Method, apparatus and readable medium for personalized generation of texture images of large stone slabs

Abstract

This invention discloses a method, apparatus, and readable medium for personalized generation of texture images of large stone slabs. Utilizing the color and texture information of the stone slab itself, the method divides the customer-specified pattern into several third images and analyzes their image information. Then, it searches a massive stone slab database to find the regions with the highest similarity to each part, and uses an intelligent processing system to process and arrange these regions, thereby achieving personalized customization of the stone slab texture image. Its working principle is to use intelligent algorithms to replace manual design and layout. This personalized design and layout method can fully utilize every texture of the stone to design more aesthetically pleasing patterns, further enhancing the added value of the stone and having significant implications for the digital transformation and upgrading of the entire stone industry.

Description

Technical Field

[0001] This invention relates to the field of intelligent stone processing, specifically to a method, apparatus, and readable medium for personalized generation of texture images of large stone slabs. Background Technology

[0002] Stone slabs are a type of building decoration material formed from raw stones quarried from mines through processes such as sawing, gluing, reinforcement, and polishing. They are characterized by their elegance, beauty, safety, durability, and natural grandeur, and are widely used in daily life, such as interior flooring, feature walls, dining tables, and cabinets, bringing life closer to nature and enriching it with an artistic atmosphere. The stone texture, as part of the stone slab, undoubtedly enhances its beauty and artistic appeal. Among thousands of stone slabs, it is extremely difficult to find two with identical textures, demonstrating the wonder of nature that makes each stone's texture unique, and its natural beauty unparalleled, adding to the mystique of stone's beauty.

[0003] As people's living standards continue to improve, their pursuit of quality of life is also becoming stronger, including their aesthetic appreciation of stone patterns. Therefore, natural stone with rich textures and reliable quality has become an important choice for building decoration. Before large stone slabs can be used in homes as building decoration materials, a necessary process is design and layout. This involves designing the position and connection relationships between slabs based on the stone's texture to achieve a more aesthetically pleasing pattern. Therefore, the design and layout process plays a crucial role in bringing out the value of the stone's texture and showcasing its beauty. High-quality and efficient design and layout are like the finishing touch to a masterpiece of stone products.

[0004] Currently, there are two methods for designing and layout textures and patterns: one is to obtain natural patterns from quarries. The subsequent cutting, grinding, and polishing processes for stones with such patterns are determined during quarrying until the texture and pattern are fully revealed. However, natural stone textures and patterns are formed over hundreds of millions of years of geological activity; they are a scarce resource, an innate beauty that cannot be replicated through post-processing. Therefore, stones with natural textures and patterns often command high market prices, making them highly sought after and unattainable. The other method is manual CAD layout, where workers, based on experience, select patterns from a limited number of large stone slabs by their textures and then lay them out. This method can only select from a limited number of large stone slabs, requiring a high level of worker experience, resulting in lower efficiency and greater susceptibility to subjective factors. Summary of the Invention

[0005] In view of the aforementioned problems such as the high difficulty, high experience requirement, low efficiency, and significant influence of subjective factors in customizing large stone slabs, the purpose of this application is to propose a method, apparatus, and readable medium for personalized generation of texture images for large stone slabs to solve the technical problems mentioned in the background section.

[0006] In a first aspect, the present invention provides a method for personalized generation of texture images of large stone slabs, comprising the following steps:

[0007] S1, acquire the first image, adjust the size of the first image to the target size, obtain the second image, and establish a coordinate system on the second image;

[0008] S2, segment the second image into several third images, obtain the position coordinates of the third images in the second images, and extract the image features of the third images;

[0009] S3, acquire the image of the stone slab, compare the similarity between the third image and the image of the stone slab, obtain the similarity, and record the position coordinates of the area with the highest similarity on the image of the stone slab and the corresponding stone slab information.

[0010] S4. Repeat step S3 to compare all third images with all stone slab images and obtain similarity results.

[0011] S5. Based on the similarity results, determine the stone slab information with the highest similarity to all third images. Generate a retrieval instruction for the corresponding stone slab based on the stone slab information. Generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image. Retrieve the stone slab according to the retrieval instruction and process the stone slab according to the processing instruction to obtain a processed stone slab. After splicing several processed stone slabs, a spliced ​​stone slab corresponding to the first image can be obtained.

