A risk early warning method and system for a sludge dewatering machine based on image recognition

Abstract

The present invention relates to the field of risk warning, and particularly to a risk warning method and system for a sludge dewatering machine based on image recognition. The method includes: obtaining a grayscale image of the filter screen of the sludge dewatering machine at the current moment, screening out the blocked pixel points in the grayscale image, enhancing the blocked pixel points by using an unsharp masking algorithm to obtain an enhanced image, performing anomaly detection on the enhanced image, and sending a warning signal in response to the existence of an abnormal area in the enhanced image; the present invention has the effect of improving the accuracy of filter screen detection.

Description

Technical Field

[0001] The present invention relates to the field of risk early warning, and particularly to a risk early warning method and system for a sludge dehydrator based on image recognition. Background Art

[0002] A sludge dehydrator is a device that can remove moisture from sludge, reduce the volume and humidity of the sludge, and thus facilitate subsequent treatment. The sludge dehydrator is applied to the sewage treatment process in industries such as municipal, chemical, petroleum, printing and dyeing, food processing, and papermaking. The dehydrated sludge usually contains less moisture, which is convenient for transportation, stacking, or further utilization. During the operation of the sludge dehydrator, it often faces some potential faults and risks, and the most common one is the clogging of the filter screen. If the clogging of the filter screen is not detected and processed in time, it will lead to low working efficiency of the equipment and even affect the environment. Traditional equipment inspection depends on manual labor, and the manual inspection method has a large workload, and there are problems of untimely and inaccurate detection, and it is easy to miss potential risks. The risk early warning system based on image recognition can monitor the working state of the sludge dehydrator in real time and automatically monitor the equipment to timely detect the occurrence of filter screen clogging. The potential clogging phenomenon on the surface of the sludge dehydrator filter screen often appears as blurred spots or unclear boundaries in the image.

[0003] Chinese patent document with publication number CN107301627B discloses a dynamic image unsharp masking artifact removal and enhancement method, including: decomposing the dynamic image to be processed by using the unsharp masking USM enhancement algorithm to obtain a high-frequency detail image and a low-frequency contour image; generating a detail enhancement artifact removal mask and a dynamic range compression artifact removal mask according to the high-frequency detail image; using the detail enhancement artifact removal mask and the dynamic range compression artifact removal mask to perform artifact removal and detail enhancement processing on the high-frequency detail image to obtain a high-frequency detail image after artifact removal and detail enhancement, performing dynamic range compression on the low-frequency contour image to obtain a compressed low-frequency contour image; synthesizing the high-frequency detail image after artifact removal and detail enhancement and the compressed low-frequency contour image to obtain a dynamic image after artifact removal.

[0004] Using the unsharp masking algorithm can make the image clearer and the details more obvious by enhancing the high-frequency details in the image. Since there will be a phenomenon of sewage droplets adhering to the surface of the sludge dehydrator filter screen during the operation process, the sewage droplets and the potential clogging phenomenon on the filter screen surface produce similar effects in the image. The unsharp masking algorithm enhances the clarity of the image by emphasizing the edges and details of the image. Due to the presence of sewage droplets, the unsharp algorithm will simultaneously sharpen and enhance the edges of the sewage droplets and the edges of the filter screen clogging area in the image, resulting in misdetection of sewage droplets as filter screen clogging and causing misjudgment, resulting in low accuracy of filter screen clogging detection. Summary of the Invention

[0005] To solve the problem of low accuracy in filter screen detection, the present invention provides a risk warning method and system for a sludge dewatering machine based on image recognition.

