Image super-resolution method and system based on structural and texture features

Abstract

This invention discloses a method and system for image super-resolution based on structural and texture features. The method includes: constructing a generative adversarial network capable of extracting structural and texture features; inputting a super-resolution image dataset into the generative adversarial network; training and generating weights for the corresponding model; obtaining an image super-resolution model based on the weights; inputting the image to be super-resolved into the image super-resolution model; and generating a high-definition image after super-resolution. By integrating the structural and texture features of an image, the method improves the image super-resolution restoration effect and avoids detail loss. It also provides efficient performance optimization and a user-friendly interface, making the image processing process more convenient.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to an image super-resolution method and system based on structure and texture features. Background Art

[0002] Image super-resolution (SR) methods involve the process of inversely restoring a high-resolution (HR) image from a low-resolution (LR) image. This technology addresses the demand for image clarity in various applications by restoring image detail and improving image quality. It is widely used in fields such as medical imaging, remote sensing imaging, and security monitoring. For example, in medical imaging, it improves diagnostic accuracy; in remote sensing processing, it enhances object resolution; and in security monitoring, it optimizes image detail, contributing to public safety. This technology holds a significant position and holds broad prospects in the field of modern image processing.

[0003] Image super-resolution methods can be mainly divided into traditional methods and deep learning-based convolutional neural network methods. Traditional methods mainly include interpolation methods and example methods. These methods rely on prior knowledge of the image. Interpolation methods such as nearest neighbor, bilinear, and bicubic interpolation improve image resolution through simple mathematical models, but they have difficulty restoring high-resolution image details. Example-based methods restore details by utilizing similar blocks or feature information in images or image databases. For example, non-local means and sparse representation techniques supplement missing details by searching for areas similar to the target image in the image database. These methods can improve the restoration of image details to a certain extent, but because they require matching and modeling prior information, their computational complexity is high and their generalization ability for large-scale complex scenes is limited.

[0004] Deep learning-based methods, particularly convolutional neural networks (CNNs), are increasingly being used in image super-resolution. The advantage of deep learning methods is that they no longer rely on hand-crafted image features or prior knowledge. Instead, they can be trained using large amounts of data to automatically extract the most appropriate features for the task, directly generating high-resolution images end-to-end. By automatically learning the multi-layered features and complex relationships of an image, these methods can effectively recover more high-frequency details from low-resolution images.

[0005] Currently, although super-resolution models can restore image clarity to a certain extent through technologies such as deep learning and convolutional neural networks (CNN), many methods are still unable to effectively cope with the challenges of multi-scale and complex backgrounds, resulting in the final generated images being blurred or lacking sufficient details, thus affecting the breadth and effectiveness of their application. Summary of the Invention

[0006] The present invention provides an image super-resolution method and system based on structural and texture features, which is used to solve the technical problem that existing deep learning models generally have blurred images or lack of sufficient details when they expect to generate high-resolution images with reasonable structure and rich texture details.

[0007] In a first aspect, the present invention provides an image super-resolution method based on structural and texture features, comprising:

[0008] Preprocessing the image dataset to obtain a super-resolution image dataset;

[0009] Constructing a generative adversarial network with structural and texture feature extraction capabilities, the generative adversarial network includes a generator and a discriminator, the generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module, and the discriminator includes a U-NET type network architecture;

[0010] Inputting the super-resolution image dataset into the generative adversarial network, training and generating weights of the corresponding model, and obtaining an image super-resolution model based on the weights;

[0011] The image to be super-resolutioned is input into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0012] In a second aspect, the present invention provides an image super-resolution system based on structural and texture features, comprising:

[0013] A preprocessing module is configured to preprocess the image dataset to obtain a super-resolution image dataset;

[0014] A construction module is configured to construct a generative adversarial network with structural and texture feature extraction capabilities, wherein the generative adversarial network includes a generator and a discriminator, wherein the generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module, and the discriminator includes a U-NET type network architecture;

[0015] A training module is configured to input the super-resolution image dataset into the generative adversarial network, train and generate weights of the corresponding model, and obtain an image super-resolution model based on the weights;

[0016] The output module is configured to input the image to be super-resolutioned into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0017] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the image super-resolution method based on structural and texture features of any embodiment of the present invention.