[0012] Preferably, step S3 specifically includes:

[0013] S31, Select a sliding window of the same size as the third image on the stone slab image;

[0014] S32, compare the similarity between the image in the sliding window and the third image;

[0015] S33, move the sliding window with a preset pixel step size, repeat step S32, and obtain the similarity between each third image and each location area on the stone slab image. Combine the highest similarity value with the stone slab information and the location coordinates of each location area to obtain the similarity result information.

[0016] Preferably, step S32 specifically includes:

[0017] The cosine similarity between the image within the sliding window and the third image is calculated using the following formula:

[0018]

[0019] Where, x i y i These are the i-th image features corresponding to the third image and the image within the sliding window, respectively, where i = 1, 2, ..., n;

[0020] The structural similarity between the image within the sliding window and the third image is calculated using the following formula:

[0021]

[0022] Where X and Y are the third image and the image within the sliding window, respectively, u X u Y σ X σ Y σ XY C1 and C2 are the mean of the third image, the mean of the images within the sliding window, the variance of the third image, the variance of the images within the sliding window, and the covariance of the third image and the images within the sliding window, respectively, and are non-zero constants.

[0023] The histogram similarity between the image within the sliding window and the third image is calculated using the following formula:

[0024]

[0025] in, K is 1 or 2, N represents the number of bins in the histogram, I represents the corresponding index value, H1 is the histogram of the third image, and H2 is the histogram of the image within the sliding window.

[0026] The overall similarity is calculated using the following formula:

[0027] R(X,Y)=W0 cosθ+W1SSIM(X,Y)+W2d(H1,H2);

[0028] Among them, W i The weights are for the corresponding similarity scores.

[0029] Preferably, step S5 involves splicing together several processed stone slabs, specifically including:

[0030] Based on the position coordinates of the third image in the second image, several processed stone slabs are spliced ​​together to obtain a spliced ​​stone slab.

[0031] Preferably, step S2 involves extracting image features from the third image, specifically including:

[0032] Color information is obtained by analyzing the values ​​of different color channels corresponding to each pixel in the third image;

[0033] The texture information is obtained based on the grayscale distribution of each pixel and its surrounding spatial domain in the third image;

[0034] The image features of the third image are obtained by combining color and texture information.

[0035] Preferably, the size of the first image must be within the range of stone slab splicing, the color of the first image must be within the comprehensive range of various colors of stone slabs that have been developed, and the pattern lines on the first image must conform to the texture characteristics of the stone slabs.

[0036] Preferably, the stone slab images are stored in a stone slab database. The stone slab database also stores the stone slab image feature information, the size information of the stone slab image, and storage information. The stone slab images and their related content are mapped to QR codes, which serve as identification credentials for retrieving the stone slab images and their related information.

[0037] Secondly, the present invention provides a device for generating personalized texture images of large stone slabs, comprising:

[0038] The image adjustment module is configured to acquire a first image, adjust the size of the first image to a target size to obtain a second image, and establish a coordinate system on the second image.

[0039] The image segmentation module is configured to segment the second image into several third images, obtain the position coordinates of the third images in the second images, and extract the image features of the third images;

[0040] The comparison module is configured to acquire images of large stone slabs, compare the similarity between the third image and the images of large stone slabs, obtain the similarity score, and record the position coordinates of the area with the highest similarity score on the images of large stone slabs and the corresponding information of the large stone slabs.

[0041] The repeat module is configured to repeatedly execute the comparison module, comparing all third images with all stone slab images to obtain similarity results;

[0042] The processing control module is configured to determine the stone slab information with the highest similarity to all third images based on the similarity results, generate a retrieval instruction for the corresponding stone slab based on the stone slab information, generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image, retrieve the stone slab according to the retrieval instruction, and process the stone slab according to the processing instruction to obtain processed stone slabs. After splicing several processed stone slabs, a spliced ​​stone slab corresponding to the first image can be obtained.