[0006] In a first aspect, the present invention provides a risk warning method for a sludge dewatering machine based on image recognition, adopting the following technical solution:

[0007] Obtain a grayscale image of the filter screen of the sludge dewatering machine at the current moment, screen out the blocked pixel points in the grayscale image, use the unsharp masking algorithm to enhance the blocked pixel points to obtain an enhanced image, perform anomaly detection on the enhanced image, and issue a warning signal in response to the existence of an abnormal area in the enhanced image;

[0008] Among them, the method for screening out the blocked pixel points in the grayscale image is: calculate the anomaly index of each pixel point, and the anomaly index represents the degree of difference between the corresponding pixel point and the rest of the pixel points; calculate the blockage index of each pixel point, and the blockage index represents the possibility of blockage in the corresponding pixel point area, and the blockage index is positively correlated with the anomaly index; use the pixel points with a blockage index greater than a preset blockage threshold as the blocked pixel points.

[0009] By calculating the potential blockage index of each pixel point, it is possible to understand the situation of blockage in the grayscale image, provide a theoretical basis for the enhancement process of the unsharp masking algorithm, ensure that the unsharp masking algorithm only enhances the potential blocked areas in the image, reduce the interference caused by sewage droplets or other irrelevant factors during image enhancement, and improve the accuracy of filter screen detection.

[0010] Preferably, the expression of the anomaly index is:

[0011] ;

[0012] In the formula, represents the anomaly index of the m-th pixel point, represents the maximum grayscale value of the pixel points in the grayscale image, represents the grayscale value of the m-th pixel point, represents the grayscale mean value of the m-th pixel point in the grayscale image at the historical moment, is a hyperparameter, and norm represents a normalization function.

[0013] Calculating the anomaly index through multiple dimensions improves the accuracy of the calculation result, and using the anomaly index can initially determine whether the corresponding pixel point area is a potential blocked area.

[0014] Preferably, the method further includes:

[0015] Construct a window centered on any pixel point, calculate the absolute value of the difference in the anomaly index between other pixel points in the window area and the central pixel point, and in response to the absolute value of the difference being less than a preset threshold, regard the corresponding pixel point as the first pixel point; construct a window centered on the first pixel point, and repeat the calculation of the absolute value of the difference in the anomaly index between other pixel points in the window area and the central pixel point until the absolute value of the difference in the anomaly index between all pixel points in the window area and the central pixel point is greater than or equal to the preset threshold; regard the area composed of all the first pixel points as the area to which the corresponding pixel point belongs; perform edge detection on the area to which it belongs to obtain the edge of the area to which it belongs, and calculate the chain code of the edge.

[0016] Preferably, the expression of the clogging index is:

[0017] ;

[0018] In the formula, represents the potential clogging index of the m-th pixel point, represents the anomaly index of the m-th pixel point, represents the information entropy of the gradient magnitude of all edge pixel points in the area to which the m-th pixel point belongs, represents the sum of the absolute values of the differences between adjacent two chain code values in the chain code in the area to which the m-th pixel point belongs, and norm represents the normalization function.

[0019] Through the clogging index, it can finally be determined whether the corresponding pixel point area is a clogged area, so that the image can be enhanced specifically and the enhancement effect can be improved.

[0020] Preferably, the expression of the clogging index is:

[0021] ;

[0022] In the formula, represents the potential clogging index of the m-th pixel point, represents the anomaly index of the m-th pixel point, represents the information entropy of the cosine value of the angle between the gradient direction of all edge pixel points in the area to which the m-th pixel point belongs and the horizontal direction, represents the sum of the absolute values of the differences between adjacent two chain code values in the chain code in the area to which the m-th pixel point belongs, and norm represents the normalization function.

[0023] The clogging index is calculated through multiple dimensions, which improves the accuracy of the calculation result of the clogging index and facilitates the judgment of whether the corresponding pixel point is a clogged area.

[0024] Preferably, use the Sobel operator to perform edge detection on the area to which it belongs to obtain the edge of the area to which it belongs.

[0025] Preferably, the method for enhancing blocked pixel points using the unsharp masking algorithm is as follows:

[0026] Blur the grayscale image to obtain a blurred image, and perform a difference between the grayscale image and the blurred image to obtain a difference image; in the difference image, take the pixel points corresponding to the blocked pixel points in the grayscale image as enhanced pixel points, and then multiply the enhanced pixel points by a preset enhancement factor; add the difference image and the grayscale image to obtain an enhanced image.

