An image processing method, device and computer readable storage medium

Abstract

Embodiments of the present application disclose an image processing method, which comprises: collecting a plurality of sample images of a tongue of a human body at different collection angles; performing region segmentation on the sample images based on pixel information of pixel points of the sample images to obtain a plurality of first images; determining a target tongue image based on the plurality of first images; and determining a constitution category of the human body based on pixel information of the target tongue image. In this way, the constitution category of the human body is determined based on the pixel information of the target tongue image, thereby avoiding the influence of a background in an image of the tongue of the human body in the related art, and improving the accuracy of determining the constitution category of the human body. Embodiments of the present application also disclose an image processing device and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to image processing technology in the field of image processing, and more particularly to an image processing method, apparatus and computer-readable storage medium. Background Technology

[0002] Traditional Chinese medicine tongue analysis determines a person's constitution by observing changes in the color and shape of the tongue. During online consultations, images of the tongue can be collected to determine the constitution. However, the background outside the tongue area in the collected images can affect the accuracy of the determined constitution. Summary of the Invention

[0003] To address the aforementioned technical problems, embodiments of this application provide an image processing method, device, and computer-readable storage medium, which solves the problem of inaccurate determination of human body constitution categories.

[0004] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0005] An image processing method, the method comprising:

[0006] Multiple sample images of the human tongue were acquired from different acquisition angles.

[0007] Based on the pixel information of the pixel points in the sample image, the sample image is segmented into regions to obtain multiple first images;

[0008] Based on the plurality of first images, the target tongue image is determined;

[0009] Based on the pixel information of the target tongue image, the body constitution category of the human body is determined.

[0010] In the above scheme, acquiring multiple sample images of the human tongue from different acquisition angles includes:

[0011] Multiple images containing information about the human tongue are acquired from different acquisition angles;

[0012] From the image to be processed, determine the non-tongue region image and the tongue region image;

[0013] Based on the non-tongue region image and the tongue region image, the location of the tongue region of the human body is determined;

[0014] Based on the location of the tongue region of the human body, multiple sample images of the tongue of the human body are acquired at different acquisition angles.

[0015] In the above scheme, the step of performing region segmentation on the sample image based on the pixel information of the sample image to obtain multiple first images includes:

[0016] Obtain the number of pixels in the sample image and the pixel value of each pixel in the sample image;

[0017] Based on the number of pixels in the sample image and a first size range, a plurality of second images are determined from the sample image;

[0018] Obtain the number of pixels in each of the second images and the pixel value of each pixel in the second image;

[0019] The color information of the sample image is determined based on the number of pixels in the plurality of second images and the pixel values ​​of the pixels in the plurality of second images;

[0020] Based on the color information and pixel values ​​of the sample images, the sample images are segmented into regions to determine the plurality of first images.

[0021] In the above scheme, the step of segmenting the sample image into regions based on the color information and pixel values ​​of the pixels in the sample image to determine the plurality of first images includes:

[0022] Based on the color information and color level precision coefficient of the sample image, the number of color levels included in the sample image is determined;

[0023] The color level of the pixel in the sample image is determined based on the color level number, the color information of the sample image, and the pixel value of the pixel in the sample image.

[0024] Based on the color levels of the pixels in the sample image, the sample image is segmented into regions to determine the plurality of first images.

[0025] In the above scheme, determining the color level of a pixel in the sample image based on the color level number, the color information of the sample image, and the pixel value of the pixel in the sample image includes:

[0026] The color value of the pixel is determined based on the pixel value of the pixel and the color information of the sample image;

[0027] The color level of the pixels in the sample image is determined based on the color value of the pixel and the level of the color level.

[0028] In the above scheme, the step of segmenting the sample image into regions based on the color levels of the pixels in the sample image to determine the plurality of first images includes:

[0029] Based on the color level and second size range of the pixels in the sample image, the sample image is segmented into regions to determine multiple third images with the same color level of the pixels;

[0030] Determine the color distance between each edge pixel in the third image and its adjacent pixels, as well as the average color distance of the pixels in the third image; wherein, the pixels adjacent to the edge pixel are the pixels in the sample image that are outside the third image.

[0031] The plurality of first images are determined based on the color distance, the average color distance, and the third image.

[0032] In the above scheme, determining the plurality of first images based on the color distance, the average color distance, and the third image includes:

[0033] A first sub-image is determined from the plurality of third images whose color distance is less than the average color distance, and a fourth image is determined based on the first sub-image and the pixels adjacent to the edge pixels.

[0034] Determine a second sub-image from the plurality of third images whose color distance is greater than or equal to the average color distance;

[0035] The plurality of first images are determined based on the fourth image and / or the second sub-image.

[0036] In the above scheme, determining the target tongue image based on the plurality of first images includes:

[0037] Obtain the distance between the plurality of first images;

[0038] Based on the distance and the plurality of first images, a plurality of first candidate region images are determined;

[0039] Based on the multiple first candidate region images, the target tongue image is determined.

[0040] In the above scheme, obtaining the distance between the plurality of first images includes:

[0041] Based on the position of each first image in the sample images, a region adjacency table is constructed.

[0042] Obtain the color distance between the m-th first image and the n-th first image, and the edge distance between the m-th first image and the n-th first image; where m and n are both positive integers;

[0043] Based on the color distance, the edge distance, and the region adjacency table, the distance between the m-th first image and the n-th first image is determined.

[0044] In the above scheme, determining multiple first candidate region images based on the distance and the multiple first images includes:

[0045] Based on the distance, the plurality of first images are processed to obtain a plurality of second candidate region images;

[0046] The multiple second candidate region images are filtered to determine the first candidate region image.

[0047] In the above scheme, the step of filtering the plurality of second candidate region images to determine the first candidate region image includes:

[0048] The second candidate region images are grouped based on their color levels to obtain multiple groups of second candidate region images; wherein, the second candidate region images in the same group have the same color level.