[0043] Thirdly, the present invention provides an electronic device including one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] (1) The personalized generation method of stone slab texture image proposed in this invention can detect the location area with similarity to its components from a huge database based on the pattern provided by the customer using advanced technology, thereby completing the retrieval of the entire target pattern. This can improve the quality and efficiency of design and layout, make fuller use of the texture of the stone, and create texture patterns that better meet people's aesthetic needs.

[0047] (2) The method for generating personalized texture images of large stone slabs proposed in this invention uses computer-aided intelligent material selection and layout, eliminating the need for manual on-site material selection and layout, thus simplifying the process and reducing labor intensity.

[0048] (3) The personalized generation method of stone slab texture image proposed in this invention can solve people's demand for stone texture patterns and fill the market gap for stone natural texture combination pattern products. It is of great significance, and can also increase the added value of stone slabs and promote the digital transformation and upgrading of the industry. Attached Figure Description

[0049] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments and, together with the description, serve to explain the principles of the invention. Other embodiments and many anticipated advantages of the embodiments will be readily recognized as they become better understood through reference to the following detailed description. Elements in the drawings are not necessarily to scale. The same reference numerals refer to corresponding similar parts.

[0050] Figure 1 A flowchart illustrating a method for personalized generation of texture images of large stone slabs according to an embodiment of this application is shown.

[0051] Figure 2 The diagram illustrates a conventional stone processing layout route and a route diagram from an embodiment of this application.

[0052] Figure 3This illustration shows a schematic diagram of the second image being decomposed into a third image in a method for personalized generation of stone slab texture images according to an embodiment of this application;

[0053] Figure 4 This illustration shows a similarity matching diagram of a third image in the personalized generation method for stone slab texture images according to an embodiment of this application.

[0054] Figure 5 A schematic diagram of the cutting of a large stone slab is shown, illustrating the method for personalized generation of texture images of large stone slabs according to an embodiment of this application.

[0055] Figure 6 A schematic diagram of a stone slab texture image personalization generation apparatus according to an embodiment of this application is shown. Detailed Implementation

[0056] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the drawings. It should be observed that the dimensions and sizes of the components in the drawings are not to scale, and the size of certain components may be highlighted for clarity.

[0057] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0058] refer to Figure 1 The embodiments of this application propose a method for personalized generation of texture images of large stone slabs, including the following steps:

[0059] S1, acquire the first image, adjust the size of the first image to the target size, obtain the second image, and establish a coordinate system on the second image.

[0060] In a specific embodiment, the size of the first image must conform to the range of stone slab splicing, the color of the first image must be within the comprehensive range of various colors of stone slabs that have been developed, and the pattern lines on the first image must conform to the texture characteristics of the stone slabs.

[0061] Specifically, such as Figure 2The diagram shows a comparison between the patented solution of this invention and a traditional solution. The first image contains a target pattern, which can be selected according to the user's preferences and needs. However, the selection must meet certain requirements: firstly, its size must conform to the range of stone slab splicing; secondly, its color must be within the comprehensive range of colors currently available for various types of stone slabs; and finally, its pattern lines must conform to the texture characteristics of the stone slabs. Therefore, the size of the first image needs to be adjusted. The adjusted second image conforms to the laying size, which is determined based on the user's specific desired final laying area of ​​the first image. This adjustment facilitates subsequent comparative analysis with stone slab images in the stone slab database.

[0062] S2, the second image is segmented into several third images, and the position coordinates of the third images in the second image are obtained, and the image features of the third images are extracted.

[0063] In a specific embodiment, step S2, which extracts image features from the third image, specifically includes:

[0064] Color information is obtained by analyzing the values ​​of different color channels corresponding to each pixel in the third image;

[0065] The texture information is obtained based on the grayscale distribution of each pixel and its surrounding spatial domain in the third image;

[0066] The image features of the third image are obtained by combining color and texture information.

[0067] For details, please refer to Figure 3 The second image is decomposed according to different sizes to obtain a third image. Since the effects of analyzing and comparing the third images of different sizes in the stone slab image database are different, the final splicing patterns generated will also differ. Specifically, the S-Spline XL algorithm in image magnification technology can be used to enlarge the second image according to the area to be laid, making its size the same as the laying area.

[0068] S3. Obtain the image of the stone slab, compare the similarity between the third image and the image of the stone slab, obtain the similarity score, and record the position coordinates of the area with the highest similarity score on the image of the stone slab and the corresponding information of the stone slab.