[0027] By selectively enhancing the pixel points in the grayscale image, the enhancement effect of the grayscale image is improved, and interference caused by sewage droplets and other substances during image enhancement is reduced.

[0028] In a second aspect, the present invention provides a risk warning system for a sludge dewatering machine based on image recognition, adopting the following technical solution:

[0029] A risk warning system for a sludge dewatering machine based on image recognition, including a processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a risk warning method for a sludge dewatering machine based on image recognition as described above is implemented.

[0030] The beneficial effect is: generating a computer program for the above-mentioned risk warning method for a sludge dewatering machine based on image recognition and storing it in the memory to be loaded and executed by the processor. Thus, a system is made according to the memory and the processor, which is convenient to use.

[0031] The present invention has the following technical effects:

[0032] By calculating the potential blockage index of each pixel point, it is convenient to understand the blockage situation in the grayscale image, so as to ensure that the unsharp masking algorithm only enhances the potential blocked areas in the image specifically, reducing interference caused by sewage droplets or other irrelevant factors during image enhancement and improving the accuracy of subsequent filter screen detection. Description of the Drawings

[0033] By reading the following detailed description with reference to the drawings, the above-mentioned and other purposes, features, and advantages of the exemplary embodiments of the present invention will become easy to understand. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0034] Figure 1 It is a flowchart of a risk warning method for a sludge dewatering machine based on image recognition according to the present invention. Detailed Embodiments

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0036] It should be understood that when terms such as "first" and "second" are used in the claims, specifications, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "including" and "comprising" used in the specifications and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0037] An embodiment of the present invention discloses a risk warning method for a sludge dewatering machine based on image recognition. Referring to Figure 1 , the following steps are included, specifically as follows:

[0038] S1: Obtain the grayscale image of the filter screen of the sludge dewatering machine at the current moment.

[0039] Use a high-definition camera to capture the surface image of the filter screen of the sludge dewatering machine, and then perform grayscale processing on the surface image of the filter screen of the sludge dewatering machine to obtain the grayscale image of the surface image of the filter screen of the sludge dewatering machine. Use the FCN semantic segmentation model to extract the filter screen area in the grayscale image for analyzing the pixel points in the filter screen area.

[0040] S2: Screen out the blocked pixel points in the grayscale image.

[0041] The screening method is as follows:

[0042] S201: Calculate the anomaly index of each pixel point. The anomaly index represents the degree of difference between the corresponding pixel point and the other pixel points.

[0043] The expression of the anomaly index is:

[0044] ;

[0045] In the formula, represents the anomaly index of the m-th pixel point, represents the maximum grayscale value of the pixel points in the grayscale image, represents the grayscale value of the m-th pixel point, represents the grayscale mean value of the m-th pixel point in the grayscale image at the historical moment, is a hyperparameter, , setting hyperparameters is to prevent the corresponding factor terms from being 0, and norm represents the normalization function. Exemplarily, represents the grayscale mean of the m-th pixel in 10 grayscale images at historical moments. It should be noted that represents the anomaly index of the m-th pixel in the grayscale image at the current moment.

[0046] In the formula The larger it is, the smaller the grayscale value of the m-th pixel in the grayscale image of the filter area, indicating that the area where the pixel is located is more likely to be a potential clogging area, and its anomaly index is larger; in the formula The larger it is, the more obvious the change in the grayscale value of the m-th pixel at multiple moments, indicating that the area where the m-th pixel is located is more likely to be a potential clogging area, and its anomaly index is larger.