[0049] Determine the number of images for each group of second candidate regions;

[0050] Based on the number of second candidate region images in each group, the multiple second candidate region images are filtered to determine the first candidate region image.

[0051] An image processing device, the device comprising: a processor, a memory, and a communication bus;

[0052] The communication bus is used to realize the communication connection between the processor and the memory;

[0053] The processor is used to execute the image processing program stored in the memory to perform the following steps:

[0054] Multiple sample images of the human tongue were acquired from different acquisition angles.

[0055] Based on the pixel information of the pixel points in the sample image, the sample image is segmented into regions to obtain multiple first images;

[0056] Based on the plurality of first images, the target tongue image is determined;

[0057] Based on the pixel information of the target tongue image, the body constitution category of the human body is determined.

[0058] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the image processing method described above.

[0059] The image processing method, device, and computer-readable storage medium provided in this application acquire multiple sample images of the human tongue from different acquisition angles; perform region segmentation on the sample images based on the pixel information of the pixel points to obtain multiple first images; determine a target tongue image based on the multiple first images; and determine the human body constitution category based on the pixel information of the target tongue image. Thus, determining the human body constitution category based on the pixel information of the target tongue image avoids the influence of the background in the human tongue image in related technologies, improving the accuracy of determining the human body constitution category. Attached Figure Description

[0060] Figure 1 A schematic flowchart of an image processing method provided in an embodiment of this application;

[0061] Figure 2 A flowchart illustrating an image processing method provided in another embodiment of this application;

[0062] Figure 3 A schematic flowchart illustrating yet another image processing method provided in another embodiment of this application;

[0063] Figure 4 A schematic diagram of a target tongue image provided for another embodiment of this application;

[0064] Figure 5 This is a schematic diagram of the structure of the image processing device provided in one embodiment of this application. Detailed Implementation

[0065] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0066] This application provides an image processing method applied to an image processing device, such as... Figure 1 As shown, the method includes the following steps:

[0067] Step 101: Collect multiple sample images of the human tongue from different acquisition angles.

[0068] The sample images are those showing only the tongue of a human body.

[0069] In this embodiment of the application, the image processing device can be a device with image acquisition and processing functions; the image processing device can scan the tongue of a human body, determine the position of the tongue, and based on the position of the tongue, acquire images of the tongue of the human body from multiple different angles, and filter the acquired images of the tongue of the human body to obtain multiple sample images of the tongue of the human body.

[0070] In one feasible implementation, the image processing device can analyze images of the human tongue, determine the clarity of each image of the human tongue, sort the multiple tongue images from highest to lowest clarity, and determine a preset number of sample images with higher clarity from the sorted multiple tongue images; alternatively, it can determine images with a clarity greater than the preset clarity threshold from the sorted multiple tongue images as sample images based on a preset clarity threshold.

[0071] It should be noted that the number of sample images can be determined according to the actual application, and the embodiments of this application do not limit the number of sample images.

[0072] Step 102: Perform region segmentation on the sample image based on the pixel information of the pixel points to obtain multiple first images.

[0073] The pixel information of a pixel includes, but is not limited to, the number of pixels, the position of the pixels, and the pixel value of the pixels.

[0074] In this embodiment of the application, the image processing device can analyze the sample image, determine the pixel information of the pixels in the sample image, and segment the sample image based on the pixel information to obtain multiple first images.

[0075] In one feasible implementation, the image processing device can analyze the size of the sample image, determine the number of pixels corresponding to the length and width of each sample image, and determine the number of pixels in the sample image based on the number of pixels corresponding to the length and width of the sample image.

[0076] Step 103: Determine the target tongue image based on multiple first images.

[0077] The target tongue image is an image with multiple target regions; the target regions include, but are not limited to, the tongue coating region and the tongue tip region.

[0078] In this embodiment of the application, multiple first images can be filtered based on the pixel information of the first image, and the filtered images can be combined to obtain a target tongue image.

[0079] Step 104: Determine the body constitution category of the human body based on the pixel information of the target tongue image.

[0080] Among them, the body constitution categories include, but are not limited to, Qi deficiency constitution, Yang deficiency constitution, Yin deficiency constitution, damp-heat constitution, phlegm-dampness constitution, blood stasis constitution, and Qi deficiency constitution.

[0081] In this embodiment, a tongue image analysis model can be trained using an artificial intelligence recognition algorithm based on a large number of sample images. The target tongue image can be input into the model, allowing it to analyze the pixel information of the target area and output the individual's constitution category. This enables online determination of a person's constitution category, eliminating the need for users to visit a hospital and improving the efficiency of constitution classification.

[0082] In one feasible implementation, each target region in the target tongue image is assigned a corresponding identifier. The tongue image analysis model can determine the region where the target identifier is located from multiple target regions in the target tongue image based on the target identifier, and analyze the image of the region where the target identifier is located to determine the body constitution category of the human body. This avoids interference from the image of the region outside the region where the target identifier is located in the target tongue image on the determination of the body constitution category, thereby improving the accuracy of determining the body constitution category of the human body.

[0083] It should be noted that when determining body constitution category, the tongue is not identified as a whole, but rather based on multiple target regions divided within the target tongue image. This improves the accuracy of identifying the body constitution category by recognizing the target regions. Furthermore, the target tongue image does not contain any regions other than the tongue itself, further improving the accuracy of tongue image analysis based on the target tongue image and reducing the computational load for determining the body constitution category, thus improving processing efficiency. Additionally, this application uses multiple sample images to determine the target tongue image, avoiding the need to process only one sample image, thereby increasing the precision of the determined target tongue image and further enhancing the accuracy of determining the body constitution category.