[0018] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the image super-resolution method based on structural and texture features of any embodiment of the present invention.

[0019] The image super-resolution method and system based on structural and texture features of the present application construct a generative adversarial network with the ability to extract structural and texture features, input a super-resolution image dataset into the generative adversarial network, train and generate weights for the corresponding model, obtain an image super-resolution model based on the weights, input the image to be super-resolution into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution. This method improves the image super-resolution restoration effect by fusing the structural and texture features of the image and avoids loss of details. At the same time, it provides efficient performance optimization and a user-friendly interface, making the image processing process more convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 A flowchart of an image super-resolution method based on structural and texture features provided by one embodiment of the present invention;

[0022] Figure 2 A structural block diagram of an image super-resolution system based on structure and texture features provided by one embodiment of the present invention;

[0023] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] See also Figure 1 , which shows a flowchart of an image super-resolution method based on structure and texture features of the present application.

[0026] like Figure 1 As shown in FIG, the image super-resolution method based on structure and texture features specifically includes the following steps:

[0027] Step S101 : preprocessing the image dataset to obtain a super-resolution image dataset.

[0028] In this step, during the training phase, the original high-resolution image is converted to a low-resolution image using bicubic interpolation. During the testing phase, the image is the original low-resolution image. After obtaining the low-resolution image, the Canny edge detector is used to generate an edge structure image and grayscale image corresponding to the low-resolution image. This example uses two public image datasets, CelebA-HQ and Paris Street View, in the experiments.

[0029] Step S102: construct a generative adversarial network with structural and texture feature extraction capabilities, wherein the generative adversarial network includes a generator and a discriminator. The generator includes a dense variable receptive field convolution block module and an upsampling module with a depth-separable deconvolution module. The discriminator includes a U-NET type network architecture.

[0030] In this step, the input of the generator is a dual-parallel branch structure with synchronized structural and texture features. Each branch structure is composed of multiple dense variable receptive field convolution block modules connected in series. Dual features are fused in the upsampling stage at the output end and sent to the depthwise separable deconvolution module for feature detail amplification to obtain a high-definition image as output.

[0031] The dense variable receptive field convolution block module is composed of three groups of dense convolution subunits with residual connections connected in series, wherein the first dense convolution subunit adopts a 1×1 convolution kernel, the second dense convolution subunit adopts a 3×3 convolution kernel, and the third dense convolution subunit adopts a 5×5 convolution kernel. The structure of the dense variable receptive field convolution block module is expressed as follows:

[0032] ,

[0033] Where, is the feature of the input dense variable receptive field convolution block module, is the feature output by the dense variable receptive field convolution block module, 、 、 and are weighted coefficients, is a dense convolution subunit;

[0034] Each dense convolution subunit is composed of multiple corresponding n×n convolutional layers and ReLU activation functions, and features are transferred across layers through dense connections. Dense connections enable the network to more effectively learn features at different levels and avoid information loss. The output of each layer not only serves as the input of the next layer, but is also directly passed to subsequent layers, thereby promoting the efficient fusion of features at different scales. Finally, the dense convolution subunit integrates the outputs of all layers through a convolution operation to generate the final output of the dense convolution unit, providing a richer feature representation for subsequent network modules. The expression for dense connection is:

[0035] ,

[0036] Where, 、 、 、 and Both are convolution features. Indicates that the convolution kernel is used The ordinary convolution operation, is the LeakyRelu activation function.

[0037] The convolution process of the depthwise separable deconvolution module includes depthwise deconvolution and pointwise convolution. In the depthwise deconvolution, each convolution kernel processes only one channel of the input feature map. In the pointwise convolution, the feature map is integrated according to the pointwise convolution to generate a new feature map. The expression of the depthwise separable convolution of the depthwise separable deconvolution module is:

[0038] ,

[0039] Where, is the feature of the input depth-wise separable deconvolution module, is the feature output by the depthwise separable deconvolution module, is point-wise convolution, To use the convolution kernel The depth deconvolution, Indicates that the convolution kernel is used The ordinary convolution operation, is the LeakyRelu activation function.