[0047] The potential clogging phenomenon in the filter area usually refers to the filter holes being clogged by impurities, dust or other substances, and the clogged substances cause the grayscale value of the potential clogging area to decrease. However, there will also be some normal areas with reduced grayscale values on the filter surface. As the usage time goes by, the dirt in the filter will gradually accumulate, the degree of clogging will change, and then the grayscale value in the image will change, resulting in different grayscale values at the same position in different frames. Therefore, when analyzing the anomaly index of each pixel, the smaller the grayscale value of a pixel and the more obvious the change in its grayscale value at multiple moments, the more likely it is that the pixel belongs to a potential clogging area, and its anomaly index is larger.

[0048] S202: Calculate the clogging index of each pixel. The clogging index represents the possibility of clogging in the corresponding pixel area. The clogging index is positively correlated with the anomaly index. Pixels with a clogging index greater than the preset clogging threshold are regarded as clogging pixels.

[0049] In one embodiment, a window is constructed centered on any pixel point, and the absolute value of the difference in the anomaly index between other pixel points in the window area and the central pixel point is calculated. In response to the absolute value of the difference being less than a preset threshold, the corresponding pixel point is taken as the first pixel point; a window is constructed centered on the first pixel point, and the absolute value of the difference in the anomaly index between other pixel points in the window area and the central pixel point is repeatedly calculated until the absolute value of the difference in the anomaly index between all pixel points in the window area and the central pixel point is greater than or equal to the preset threshold; the area composed of all the first pixel points is taken as the area to which the corresponding pixel point belongs; the Sobel operator is used to perform edge detection on the area to which it belongs to obtain the edge of the area to which it belongs, and the chain code of the edge is calculated. The chain code is a simplified method for representing boundaries or contours in an image. The chain code effectively represents the shape by describing the directional relationship between consecutive points on the image contour. The present invention uses an 8-neighborhood chain code, and the calculation of the chain code is prior art and will not be elaborated here. The threshold is set manually according to the actual situation. Exemplarily, the threshold is 0.01.

[0050] Exemplarily, a 3×3 window is constructed centered on the pixel point In the window area, for the pixel point the absolute value of the difference in the anomaly index from the central pixel point is less than the threshold 0.01, then the pixel point is taken as the first pixel point; a 3×3 window is constructed centered on the pixel point In the window area, if the first pixel point is found, then continue to construct a 3×3 window centered on the pixel point If the first pixel point is not found in the window area, stop searching. The found first pixel points , , The area where they are located is taken as the area to which the pixel point belongs.

[0051] In one embodiment, a circular area with a radius of r is constructed centered on any pixel point, and the circular area is taken as the area to which the corresponding pixel point belongs; the Sobel operator is used to perform edge detection on the area to which it belongs to obtain the edge of the area to which it belongs, and the chain code of the edge is calculated.

[0052] In one embodiment, the expression for the clogging index is:

[0053] ;

[0054] In the formula, represents the potential clogging index of the m-th pixel point, represents the anomaly index of the m-th pixel point, The information entropy representing the gradient amplitude of all edge pixels in the region to which the m-th pixel belongs is obtained by calculating the gradient amplitude using the Sobel operator. The calculation method of the information entropy is a prior art and will not be described in detail here. It represents the sum of the absolute values ​​of the differences between the two adjacent chain code values ​​in the chain code of the area to which the mth pixel belongs. If there are multiple chain codes, calculate the absolute value of each chain code. , take its maximum value, norm represents the normalization function.

[0055] In the formula, The larger the value is, the greater the anomaly index of the m-th pixel in terms of gray value expression and gray value change analysis in multiple gray images, and the greater the possibility that the pixel belongs to a potential blockage area.

[0056] The larger it is, the more chaotic the gradient amplitude change of the edge pixels in the area to which the m-th pixel belongs is, which means that the possibility that the area to which the m-th pixel belongs belongs to a potential blockage area is greater, and the possibility that it belongs to a sewage drop area is smaller, and the corresponding m-th pixel has a larger potential blockage index.