[0084] The image processing method provided in this application acquires multiple sample images of the human tongue from different acquisition angles; performs region segmentation on the sample images based on the pixel information of the pixel points to obtain multiple first images; determines a target tongue image based on the multiple first images; and determines the human body constitution category based on the pixel information of the target tongue image. In this way, determining the human body constitution category based on the pixel information of the target tongue image avoids the influence of the background in the human tongue image in related technologies and improves the accuracy of determining the human body constitution category.

[0085] Based on the foregoing embodiments, this application provides an image processing method, referring to... Figure 2 The method includes the following steps:

[0086] Step 201: The image processing device acquires multiple images containing information about the tongue of a human body from different acquisition angles.

[0087] The image to be processed refers to an image containing the tongue of a human body.

[0088] In this embodiment, the image acquisition device can acquire multiple images of the human tongue from different angles using its image acquisition component. During acquisition, the distance between the human tongue and the image acquisition component determines whether to acquire the images. When the distance is less than a first preset distance, the image acquisition component can acquire multiple images containing human tongue information from different angles. When the distance is greater than the first preset distance, a prompt can be issued to remind the user to adjust their position. Alternatively, when the distance is greater than the first preset distance but less than a second preset distance, the image acquisition component can adjust its position using a telescopic device on the image processing device. When the adjusted distance between the image acquisition component and the human tongue is less than the first preset distance, the image acquisition component can acquire multiple images containing human tongue information from different angles.

[0089] Step 202: The image processing device determines the non-tongue region image and the tongue region image from the image to be processed.

[0090] In this embodiment of the application, the image processing device can perform region segmentation on the image to be processed based on the pixel values ​​of the pixels in the image to be processed, and segment the non-tongue region image and the tongue region image from the image to be processed.

[0091] In one feasible implementation, a tongue recognition model can be used to recognize and process the image to be processed, determine the tongue region from the image to be processed, and then extract the image where the tongue region is located from the image to be processed based on the determined tongue region, i.e., the tongue region image, and take the image outside the tongue region in the image to be processed as the non-tongue region image.

[0092] Step 203: The image processing device determines the location of the tongue region of the human body based on the non-tongue region image and the tongue region image.

[0093] In this embodiment of the application, the initial position of the human tongue can be obtained by analyzing the non-tongue region image and the tongue region image determined in each image to be processed. Finally, the position of the human tongue region can be determined based on the initial position of the tongue determined in each image to be processed.

[0094] Step 204: Based on the location of the tongue region of the human body, the image processing device acquires multiple sample images of the tongue of the human body at different acquisition angles.

[0095] In this embodiment of the application, the image processing device can acquire images of the tongue region at different acquisition angles based on the determined position of the tongue region of the human body, thereby obtaining multiple sample images.

[0096] In one feasible implementation, such as Figure 3 As shown, the image processing device can acquire multiple images containing human tongue information from different acquisition angles, process the multiple images to determine the location of the human tongue region, illuminate the area outside the tongue region so that the light is projected onto the tongue region through diffuse reflection, and take multiple sample images of the human tongue region from multiple angles to obtain multiple sample images of the human tongue.

[0097] Step 205: The image processing device acquires the number of pixels in the sample image and the pixel value of each pixel in the sample image.

[0098] In this embodiment, the image processing device can acquire the size of the sample image and determine the number of pixels in the sample image based on the size. The image processing device can also analyze the sample image to determine the pixel value of each pixel. The pixel value can also be referred to as the pixel color value, and is typically represented by R, G, and B.

[0099] Step 206: The image processing device determines a plurality of second images from the sample image based on the number of pixels in the sample image and a first size range.

[0100] The shapes of the multiple second images can all be regular shapes, and the shapes and areas of the multiple second images are the same; the first size range is used to define the size of the second image, and the first size range represents the range of the length and width of the second image, wherein the length and width of the second image can be represented by the number of pixels.

[0101] In this embodiment of the application, the image processing device can determine the size of the second image based on the first size range, and determine the number of second images based on the size of the second image and the number of pixels in the sample image. Based on the number of second images and the determined size of the second images, the sample image is segmented to obtain multiple second images.

[0102] In one feasible implementation, the image processing device can read the number of rows and columns of pixels in the sample image, determine the number M of second images based on the number of rows and columns of pixels and a first size range, and divide the sample image into equal parts to determine M rectangular images, which are then used as the second images. The length and width of the second images can both be between 1 / 100 and 1 / 400 of the length and width of the sample image.

[0103] Step 207: The image processing device obtains the number of pixels in each second image and the pixel value of each pixel in the second image.

[0104] In this embodiment of the application, the number of pixels in the second image can be determined according to the size of the second image, and the pixel value of each pixel in each second image can be determined from the pixel values ​​of multiple pixels in the sample image.

[0105] Step 208: The image processing device determines the color information of the sample image based on the number of pixels in the multiple second images and the pixel values ​​of the pixels in the multiple second images.

[0106] The color information of the sample image can be referred to as the color roughness of the sample image, or as the standard deviation of the pixel values ​​of the sample image.

[0107] In this embodiment, the mean pixel value of the pixels in the second image can be determined based on the number of pixels and the pixel value of the pixels in the second image. The color information of the second image can then be determined based on the number of pixels, the pixel value of the pixels in the second image, and the mean pixel value of the pixels in the second image. Furthermore, the color information of a sample image can be determined based on the color information of multiple second images. The color information of the second image can be referred to as the color roughness of the second image, or the standard deviation of the pixel values ​​of the pixels in the second image.

[0108] In one feasible implementation, the color information of the m-th second image can be determined by formula (1) based on the number of pixels in the second image, the pixel value of the pixels, and the average pixel value of the pixels in the second image.

[0109]

[0110] Among them, S m The color information of the m-th second image; It is a vector form of the pixel value of the i-th pixel in the second image; The vector form represents the average pixel value of all pixels in the second image; ||·|| represents the Euclidean distance; n is the number of pixels in the second image, and m is the ordinal number of the second image.

[0111] In one feasible implementation, the color information of the sample image can be calculated using formula (2) based on the color information of each second image in the sample image.