[0040] The discriminator consists of three layers of encoders, three layers of decoders and one layer of output convolution. It uses the skip connection between the encoder and decoder to enhance feature transfer, and maps the discriminant features to a two-dimensional plane by gradually extracting features. The discriminant features are normalized to the 0-1 range through the Sigmoid activation function.

[0041] Step S103: input the super-resolution image dataset into the generative adversarial network, train and generate weights of the corresponding model, and obtain an image super-resolution model based on the weights.

[0042] In this step, the combined loss function of the image super-resolution model includes pixel loss sub-function, perceptual loss sub-function and relative adversarial loss sub-function;

[0043] The expression for calculating the combined loss function is:

[0044] ,

[0045] Where, is the combined loss function, is the weight of the pixel loss sub-function, is the pixel loss subfunction, is the weight of the perceptual loss sub-function, is the perceptual loss subfunction, is the weight of the relative adversarial loss sub-function, is the relative adversarial loss subfunction;

[0046] The expression for calculating the pixel loss subfunction is:

[0047] ,

[0048] Where, is the mathematical expectation, The super-resolution image generated by the generator, is the real image of the corresponding size;

[0049] The expression for calculating the perceptual loss subfunction is:

[0050] ,

[0051] Where, For the VGG-19 network The activation map of the pooling layer, To use VGG network Extract features, To use VGG network Extract features;

[0052] The expression for calculating the relative adversarial loss subfunction is:

[0053] ,

[0054] Where, For the generator, is the discriminator, Generate an image discriminator for real images. To generate an image relative to the real image discriminator, For Find the mathematical expectation, For Find the mathematical expectation.

[0055] Step S104: input the image to be super-resolutioned into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0056] In summary, the method of the present application constructs a generative adversarial network with the ability to extract structural and texture features, inputs a super-resolution image dataset into the generative adversarial network, trains and generates weights for the corresponding model, obtains an image super-resolution model based on the weights, inputs the image to be super-resolution into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution. This improves the image super-resolution restoration effect by fusing the structural and texture features of the image and avoids detail loss. At the same time, it provides efficient performance optimization and a user-friendly interface, making the image processing process more convenient.

[0057] In one specific embodiment, the simulation experiments of this application were implemented in PyTorch, using an NVIDIA® Tesla® V100 GPU for training and testing. For ease of comparison, all low-resolution images were resized to 128×128 pixels and then upscaled to 512×512 pixels using a ×4 super-resolution method. The batch size was set to 4, and the Adam optimizer was used. The initial learning rate was 0.0002, and the fine-tuning learning rate was 0.0001.

[0058] The superior performance of our method is verified by comparison with three other representative image super-resolution algorithms of the same type: SRGAN, ESRGAN, and Real-ESRGAN. Image quality evaluation was performed using several common image processing metrics: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Learning Perceptual Patch Similarity (LPIPS). Table 1 shows comparative experimental results on the CelebA-HQ and Paris Street View datasets.

[0059] Table 1: Comparison of experimental results of data sets

[0060] ,

[0061] From the image super-resolution index results given in Table 1, it can be seen that in the image super-resolution enhancement process, the method of the present invention is superior to the comparison method. At the same time, the error between the pixel values of the experimental image and the real image is the smallest among all experimental methods, and the image super-resolution effect is the best.

[0062] See also Figure 2 , which shows a structural block diagram of an image super-resolution system based on structure and texture features of the present application.

[0063] like Figure 2 As shown, the image super-resolution system 200 includes a pre-processing module 210 , a construction module 220 , a training module 230 and an output module 240 .