[0057] The larger it is, the more dramatic the change in the gradient direction between all adjacent edge pixels in the area to which the m-th pixel belongs is. This means that the edge of the area to which the m-th pixel belongs is more chaotic and the texture is more complex. The more complex the direction of the gradient change is, the greater the possibility that the area to which the m-th pixel belongs is a potential blockage area, and the smaller the possibility that it belongs to a sewage drop area. Therefore, the potential blockage index of the m-th pixel is also greater.

[0058] The blocking threshold is set manually according to the actual situation. For example, the blocking threshold is 0.55, and the pixels with a blocking index greater than 0.55 are regarded as blocked pixels.

[0059] In the actual operation of the sludge dewatering machine, the edges of the potential blocking areas in the filter area are more chaotic and the texture is more complex, while the texture of the sewage drop area is smoother and the edges are clearer and more regular. Therefore, by analyzing the texture characteristics of the pixels in the area to which each pixel belongs in the filter area, the anomaly index of the pixel is optimized to obtain the potential blocking index of the corresponding pixel. Among them, the more chaotic the gradient amplitude change in the area to which the pixel belongs and the more complex the gradient change direction, the greater the possibility that the area to which the corresponding pixel belongs is a potential blocking area, and the greater the blocking index of the pixel.

[0060] In one embodiment, the expression of the congestion index is:

[0061] ;

[0062] In the formula, represents the potential clogging index of the m-th pixel point represents the anomaly index of the m-th pixel point represents the information entropy of the cosine value of the angle between the gradient directions of all edge pixel points in the region to which the m-th pixel point belongs and the horizontal direction represents the sum of the absolute values of the differences between two adjacent chain code values in the chain code within the region to which the m-th pixel point belongs, and norm represents the normalization function

[0063] The larger it is, the more chaotic the change in the gradient amplitude of the edge pixel points in the region to which the m-th pixel point belongs, the greater the possibility that the region to which the m-th pixel point belongs is a potential clogging region, the smaller the possibility of belonging to the sewage droplet region, and the larger the potential clogging index of the corresponding m-th pixel point

[0064] S3: Use the unsharp masking algorithm to enhance the clogged pixel points to obtain an enhanced image, perform anomaly detection on the enhanced image, and issue a warning signal in response to the presence of an abnormal region in the enhanced image

[0065] Use the Gaussian blur method to blur the grayscale image to obtain a blurred image, subtract the blurred image from the grayscale image to obtain a difference image; in the difference image, take the pixel points corresponding to the clogged pixel points in the grayscale image as enhanced pixel points, and then multiply the enhanced pixel points by a preset enhancement factor; add the difference image and the grayscale image to obtain an enhanced image

[0066] Exemplarily ;

[0067] In the formula represents the pixel point in the difference image represents the pixel point in the grayscale image represents the pixel point in the blurred image represents the enhanced pixel point in the difference image represents the pixel point in the enhanced image, x, y represent the abscissa and ordinate of the pixel point in the corresponding image, k represents the enhancement factor, and the enhancement factor is set manually according to the actual situation. Exemplarily, k = 1.8

[0068] In one embodiment, use the template matching method to perform anomaly detection on the clogged region in the enhanced image, determine whether there is a clogged region in the filter screen region, and issue a warning signal when there is a clogged region in the enhanced image. The warning signal is one or a combination of voice prompt, information prompt, and signal light prompt. The template matching method is a prior art, and the specific steps are not described here

[0069] In one embodiment, a convolutional neural network model is used to detect the enhanced image to check whether there is a blocked area in the filter screen area.

[0070] By calculating the potential blockage index of each pixel point, the situation of blockage in the grayscale image can be understood, providing a theoretical basis for the enhancement process of the unsharp masking algorithm, ensuring that the unsharp masking algorithm only enhances the potentially blocked areas in the image, reducing the interference caused by sewage droplets or other irrelevant factors during image enhancement, and improving the accuracy of filter screen detection.