[0112]

[0113] Among them, S mean S represents the color information of the sample image. m Let m be the color information of the m-th second image, where m is the number of second images. In other words, the average of the color information of multiple second images in the sample image is used as the color information of the sample image.

[0114] Step 209: The image processing device performs region segmentation on the sample image based on the color information and pixel values ​​of the pixels in the sample image to determine multiple first images.

[0115] In this embodiment, pixels in a sample image can be classified (i.e., categorized) based on their color information and pixel values. Then, based on each category of pixels, the sample image is segmented into regions to determine multiple first images. Each sample image can yield multiple first images.

[0116] It should be noted that step 209 can also be achieved through steps a1-a3:

[0117] a1. The image processing device determines the number of color levels included in the sample image based on the color information and color level accuracy coefficient of the sample image.

[0118] The color level precision coefficient is preset; the number of color levels indicates the number of color levels into which the sample image is divided. In one feasible implementation, if the number of color levels is M, it means that the color of the sample image is divided into M levels.

[0119] In one feasible implementation, the color level of the sample image is calculated using formula (3) based on the color level and color level precision coefficient of the sample image.

[0120] N = a·S mean +1 formula (3)

[0121] Where N represents the color level of the sample image; a represents the pre-set color level precision coefficient; S mean This represents the color information of the sample image.

[0122] a2. The image processing device determines the color level of the pixels in the sample image based on the color level, the color information of the sample image, and the pixel value of the pixel in the sample image.

[0123] The color level of a pixel represents the color level corresponding to the color represented by the pixel value of that pixel.

[0124] In this embodiment, the color information and pixel values ​​of the sample image can be analyzed to determine the color information of the pixels, and the color level of the pixels can be determined based on the color information and the color level. The color information includes color values.

[0125] It should be noted that step a2 can be achieved through steps b1-b2:

[0126] b1. The image processing device determines the color value of a pixel based on the pixel value of the pixel and the color information of the sample image.

[0127] In this embodiment of the application, the difference between the pixel value of a pixel and the color information of the sample image can be calculated as the color value of the pixel.

[0128] b2. The image processing device determines the color level of pixels in the sample image based on the color value of the pixel and the number of color levels.

[0129] In this embodiment of the application, the color value of a pixel can be rounded, and the corresponding color level in the color level can be determined based on the color value of the pixel.

[0130] In one feasible implementation, if the color value of a pixel is "2.75", then the pixel value is rounded down to "3". If the color level of the sample image is "7" and the color levels are "0, 1, 2, 3, 4, 5 and 6", then the color level of the pixel corresponds to the third level from left to right in the color level of the sample image, that is, the color level of the pixel is "2".

[0131] a3. The image processing device performs region segmentation on the sample image based on the color level of the pixels, and obtains multiple first images.

[0132] In this embodiment of the application, the image processing device can classify the pixels in the sample image based on the color level of the pixels in the sample image, group the pixels with the same color level into the same category, and determine the first image based on each category of pixels.

[0133] It should be noted that step a3 can also be achieved through steps c1-c3:

[0134] c1. The image processing device performs region segmentation on the sample image based on the color level and second size range of the pixels in the sample image, and determines multiple third images with the same color level of the pixels.

[0135] The second size range is used to define the size of the third image.

[0136] In this embodiment, pixels in the sample image can be classified based on their color levels. Pixels with the same color level are grouped into the same category. For any category of pixels, the pixels in that category can be filtered based on their position. Multiple pixels with consecutive positions are determined from each category, and a third image is determined based on these multiple consecutive pixels and a second size range. In the third image, each pixel has the same color level.

[0137] It should be noted that the area of ​​the third image is controlled based on the second size range, so that the area of ​​the third image is at least 2% of the area of ​​the sample image. This can reduce the complexity of subsequent processing of each third image. The third image can be composed of pixels and pixels connected to their four or eight neighboring regions.

[0138] c2. The image processing device determines the color distance between edge pixels and adjacent pixels in each third image, as well as the average color distance of pixels in the third image.

[0139] Among them, the pixels adjacent to the edge pixels are the pixels outside the third image in the sample image; color distance refers to the difference between the color represented by the pixel value of the edge pixel in the third image and the color represented by the pixel value of the pixel value of the edge pixel.

[0140] In this embodiment of the application, the average color distance of the pixels in the third image is the mean of the color distances between the pixels in the third image.

[0141] c3. The image processing device determines multiple first images based on color distance, average color distance, and the third image.

[0142] In this embodiment of the application, it is possible to determine whether to include pixels adjacent to edge pixels in the third image in the third image based on the color distance between edge pixels and adjacent pixels in the third image and the average color distance of pixels in the third image, thereby obtaining a determination result, and further determining multiple first images based on the determination result.

[0143] It should be noted that step c3 can be achieved through steps d1-d3:

[0144] d1. The image processing device determines a first sub-image from multiple third images whose color distance is less than the average color distance, and determines a fourth image based on the first sub-image and the pixels adjacent to the edge pixels.

[0145] In this embodiment of the application, multiple third images can be filtered based on the color distance between the edge pixels of each third image and the adjacent pixels of the edge pixels and the average color distance of the pixels in the third image. The third image with a color distance less than the average color distance is taken as the first sub-image, and a fourth image is generated based on the first sub-image and the adjacent pixels of the edge pixels of the first sub-image.

[0146] Specifically, if the color distance between an edge pixel of the i-th third image and its adjacent pixels is less than the average color distance of all pixels in the i-th third image, then the i-th third image can be designated as the first sub-image. Based on the first sub-image and the pixels adjacent to its edge pixels, a fourth image is generated. In other words, the boundary of the first sub-image is expanded so that the expanded first sub-image includes the pixels adjacent to the edge pixels of the unexpanded first sub-image. Here, i is a positive integer.