[0069] In a specific embodiment, the stone slab image is stored in a stone slab database. The stone slab database also stores stone slab image feature information, stone slab image size information, and storage information. The stone slab image and its related content are mapped to a QR code, which serves as the identification credential for retrieving the stone slab image and its related content.

[0070] Specifically, the raw stone blocks mined from the mine undergo sawing, gluing, polishing, and reinforcement processes to form large stone slabs. Upon entering the warehouse, a specialized image acquisition system collects information about the slabs, ultimately creating a stone slab database. This database stores images of the stone slabs, image feature information, size information, and their location within the stone slab library. This information is mapped to QR codes, and each slab is associated with a QR code containing its information for subsequent retrieval.

[0071] In a specific embodiment, step S3 specifically includes:

[0072] S31, Select a sliding window of the same size as the third image on the stone slab image;

[0073] S32, compare the similarity between the image in the sliding window and the third image;

[0074] S33, move the sliding window with a preset pixel step size, repeat step S32, and obtain the similarity between each third image and each location area on the stone slab image. Combine the highest similarity value with the stone slab information and the location coordinates of each location area to obtain the similarity result information.

[0075] In a specific embodiment, step S32 specifically includes:

[0076] The cosine similarity between the image within the sliding window and the third image is calculated using the following formula:

[0077]

[0078] Where, x i y i These are the i-th image features corresponding to the third image and the image within the sliding window, respectively, where i = 1, 2, ..., n;

[0079] The structural similarity between the image within the sliding window and the third image is calculated using the following formula:

[0080]

[0081] Where X and Y are the third image and the image within the sliding window, respectively, u X u Y σ X σ Y σ XY C1 and C2 are the mean of the third image, the mean of the images within the sliding window, the variance of the third image, the variance of the images within the sliding window, and the covariance of the third image and the images within the sliding window, respectively, and are non-zero constants.

[0082] The histogram similarity between the image within the sliding window and the third image is calculated using the following formula:

[0083]

[0084] in, K is 1 or 2, N represents the number of bins in the histogram, I represents the corresponding index value, H1 is the histogram of the third image, and H2 is the histogram of the image within the sliding window.

[0085] The overall similarity is calculated using the following formula:

[0086] R(X,Y)=W0 cosθ+W1SSIM(X,Y)+W2d(H1,H2);

[0087] Among them, W i The weights are for the corresponding similarity scores.

[0088] For details, please refer to Figure 4 The decomposed third image can be matched with any slab in the stone slab database at any position and orientation. The third image acts as an image template, while the stone slab image is the matching region. A coordinate system is established based on the contour of the stone slab image, with the upper boundary of the stone slab image as the X-axis and the left side as the Y-axis. The third image is compared with the stone slab image within its contour range at a certain pixel step, and the similarity of each region is calculated according to a similarity calculation method. The region with the highest similarity and its coordinates on the stone slab image are found.

[0089] S4. Repeat step S3 to compare all third images with all stone slab images and obtain similarity results.

[0090] Specifically, after matching all stone slab images in the stone slab image database, the location coordinates of the region with the highest similarity and its corresponding stone slab image information are exported. The similarity of the third image to each region of each stone slab image is recorded and saved in the corresponding list of the third image according to the pattern: stone slab information + location information of the matching region + highest similarity value, forming the similarity result.

[0091] S5. Based on the similarity results, determine the stone slab information with the highest similarity to all third images. Generate a retrieval instruction for the corresponding stone slab based on the stone slab information. Generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image. Retrieve the stone slab according to the retrieval instruction and process the stone slab according to the processing instruction to obtain a processed stone slab. After splicing several processed stone slabs, a spliced ​​stone slab corresponding to the first image can be obtained.

[0092] In a specific embodiment, step S5 involves splicing together several processed stone slabs, specifically including:

[0093] Based on the position coordinates of the third image in the second image, several processed stone slabs are spliced ​​together to obtain a spliced ​​stone slab.

[0094] For details, please refer to Figure 5 Based on the similarity results, the stone slabs with the highest similarity to all the third images are retrieved from the stone warehouse, and the location information of the slabs with the highest similarity is imported into the intelligent processing terminal to process the corresponding stone slabs. The processed stone slabs are then laid out according to their positions in the second image based on the third image, completing the customization of the target pattern.