[0064] Among them, the preprocessing module 210 is configured to preprocess the image dataset to obtain a super-resolution image dataset; the construction module 220 is configured to construct a generative adversarial network with the ability to extract structural and texture features, and the generative adversarial network includes a generator and a discriminator, the generator includes a dense variable receptive field convolution block module, an upsampling module with a depth-separable deconvolution module, and the discriminator includes a U-NET type network architecture; the training module 230 is configured to input the super-resolution image dataset into the generative adversarial network, train and generate the weights of the corresponding model, and obtain an image super-resolution model according to the weights; the output module 240 is configured to input the image to be super-resolution into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0065] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects also apply to Figure 2 The modules in it will not be described in detail here.

[0066] In other embodiments, embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the image super-resolution method based on structure and texture features in any of the above method embodiments;

[0067] As an embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0068] Preprocessing the image dataset to obtain a super-resolution image dataset;

[0069] Constructing a generative adversarial network with structural and texture feature extraction capabilities, the generative adversarial network includes a generator and a discriminator, the generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module, and the discriminator includes a U-NET type network architecture;

[0070] Inputting the super-resolution image dataset into the generative adversarial network, training and generating weights of the corresponding model, and obtaining an image super-resolution model based on the weights;

[0071] The image to be super-resolutioned is input into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0072] The computer-readable storage medium may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function; the data storage area may store data generated based on the use of the structure and texture feature-based image super-resolution system. Furthermore, the computer-readable storage medium may include high-speed random access memory and may also include storage, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include storage remote from the processor, and such remote storage may be connected to the structure and texture feature-based image super-resolution system via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0073] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 The example of the bus connection is taken. The memory 320 is the computer-readable storage medium mentioned above. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, implements the image super-resolution method based on structure and texture features of the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the image super-resolution system based on structure and texture features. The output device 340 may include a display device such as a display screen.

[0074] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0075] As an embodiment, the electronic device is applied to an image super-resolution system based on structural and texture features, and is used for a client, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0076] Preprocessing the image dataset to obtain a super-resolution image dataset;

[0077] Constructing a generative adversarial network with structural and texture feature extraction capabilities, the generative adversarial network includes a generator and a discriminator, the generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module, and the discriminator includes a U-NET type network architecture;

[0078] Inputting the super-resolution image dataset into the generative adversarial network, training and generating weights of the corresponding model, and obtaining an image super-resolution model based on the weights;

[0079] The image to be super-resolutioned is input into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

[0080] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An image super-resolution method based on structural and texture features, characterized in that: include: Preprocessing the image dataset to obtain a super-resolution image dataset; Constructing a generative adversarial network capable of extracting structural and texture features, the generative adversarial network includes a generator and a discriminator. The generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module. The discriminator includes a U-NET network architecture. The input of the generator is a dual-parallel branch structure with synchronized structural and texture features. Each branch structure is composed of multiple dense variable receptive field convolution block modules connected in series. Dual features are fused in the upsampling stage of the output and fed into a depthwise separable deconvolution module for feature detail amplification, resulting in a high-definition image as output. The dense variable receptive field convolution block module is composed of three groups of dense convolution subunits with residual connections connected in series, wherein the first dense convolution subunit adopts a 1×1 convolution kernel, the second dense convolution subunit adopts a 3×3 convolution kernel, and the third dense convolution subunit adopts a 5×5 convolution kernel. The structure of the dense variable receptive field convolution block module is expressed as follows: ， Where, is the feature of the input dense variable receptive field convolution block module, is the feature output by the dense variable receptive field convolution block module, 、 、 and are weighted coefficients, is a dense convolution subunit; Each dense convolution subunit consists of multiple corresponding n×n convolutional layers and ReLU activation functions, and features are transferred across layers through dense connections. The expression of dense connection is: ， Where, 、 、 、 and Both are convolution features. Indicates that the convolution kernel is used The ordinary convolution operation, LeakyRelu activation function; Inputting the super-resolution image dataset into the generative adversarial network, training and generating weights of the corresponding model, and obtaining an image super-resolution model based on the weights; The image to be super-resolutioned is input into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