[0147] d2. The image processing device determines a second sub-image from a plurality of third images whose color distance is greater than or equal to the average color distance.

[0148] In this embodiment of the application, multiple third images can be filtered based on the color distance between the edge pixels of each third image and the adjacent pixels of the edge pixels and the average color distance of the pixels in the third image, and the third image with a color distance greater than or equal to the average color distance can be used as the second sub-image.

[0149] Specifically, if the color distance between an edge pixel of the i-th third image and its adjacent pixels is greater than or equal to the average color distance of the pixels in the i-th third image, then the i-th third image can be designated as the second sub-image. Here, i is a positive integer.

[0150] d3. The image processing device determines a plurality of first images based on the fourth image and / or the second sub-image.

[0151] In this embodiment, if all third images in the sample image can generate multiple fourth images from pixels adjacent to the edge pixels of the third image, then the multiple fourth images can be used as multiple first images; if all third images in the sample image can be used as second sub-images, then all second sub-images can be used as multiple first images; if there are third images in the sample image that can generate fourth images from pixels adjacent to the edge pixels of the third image, and there are also third images that can be used as second sub-images, then both the fourth images and the second sub-images can be used as first images to obtain multiple first images.

[0152] Step 210: The image processing device acquires the distance between multiple first images.

[0153] In this embodiment of the application, the distance between the first images can be determined based on the position of each first image in the sample image.

[0154] It should be noted that step 210 can also be achieved through steps e1-e3:

[0155] e1. The image processing device constructs a region adjacency table based on the position of each first image in the sample images.

[0156] The region adjacency table represents the positional relationships between the first images.

[0157] In this embodiment of the application, each first image can be numbered based on its position in the sample image to construct a region adjacency table.

[0158] e2. The image processing device obtains the color distance between the m-th first image and the n-th first image, and the edge distance between the m-th first image and the n-th first image; where m and n are both positive integers.

[0159] In this embodiment of the application, the color distance between the m-th first image and the n-th first image can be determined based on the number of pixels in the m-th first image, the number of pixels in the n-th first image, the color level of the pixels in the m-th first image, and the color level of the pixels in the n-th first image.

[0160] In one feasible implementation, the color distance between the m-th first image and the n-th first image can be determined using formula (4).

[0161]

[0162] Where, |r m | represents the number of pixels in the m-th first image; |r n | represents the number of pixels in the nth first image; A vector representation of the average color level of the m-th pixel in the first image; A vector representation of the average color level of the nth pixel in the first image; This represents the color distance between the m-th and n-th first images; "·" indicates multiplication.

[0163] In this embodiment of the application, the edge distance between the m-th first image and the n-th first image can be determined by an edge detection method. Specifically, it can be determined based on the color level of the edge pixels of the m-th first image and the color level of the edge pixels of the n-th first image, the number of edge pixels of the m-th first image and the number of edge pixels of the n-th first image.

[0164] In one feasible implementation, the edge distance between the m-th first image and the n-th first image can be calculated using formula (5).

[0165]

[0166] in, In the m-th first image, the first... k The vector form of the color level of each edge pixel; In the nth first image, the first... l The vector form of the color level of each edge pixel; |E mn | represents the sum of the number of edge pixels in the m-th and n-th first images.

[0167] e3. The image processing device determines the distance between the m-th first image and the n-th first image based on the color distance, edge distance, and region adjacency table.

[0168] The region adjacency table includes region relation values; these values ​​characterize the positional relationship between the m-th and n-th first images. In one feasible implementation, the region relation value between the m-th and n-th first images can be represented by Δ. mn Let Δ represent that if the m-th first image is adjacent to the n-th first image, then Δ mn =1, if the m-th first image and the n-th first image are not adjacent, then Δ ij =+∞.

[0169] In one feasible implementation, the distance between the m-th first image and the n-th first image can be determined by formula (6).

[0170]

[0171] in, This represents the distance between the m-th first image and the n-th first image; This represents the color distance between the m-th first image and the n-th first image; Let represent the edge distance between the m-th and n-th first images; p represents the weighting coefficient of the color distance; n represents the weighting coefficient of the edge distance; Δ mnThis represents the region relationship value between the m-th first image and the n-th first image.

[0172] Step 211: The image processing device determines multiple first candidate region images based on the distance between multiple first images and the multiple first images.

[0173] In this embodiment of the application, multiple first images can be filtered based on the distance between them, and the filtered images can be merged to obtain a merged image. The merged image and the images other than the filtered images can be filtered again to determine multiple first candidate region images.

[0174] It should be noted that step 211 can be achieved through steps f1-f2:

[0175] f1. The image processing device processes multiple first images based on distance to obtain multiple second candidate region images;

[0176] In this embodiment, multiple first target images are determined from multiple first images, and these multiple first target images are merged to obtain a first merged image. A first merging threshold is calculated. Based on the distance between the first merged image and images other than the first target image in the multiple first images, and the distance between the images other than the first target image in the multiple first images, a second target image is determined from the first merged image and the images other than the first target image in the multiple first images. The second target image is merged to obtain a second merged image, and a second merging threshold is calculated. Based on the distance between the second merged image and images other than the second target image, and the distance between the images other than the second target image, a third target image is determined from the second merged image and the images other than the second target image. The third target image is merged to obtain a third merged image, and a third merging threshold is calculated. When the second merging threshold is less than the first merging threshold and less than the third merging threshold, the images other than the second target image in the second merged image are used as multiple second candidate images. Specifically, when the merging threshold is determined to be at its minimum, merging stops, and the merged image and the unmerged image are used as multiple second candidate images. The minimum merging threshold is determined from the merging thresholds of at least three merging operations, and the minimum merging threshold must be smaller than the merging thresholds of the two adjacent merges. It should be noted that after each merge, the region adjacency table needs to be reconstructed, and the distance between images is calculated using this reconstructed table.