[0095] The personalized stone slab texture image generation method provided in this application is a new technology that revolves around the design and layout process and fully utilizes modern advanced algorithms and technologies to complete the design and layout. Based on the pattern provided by the user, an intelligent algorithm detects regions with certain similarities to its components from a stone slab database, completing the entire pattern retrieval and realizing personalized customization of the texture pattern, ultimately achieving intelligent design and layout. The image is formed by splicing together slabs already existing in the stone warehouse; these slabs have been acquired by an image acquisition system and entered into the corresponding stone slab database. The second image with the target pattern is decomposed into smaller images of a certain size. Each decomposed small image is compared with the entire area of ​​all stone slab images in the stone database based on information such as color and texture. Traditional machine learning or deep learning algorithms related to image processing are used to calculate the similarity, and the similarity is statistically analyzed. Finally, the part with the highest similarity is used as the subsequent stone slab for splicing. The basis for splicing stone slabs into the target image is to find the location region with the highest similarity to the third image decomposed from the second image in the stone slab database, and these location regions are used as the final stone slabs for splicing the target pattern.

[0096] Further reference Figure 6 As an implementation of the methods shown in the above figures, this application provides an embodiment of a personalized stone slab texture image generation device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0097] This application provides a device for personalized generation of texture images of large stone slabs, including:

[0098] Image adjustment module 1 is configured to acquire a first image, adjust the size of the first image to a target size to obtain a second image, and establish a coordinate system on the second image;

[0099] Image segmentation module 2 is configured to segment the second image into several third images, obtain the position coordinates of the third images in the second images, and extract the image features of the third images;

[0100] Comparison module 3 is configured to acquire images of large stone slabs, compare the similarity between the third image and the images of large stone slabs, obtain the similarity score, and record the position coordinates of the area with the highest similarity score on the images of large stone slabs and the corresponding information of the large stone slabs.

[0101] Repeat module 4 is configured to repeatedly execute comparison module 3, comparing all third images with all stone slab images to obtain similarity results;

[0102] The processing control module 5 is configured to determine the stone slab information with the highest similarity to all third images based on the similarity results, generate a retrieval instruction for the corresponding stone slab based on the stone slab information, generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image, retrieve the stone slab according to the retrieval instruction, and process the stone slab according to the processing instruction to obtain a processed stone slab. After splicing several processed stone slabs, a spliced ​​stone slab corresponding to the first image can be obtained.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based apparatus to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0104] The modules described in the embodiments of this application can be implemented in software or hardware. These modules can also be located within a processor.

[0105] In the description of this application, it should be understood that the word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The simple fact that certain measures are recited in mutually different dependent claims does not indicate that combinations of these measures cannot be used for improvement. Any reference numerals in the claims should not be construed as limiting the scope. The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed.

[0106] Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-mentioned technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, technical solutions formed by substituting the above-mentioned features with technical features disclosed in this application (but not limited to) that have similar functions.

Claims

1. A method for personalized generation of texture images of large stone slabs, characterized in that, Includes the following steps: S1, acquire the first image, adjust the size of the first image to the target size to obtain the second image, and establish a coordinate system on the second image; S2, the second image is segmented into several third images, and the position coordinates of the third images in the second image are obtained, and the image features of the third images are extracted; S3, acquire an image of a large stone slab, compare the similarity between the third image and the image of the large stone slab, obtain the similarity score, and record the position coordinates of the area with the highest similarity score on the image of the large stone slab and its corresponding information. Step S3 specifically includes: S31, Select a sliding window of the same size as the third image on the image of the large stone slab; S32, compare the similarity between the image in the sliding window and the third image; S33, move the sliding window with a preset pixel step size, repeat step S32, and obtain the similarity of each position area on each of the third images and the stone slab images. Combine the highest value of the similarity with the stone slab information and the position coordinates of each position area to obtain the similarity result information. S4, Repeat step S3, compare all the third images with all the stone slab images to obtain similarity results; S5. Based on the similarity results, determine the stone slab information with the highest similarity to all the third images. Generate a retrieval instruction for the corresponding stone slab based on the stone slab information. Generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image. Retrieve the stone slab according to the retrieval instruction and process the stone slab according to the processing instruction to obtain a processed stone slab. After splicing several processed stone slabs, a spliced ​​stone slab corresponding to the first image can be obtained.