[0071] An embodiment of the present invention also discloses a risk warning system for a sludge dewatering machine based on image recognition, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a risk warning method for a sludge dewatering machine based on image recognition according to the present invention is implemented.

[0072] The above system further includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0073] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0074] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted during the practice of the present invention.

[0075] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A sludge dewatering machine risk warning method based on image recognition, characterized in that: Includes steps: Obtaining a grayscale image of the filter screen of the sludge dewatering machine at the current moment, filtering out blocked pixels in the grayscale image, enhancing the blocked pixels using an unsharp masking algorithm to obtain an enhanced image, performing anomaly detection on the enhanced image, and issuing an early warning signal in response to the presence of an abnormal area in the enhanced image; Among them, the method for screening out blocked pixels in the grayscale image is as follows: calculating the anomaly index of each pixel, the anomaly index indicates the degree of difference between the corresponding pixel and the remaining pixels; calculating the blocking index of each pixel, the blocking index indicates the possibility of blocking in the corresponding pixel area, and the blocking index is positively correlated with the anomaly index; taking pixels whose blocking index is greater than a preset blocking threshold as blocked pixels; building a window with any pixel as the center, calculating the absolute value of the difference between the anomaly index of other pixels in the window area and the central pixel, and in response to the absolute value of the difference being less than a preset threshold, taking the corresponding pixel as the first pixel; building a window with the first pixel as the center, repeatedly calculating the absolute value of the difference between the anomaly index of other pixels in the window area and the central pixel, until the absolute value of the difference between the anomaly index of all pixels in the window area and the central pixel is greater than or equal to the preset threshold; taking the area composed of all first pixels as the area to which the corresponding pixel belongs; performing edge detection on the area to which it belongs to obtain the edge of the area to which it belongs, and calculating the chain code of the edge; The expression of the congestion index is: ； In the formula, represents the potential blocking index of the m-th pixel, represents the anomaly index of the mth pixel, The information entropy representing the gradient amplitude of all edge pixels in the region to which the m-th pixel belongs, It represents the sum of the absolute values ​​of the differences between two adjacent chain code values ​​in the chain code in the area to which the m-th pixel belongs, and norm represents the normalization function.

2. The sludge dewatering machine risk early warning method based on image recognition according to claim 1 is characterized in that: The expression of the anomaly index is: ； In the formula, represents the anomaly index of the mth pixel, Indicates the maximum grayscale value of a pixel in a grayscale image. Represents the gray value of the mth pixel, Represents the grayscale mean value of the mth pixel in the grayscale image at the historical moment, is a hyperparameter, and norm represents the normalization function.

3. The sludge dewatering machine risk early warning method based on image recognition according to claim 1 is characterized in that: The expression of the congestion index is: ； In the formula, represents the potential blocking index of the m-th pixel, represents the anomaly index of the mth pixel, The information entropy of the cosine value of the angle between the gradient direction and the horizontal direction of all edge pixels in the region to which the m-th pixel belongs, It represents the sum of the absolute values ​​of the differences between two adjacent chain code values ​​in the chain code in the area to which the m-th pixel belongs, and norm represents the normalization function.

4. The sludge dewatering machine risk early warning method based on image recognition according to claim 1 is characterized in that: Use the Sobel operator to perform edge detection on the area to obtain the edge of the area.

5. The sludge dewatering machine risk early warning method based on image recognition according to claim 1 is characterized in that: The method of enhancing blocked pixels using the unsharp mask algorithm is: The grayscale image is blurred to obtain a blurred image, and the grayscale image and the blurred image are differentiated to obtain a difference image; in the difference image, the pixel points corresponding to the blocked pixel points in the grayscale image are used as enhanced pixel points, and then the enhanced pixel points are multiplied by a preset enhancement factor; The difference image is added to the grayscale image to obtain the enhanced image.

6. A sludge dewatering machine risk warning system based on image recognition, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a sludge dewatering machine risk warning method based on image recognition according to any one of claims 1 to 5 is implemented.

Images