[0177] In one feasible implementation, if any sample image contains 10 first images, the two first images with the smallest distance are determined from the 10 first images based on the distances between them. If the two first images with the smallest distance are the a-th first image and the b-th first image, then the a-th first image and the b-th first image can be merged. A first merging threshold is calculated, and the region adjacency table is reconstructed to obtain the first region adjacency table (i.e., the first merging), resulting in a merged image and unmerged first images (i.e., 9 images). The distances between the 9 images are calculated again, and the two images with the smallest distance are determined from the 9 images and merged. A second merging threshold is calculated, and the region adjacency table is reconstructed to obtain the second region adjacency table (i.e., the second merging), resulting in a merged image and unmerged images (i.e., 8 images). The distances between the 8 images are calculated again, and the two images with the smallest distance are determined from the 8 images and merged. A third merging threshold is calculated, and the region adjacency table is reconstructed to obtain the third region adjacency table (i.e., the third merging). The process involves obtaining the merged and unmerged images (i.e., 7 images), and determining whether the second merging threshold is less than both the first and third merging thresholds. If the second merging threshold is less than both the first and third merging thresholds, then the second merging threshold is used as the minimum merging threshold, and the 8 images obtained from the second merging are used as multiple second candidate region images. If the second merging threshold is greater than the first or the third merging threshold, then a fourth merging is required, calculated using the above method. The fourth merging threshold is calculated, and the region adjacency table is reconstructed to obtain the fourth region adjacency table. The third merging threshold is compared with the second and fourth merging thresholds. If the third merging threshold is less than both the second and fourth merging thresholds, then the third merging threshold is used as the minimum merging threshold, and the 7 images obtained from the third merging are used as multiple second candidate region images. If the third merging threshold is not the minimum merging threshold, then the nth merging threshold needs to be determined using the above method until the minimum merging threshold is determined, further determining multiple second candidate region images.

[0178] f2. The image processing device filters multiple second candidate region images to determine the first candidate region image.

[0179] In this embodiment of the application, multiple second candidate regions can be filtered based on the color level of the pixels of the second candidate region image to determine the first candidate region image.

[0180] It should be noted that step f2 can be achieved through steps g1-g3:

[0181] g1. The image processing device groups the second candidate region images based on the color level of the second candidate region images to obtain multiple groups of second candidate region images.

[0182] Among them, the second candidate region images in the same group have the same color level.

[0183] In this embodiment, the second candidate region images can be grouped according to their color levels, with images having the same color level grouped together, resulting in multiple groups of first candidate region images. The color level of the second candidate region images in each group differs from that of the second candidate region images in other groups.

[0184] g2. The image processing device determines the number of images for each group of second candidate regions.

[0185] In this embodiment of the application, the image processing device can determine the number of second candidate region images in each group based on the second candidate region images in each group.

[0186] g3. The image processing device filters multiple second candidate regions based on the number of images in each group of second candidate regions to determine the first candidate region image.

[0187] In this embodiment of the application, the image processing device determines the number of second candidate region images that appear most frequently in the target region from the number of second candidate region images in each group, and determines the first candidate region image based on the number of second candidate region images that appear most frequently in the target region.

[0188] In one feasible implementation, if there are 10 groups of second candidate region images, taking the first group of second candidate region images as an example, the target region of each second candidate region image in the first group is determined. Specifically, the number of second candidate region images belonging to the tongue coating region and the number of second candidate region images belonging to the tongue tip region in the first group can be counted. Thus, the number of second candidate regions belonging to the tongue coating region and the number of second candidate regions belonging to the tongue tip region in each group are counted. Finally, the second candidate region images from group a (which has the most images belonging to the tongue coating region) and group b (which has the most images belonging to the tongue tip region) are both selected as first candidate region images. If the number of second candidate regions belonging to the tongue coating region in group a is the same as the number of second candidate regions belonging to the tongue coating region in group b, then the second candidate region with the larger area occupied by the tongue coating region is selected as the first candidate region image.

[0189] Step 212: The image processing device determines the target tongue image based on multiple first candidate region images.

[0190] Among them, the target tongue image is an image with multiple target regions.

[0191] In this embodiment of the application, multiple first candidate region images can be combined to obtain a target tongue image.

[0192] In one feasible implementation, images of multiple target regions, such as Figure 4 As shown, Figure 4 The shaded area in the image represents the target tongue image, which is clearly divided into multiple target regions; these target regions include, but are not limited to, the tongue coating region and the tongue tip region.

[0193] Step 213: The image processing device determines the body constitution category of the human body based on the pixel information of the target tongue image.

[0194] It should be noted that the descriptions of the same steps and contents as in other embodiments in this embodiment can be found in the descriptions in other embodiments, and will not be repeated here.

[0195] The image processing method provided in this application determines the body constitution category of a human body based on the pixel information of the target tongue image, avoiding the influence of the background in the image of the human tongue in related technologies, and improving the accuracy of determining the body constitution category of a human body.

[0196] Based on the foregoing embodiments, embodiments of this application provide an image processing device that can be applied to... Figure 1-2 In the image processing method provided in the corresponding embodiment, refer to Figure 5 As shown, the image processing device 3 includes: a processor 32, a memory 31, and a communication bus 33;

[0197] Communication bus 33 is used to realize the communication connection between processor 32 and memory 31;

[0198] The processor 32 is used to execute the image processing program stored in the memory 31 to perform the following steps:

[0199] Multiple sample images of the human tongue were acquired from different acquisition angles.

[0200] The sample image is segmented into regions based on the pixel information of the pixel points of the sample image to obtain multiple first images;

[0201] Based on multiple first images, the target tongue image is determined;

[0202] Based on the pixel information of the target tongue image, the body constitution category of the human body is determined.

[0203] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31 to acquire multiple sample images of the tongue of a human body at different acquisition angles, in order to perform the following steps:

[0204] Multiple images containing information about the human tongue are acquired from different acquisition angles;

[0205] From the image to be processed, determine the non-tongue region image and the tongue region image;

[0206] The location of the tongue region in the human body is determined based on images of the non-tongue region and the tongue region.