2. The image super-resolution method based on structure and texture features according to claim 1, characterized in that: The combined loss function of the image super-resolution model includes a pixel loss sub-function, a perceptual loss sub-function and a relative adversarial loss sub-function; The expression for calculating the combined loss function is: ， Where, is the combined loss function, is the weight of the pixel loss sub-function, is the pixel loss subfunction, is the weight of the perceptual loss sub-function, is the perceptual loss subfunction, is the weight of the relative adversarial loss sub-function, is the relative adversarial loss subfunction; The expression for calculating the pixel loss subfunction is: ， Where, is the mathematical expectation, The super-resolution image generated by the generator, is the real image of the corresponding size; The expression for calculating the perceptual loss subfunction is: ， Where, is the activation map of the pooling layer in the VGG-19 network, To use VGG network Extract features, To use VGG network Extract features; The expression for calculating the relative adversarial loss subfunction is: ， Where, For the generator, is the discriminator, Generate an image discriminator for real images. To generate an image relative to the real image discriminator, For Find the mathematical expectation, For Find the mathematical expectation.

3. The image super-resolution method based on structure and texture features according to claim 1, characterized in that: The convolution process of the depthwise separable deconvolution module includes depthwise deconvolution and pointwise convolution. In the depthwise deconvolution, each convolution kernel processes only one channel of the input feature map. In the pointwise convolution, the feature map is integrated according to the pointwise convolution to generate a new feature map. The expression of the depthwise separable convolution of the depthwise separable deconvolution module is: ， Where, is the feature of the input depth-wise separable deconvolution module, is the feature output by the depthwise separable deconvolution module, is point-wise convolution, To use the convolution kernel The depth deconvolution of Indicates that the convolution kernel is used The ordinary convolution operation, is the LeakyRelu activation function.

4. The image super-resolution method based on structure and texture features according to claim 1, characterized in that: The discriminator includes three layers of encoders, three layers of decoders and one layer of output convolution. It uses jump connections between the encoder and decoder to enhance feature transfer, and maps the discriminant features to a two-dimensional plane by gradually extracting features. The discriminant features are normalized to the 0-1 range through the Sigmoid activation function.

5. An image super-resolution system based on structural and texture features, characterized in that: include: A preprocessing module is configured to preprocess the image dataset to obtain a super-resolution image dataset; A construction module is configured to construct a generative adversarial network with structural and texture feature extraction capabilities, wherein the generative adversarial network includes a generator and a discriminator, wherein the generator includes a dense variable receptive field convolution block module and an upsampling module with a depthwise separable deconvolution module, and the discriminator includes a U-NET type network architecture, wherein the input end of the generator is a dual parallel branch structure with synchronized structural and texture features, each branch structure is composed of multiple dense variable receptive field convolution block modules connected in series, and dual features are fused in the upsampling stage of the output end, and are jointly fed into the depthwise separable deconvolution module for feature detail amplification, thereby outputting a high-definition image; The dense variable receptive field convolution block module is composed of three groups of dense convolution subunits with residual connections connected in series, wherein the first dense convolution subunit adopts a 1×1 convolution kernel, the second dense convolution subunit adopts a 3×3 convolution kernel, and the third dense convolution subunit adopts a 5×5 convolution kernel. The structure of the dense variable receptive field convolution block module is expressed as follows: ， Where, is the feature of the input dense variable receptive field convolution block module, is the feature output by the dense variable receptive field convolution block module, 、 、 and are weighted coefficients, is a dense convolution subunit; Each dense convolution subunit consists of multiple corresponding n×n convolutional layers and ReLU activation functions, and features are transferred across layers through dense connections. The expression of dense connection is: ， Where, 、 、 、 and Both are convolution features. Indicates that the convolution kernel is used The ordinary convolution operation, LeakyRelu activation function; A training module is configured to input the super-resolution image dataset into the generative adversarial network, train and generate weights of the corresponding model, and obtain an image super-resolution model based on the weights; The output module is configured to input the image to be super-resolutioned into the image super-resolution model, and the image super-resolution model generates a high-definition image after super-resolution.

6. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images