second and third convolutional layers are followed by batch normalization and ReLU activation. The first output layer consists of the fourth convolutional layer and the Tanh activation function. The discriminator includes an input layer, a feature extraction layer, an intermediate layer and a second output layer; the input layer is used to input images; the feature extraction layer includes multiple convolutional layers and LeakyReLU activation functions; the intermediate layer is located in the middle of the feature extraction layer and is a batch normalization layer; the second output layer includes multiple fully connected layers and output neurons.

4. A facial recognition payment management method as claimed in claim 3, characterized in that: The training method of the adversarial network model includes: training the discriminator and the generator in a loop, and ending the loop when the generator loss function and the discriminator loss function converge, and the training is completed.

5. A facial recognition payment management method as claimed in claim 1, characterized in that: The training method of the payment permission determination model includes: taking all complete feature point sets and database templates as inputs of the payment permission determination model, the payment permission determination model using the liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as outputs, using the actual liveness determination value and similarity score corresponding to each set of complete feature point sets and the database template as prediction targets, and minimizing the sum of the second prediction accuracies of all predicted liveness determination values ​​and similarity scores as a training target; training the payment permission determination model until the sum of the second prediction accuracies reaches convergence, and stopping training; the payment permission determination model is a convolutional neural network model.

6. A face-scanning payment management system, characterized in that: include: A collection module, the collection module is used to collect humidity sensor data, light sensor data and face images; A pre-labeling module, which is used to input humidity sensor data, light sensor data, and facial images into a pre-built oil-water detection model and output an environmental sign; The oil-water detection model includes an oil-water interference identification model and a frequency domain analysis mathematical model; The frequency domain analysis mathematical model includes: Convert face images to grayscale ; By calculating the grayscale image Get the frequency domain representation of the image , Calculation methods include: ； Where, is the gray value of the image in the time domain; is a complex value in the frequency domain, representing the frequency component; and is the width and height of the image; and are frequency domain coordinates, corresponding to horizontal and vertical frequencies respectively; is an imaginary unit; According to the frequency domain Generate a spectrum and perform logarithmic transformation to enhance the contrast; Perform high-pass filtering on the spectrum graph, and then inversely transform it back into a face image, that is, filter the face image, input the filtered face image into the database, and perform threshold segmentation on the filtered face image to obtain an image containing only high-frequency features, that is, a time series highlight image; The inverse transform calculation method includes: ； A marking module is used to mark corresponding positions of the face image according to the environmental markers to obtain the original image; An image restoration module is used to perform image restoration based on the original image to obtain a clear portrait. The method for obtaining the clear portrait includes: Analyze and repair the marked areas on the original image: Environmental markers include no interference, water interference, oil interference, and oil-water mixed interference; if the marked environmental marker is no interference, no operation is performed; if the marked environmental marker is water interference, the area marked as water interference, i.e., the water interference area, is input into the pre-built adversarial network model, and a clear area map is output; if the marked environmental marker is oil interference, the filtered face image at the corresponding position is output from the database; if the marked environmental marker is oil-water mixed interference, the filtered face image at the corresponding position in the database is input into the pre-built adversarial network model, and a clear area map is output; When all marked areas on the original image are analyzed and repaired, a clear portrait is obtained; A feature extraction module, which is used to extract the clear human portrait and obtain a complete feature point set; A liveness determination module, which is used to input the complete feature point set and the database template into a pre-built payment permission determination model to obtain a liveness determination value and a similarity score; The payment output module is used to output the payment result according to the liveness determination value and the similarity score.

Images