[0207] Based on the location of the tongue region in the human body, multiple sample images of the tongue are collected from different acquisition angles.

[0208] In other embodiments of this application, the processor 32 is configured to execute a region segmentation of the sample image based on pixel information of the sample image in an image processing program stored in the memory 31, to obtain a plurality of first images, in order to implement the following steps:

[0209] Obtain the number of pixels and the pixel value of each pixel in the sample image;

[0210] Based on the number of pixels in the sample image and a first size range, multiple second images are determined from the sample image;

[0211] Obtain the number of pixels and the pixel value of each pixel in each second image;

[0212] The color information of the sample image is determined based on the number of pixels and the pixel values ​​of the pixels in the multiple second images.

[0213] Based on the color information and pixel values ​​of the sample images, the sample images are segmented into regions to determine multiple first images.

[0214] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31, based on color information of a sample image and pixel values ​​of pixels in the sample image, to perform region segmentation on the sample image and determine multiple first images, thereby implementing the following steps:

[0215] Based on the color information and color level precision coefficient of the sample image, determine the number of color levels included in the sample image;

[0216] The color level of the pixels in the sample image is determined based on the color level number, the color information of the sample image, and the pixel value of the pixel in the sample image.

[0217] Based on the color levels of the pixels in the sample image, the sample image is segmented into regions to determine multiple first images.

[0218] In other embodiments of this application, the processor 32 is configured to execute an image processing program stored in the memory 31, based on the color level, color information of the sample image, and pixel values ​​of the sample image pixels, to determine the color level of the sample image pixels, thereby implementing the following steps:

[0219] The color value of a pixel is determined based on its pixel value and the color information of the sample image.

[0220] The color level of a pixel in a sample image is determined based on its color value and the number of color levels.

[0221] In other embodiments of this application, the processor 32 is configured to execute a color level based on pixel points of a sample image in an image processing program stored in the memory 31, perform region segmentation on the sample image, and determine a plurality of first images to implement the following steps:

[0222] Based on the color level and second size range of pixels in the sample image, the sample image is segmented into regions to identify multiple third images with the same color level of pixels.

[0223] Determine the color distance between each edge pixel and its adjacent pixels in the third image, as well as the average color distance between pixels in the third image; wherein, the adjacent pixels of the edge pixel are pixels outside the third image in the sample image;

[0224] Multiple first images are determined based on color distance, average color distance, and the third image.

[0225] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31, based on color distance, average color distance, and a third image, to determine a plurality of first images to perform the following steps:

[0226] A first sub-image with a color distance less than the average color distance is determined from multiple third images, and a fourth image is determined based on the first sub-image and the pixels adjacent to the edge pixels.

[0227] Determine a second sub-image from multiple third images whose color distance is greater than or equal to the average color distance;

[0228] Based on the fourth image and / or the second sub-image, multiple first images are determined.

[0229] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31 to determine a target tongue image based on a plurality of first images, in order to perform the following steps:

[0230] Obtain the distance between multiple first images;

[0231] Based on distance and multiple first images, multiple first candidate region images are determined;

[0232] The target tongue image is determined based on multiple first candidate region images.

[0233] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31 to obtain the distance between a plurality of first images, in order to perform the following steps:

[0234] Based on the position of each first image in the sample images, construct a region adjacency table;

[0235] Obtain the color distance between the m-th first image and the n-th first image, and the edge distance between the m-th first image and the n-th first image; where m and n are both positive integers;

[0236] Based on color distance, edge distance, and region adjacency table, determine the distance between the m-th first image and the n-th first image.

[0237] In other embodiments of this application, processor 32 is configured to execute an image processing program stored in memory 31, based on distance and multiple first images, to determine multiple first candidate region images to perform the following steps:

[0238] Multiple first region images are processed based on distance to obtain multiple second candidate region images;

[0239] Multiple second candidate region images are filtered to determine the first candidate region image.

[0240] In other embodiments of this application, the processor 32 is configured to execute an image processing program stored in the memory 31 to filter multiple second candidate region images and determine a first candidate region image, thereby implementing the following steps:

[0241] The second candidate region images are grouped based on their color levels to obtain multiple groups of second candidate region images; among them, the second candidate region images in the same group have the same color level.

[0242] Determine the number of images for each group of second candidate regions;

[0243] Based on the number of second candidate region images in each group, multiple second candidate region images are filtered to determine the first candidate region image.

[0244] It should be noted that the specific implementation process of the steps executed by processor 32 in this embodiment can be referred to Figure 1-2 The implementation process of the image processing method provided in the corresponding embodiments will not be described in detail here.

[0245] The image processing device provided in this application determines the body constitution category of a human body based on the pixel information of the target tongue image, avoiding the influence of the background in the image of the human tongue in related technologies, and improving the accuracy of determining the body constitution category of a human body.

[0246] Based on the foregoing embodiments, this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to achieve... Figure 1-2 The steps in the image processing method provided in the corresponding embodiment.