2. The method for personalized generation of stone slab texture images according to claim 1, characterized in that, Step S32 specifically includes: The cosine similarity between the image within the sliding window and the third image is calculated using the following formula: ； Where, x i y i These are the i-th image features corresponding to the third image and the image within the sliding window, respectively, where i = 1, 2, ..., n; The structural similarity between the image within the sliding window and the third image is calculated using the following formula: SSIM(X,Y)= ; Where X and Y are the third image and the image within the sliding window, respectively. , , These are, respectively, the mean of the third image, the mean of the images within the sliding window, the variance of the third image, the variance of the images within the sliding window, and the covariance of the third image and the images within the sliding window. ; The histogram similarity between the image within the sliding window and the third image is calculated using the following formula: d(H1,H2)= ; in, K is 1 or 2, N represents the number of bins in the histogram, I represents the corresponding index value, H1 is the histogram of the third image, and H2 is the histogram of the image within the sliding window. The overall similarity is calculated using the following formula: R(X,Y)= ; in, 3. The method for personalized generation of stone slab texture images according to claim 1, characterized in that, Step S5, which involves assembling several of the processed stone slabs, specifically includes: Based on the position coordinates of the third image in the second image, several processed stone slabs are spliced ​​together to obtain the spliced ​​stone slab.

4. The method for personalized generation of stone slab texture images according to claim 1, characterized in that, The step S2 of extracting image features from the third image specifically includes: Color information is obtained based on the values ​​of different color channels corresponding to each pixel in the third image; The texture information is obtained based on the grayscale distribution of each pixel and its surrounding spatial domain in the third image; The image features of the third image are obtained by combining color information and texture information.

5. The method for personalized generation of stone slab texture images according to claim 1, characterized in that, The size of the first image must be within the range of stone slab splicing, the color of the first image must be within the comprehensive range of various colors of stone slabs that have been developed, and the pattern lines on the first image must conform to the texture characteristics of the stone slabs.

6. The method for personalized generation of stone slab texture images according to claim 1, characterized in that, The stone slab image is stored in a stone slab database. The stone slab database also stores stone slab image feature information, stone slab image size information, and storage information. The stone slab image and its related content are mapped to a QR code, which serves as the identification credential for retrieving the stone slab image and its related information.

7. A device for generating personalized texture images of large stone slabs, characterized in that, include: The image adjustment module is configured to acquire a first image, adjust the size of the first image to a target size to obtain a second image, and establish a coordinate system on the second image; The image segmentation module is configured to segment the second image into several third images, obtain the position coordinates of the third images in the second image, and extract the image features of the third images; The comparison module is configured to acquire an image of a large stone slab, compare the similarity between the third image and the image of the large stone slab, obtain a similarity score, and record the position coordinates of the region with the highest similarity score on the image of the large stone slab and its corresponding information about the large stone slab. The image segmentation module specifically includes: The first submodule is configured to select a sliding window of the same size as the third image on the image of the stone slab; The second submodule is configured to perform a similarity comparison between the image in the sliding window and the third image; The third submodule is configured to move the sliding window by a preset pixel step size, repeat the second submodule step, obtain the similarity between each third image and each position region on the stone slab image, and combine the highest value of the similarity with the stone slab information and the position coordinates of each position region to obtain similarity result information. The repeat module is configured to repeatedly execute the comparison module, comparing all the third images with all the stone slab images to obtain similarity results; The processing control module is configured to determine the stone slab information with the highest similarity to all the third images based on the similarity results, generate a retrieval instruction for the corresponding stone slab based on the stone slab information, generate a processing instruction based on the position coordinates of the location area corresponding to the highest similarity on the stone slab image, retrieve the stone slab according to the retrieval instruction, and process the stone slab according to the processing instruction to obtain a processed stone slab. Several processed stone slabs can be spliced ​​together to obtain a spliced ​​stone slab corresponding to the first image.

8. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images