[0247] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0248] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0249] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0250] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0251] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0252] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0253] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0254] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0255] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An image processing method, characterized in that, The method includes: Multiple sample images of the human tongue are acquired from different acquisition angles; the sample images are images that only show the human tongue. Based on the pixel information of the pixel points in the sample image, the sample image is segmented into regions to obtain multiple first images; Based on the plurality of first images, a target tongue image is determined; the target tongue image includes tongue images corresponding to different target regions, and the tongue images corresponding to different target regions are obtained by filtering the plurality of first images; Based on the pixel information of the target tongue image, the body constitution category of the human body is determined; The step of determining the target tongue image based on the plurality of first images includes: Obtain the distance between the plurality of first images; Based on the distance and the plurality of first images, a plurality of first candidate region images are determined; Based on the multiple first candidate region images, the target tongue image is determined; Obtaining the distance between the plurality of first images includes: Based on the position of each first image in the sample images, a region adjacency table is constructed. Obtain the color distance between the m-th first image and the n-th first image, and the edge distance between the m-th first image and the n-th first image; where m and n are both positive integers; Based on the color distance, the edge distance, and the region adjacency table, the distance between the m-th first image and the n-th first image is determined; The step of determining multiple first candidate region images based on the distance and the multiple first images includes: Based on the distance, the plurality of first images are processed to obtain a plurality of second candidate region images; The multiple second candidate region images are filtered to determine the first candidate region image; The step of filtering the plurality of second candidate region images to determine the first candidate region image includes: The second candidate region images are grouped based on their color levels to obtain multiple groups of second candidate region images; wherein, the second candidate region images in the same group have the same color level. Determine the number of images for each group of second candidate regions; Based on the number of second candidate region images in each group, the multiple second candidate region images are filtered to determine the first candidate region image.

2. The method according to claim 1, characterized in that, The process involves acquiring multiple sample images of the human tongue from different acquisition angles, including: Multiple images containing information about the human tongue are acquired from different acquisition angles; From the image to be processed, determine the non-tongue region image and the tongue region image; Based on the non-tongue region image and the tongue region image, the location of the tongue region of the human body is determined; Based on the location of the tongue region of the human body, multiple sample images of the tongue of the human body are acquired at different acquisition angles.

3. The method according to claim 1, characterized in that, The sample image is segmented into regions based on pixel information of the pixel points to obtain multiple first images, including: Obtain the number of pixels in the sample image and the pixel value of each pixel in the sample image; Based on the number of pixels in the sample image and a first size range, a plurality of second images are determined from the sample image; Obtain the number of pixels in each of the second images and the pixel value of each pixel in the second image; The color information of the sample image is determined based on the number of pixels in the plurality of second images and the pixel values ​​of the pixels in the plurality of second images; Based on the color information and pixel values ​​of the sample images, the sample images are segmented into regions to determine the plurality of first images.

4. The method according to claim 3, characterized in that, The step of segmenting the sample image into regions based on the color information and pixel values ​​of the pixels in the sample image to determine the plurality of first images includes: Based on the color information and color level precision coefficient of the sample image, the number of color levels included in the sample image is determined; The color level of the pixel in the sample image is determined based on the color level number, the color information of the sample image, and the pixel value of the pixel in the sample image. Based on the color levels of the pixels in the sample image, the sample image is segmented into regions to determine the plurality of first images.

5. The method according to claim 4, characterized in that, Determining the color level of a pixel in a sample image based on the color level number, the color information of the sample image, and the pixel value of the pixel in the sample image includes: The color value of the pixel is determined based on the pixel value of the pixel and the color information of the sample image; The color level of the pixels in the sample image is determined based on the color value of the pixel and the level of the color level.

6. The method according to claim 4, characterized in that, The step of segmenting the sample image into regions based on the color levels of the pixels in the sample image to determine the plurality of first images includes: Based on the color level and second size range of the pixels in the sample image, the sample image is segmented into regions to determine multiple third images with the same color level of the pixels; Determine the color distance between each edge pixel in the third image and its adjacent pixels, as well as the average color distance of the pixels in the third image; wherein, the pixels adjacent to the edge pixel are the pixels in the sample image that are outside the third image. The plurality of first images are determined based on the color distance, the average color distance, and the third image.

7. The method according to claim 6, characterized in that, The determination of the plurality of first images based on the color distance, the average color distance, and the third image includes: A first sub-image is determined from the plurality of third images whose color distance is less than the average color distance, and a fourth image is determined based on the first sub-image and the pixels adjacent to the edge pixels. Determine a second sub-image from the plurality of third images whose color distance is greater than or equal to the average color distance; The plurality of first images are determined based on the fourth image and / or the second sub-image.

8. An image processing device, characterized in that, The device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute the image processing program stored in the memory to perform the following steps: Multiple sample images of the human tongue are acquired from different acquisition angles; the sample images are images that only show the human tongue. Based on the pixel information of the pixel points in the sample image, the sample image is segmented into regions to obtain multiple first images; Based on the plurality of first images, a target tongue image is determined; the target tongue image includes tongue images corresponding to different target regions, and the tongue images corresponding to different target regions are obtained by filtering the plurality of first images; Based on the pixel information of the target tongue image, the body constitution category of the human body is determined; The processor is used to execute an image processing program stored in the memory, based on multiple first images, to determine a target tongue image, in order to perform the following steps: Obtain the distance between multiple first images; Based on distance and multiple first images, multiple first candidate region images are determined; The target tongue image is determined based on multiple first candidate region images; The processor is used to execute the image processing program stored in the memory to obtain the distance between multiple first images, in order to achieve the following steps: Based on the position of each first image in the sample images, construct a region adjacency table; Obtain the color distance between the m-th first image and the n-th first image, and the edge distance between the m-th first image and the n-th first image; where m and n are both positive integers; Based on color distance, edge distance, and region adjacency table, determine the distance between the m-th first image and the n-th first image; The processor is used to execute an image processing program stored in the memory, based on distance and multiple first images, to determine multiple first candidate region images, in order to perform the following steps: Multiple first region images are processed based on distance to obtain multiple second candidate region images; Multiple second candidate region images are filtered to determine the first candidate region image; The processor is used to execute the image processing program stored in the memory to filter multiple second candidate region images and determine a first candidate region image, in order to achieve the following steps: The second candidate region images are grouped based on their color levels to obtain multiple groups of second candidate region images; among them, the second candidate region images in the same group have the same color level. Determine the number of images for each group of second candidate regions; Based on the number of second candidate region images in each group, multiple second candidate region images are filtered to determine the first candidate region image.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the image processing method as described in any one of claims 1 to 7.

Images