Image texture feature extraction method and system based on Hamming-Pedeson graph

Abstract

The invention provides an image texture feature extraction method and system based on a Hamming-Pedeson graph, and the method comprises the steps: directionally analyzing the relation between pixels of an image according to the Pedeson graph, describing the local fluctuation trend of the relation through employing a threshold function and a structural mode, constructing a local three-valued pattern PLTP feature vector of the Pedeson graph, and carrying out the feature extraction of the local three-valued pattern PLTP feature vector of the Pedeson graph. The robustness, the discrimination capability and the applicability of texture feature extraction operators are improved; the Hamming distance between the central point of the PLTP code and the adjacent point is calculated to extract the spatial structure of the PLTP code, so that the HDPLBP feature vector based on the Hamming distance is generated, and the accuracy of image texture description is improved; the statistical histograms of the PLTP descriptor and the HDPLBP descriptor are combined into the PLTPHHDPLTP texture feature histogram, so that the texture feature quantity can more intuitively and effectively represent the image texture condition, and the texture description capability is ensured to be more robust and stable. Compared with a traditional texture descriptor, image texture analysis is more effective, local information and spatial distribution information are considered, and the function of completely extracting image texture features is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and particularly relates to an image texture feature extraction method and system based on a Hamming-Petersen graph. Background Art

[0002] Image texture is considered as the spatial arrangement feature of information such as pixel intensity, color, and structure in a local area. It has wide applications in the field of computer vision, such as tasks like object recognition, image segmentation, image enhancement, and medical imaging. To effectively extract texture information, researchers have proposed various texture representation and analysis methods. Common methods include local feature extraction based on statistics, geometric description based on structure, parametric representation based on models, and transform domain methods, etc. Each method has its own advantages in different scenarios. Local Binary Pattern (LBP), as a classic statistical method, has been widely applied to texture recognition tasks due to its simplicity and effectiveness. However, the limitations of LBP are becoming increasingly apparent, especially when dealing with images with complex textures or large noise interference, where its discriminative ability is weak. To solve this problem, researchers have proposed some improved versions of LBP, such as improved local binary patterns (GLCM, LBP, HOG, etc.). These methods consider more fine-grained pixel relationships and texture changes to a certain extent, thereby enhancing the robustness and applicability of features. Nevertheless, existing methods still face certain challenges when dealing with complex and variable texture patterns, especially in terms of maintaining details of texture information and fusing spatial distribution information. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an image texture feature extraction method and system based on a Hamming-Petersen graph for extracting image texture features including local information and spatial distribution information.

[0004] The technical solution adopted by the present invention to solve the above technical problem is: an image texture feature extraction method based on a Hamming-Petersen graph, comprising the following steps: S1: Obtain the image to be measured and perform gray-scale preprocessing to obtain a gray-scale image; S2: Traverse the gray-scale image through a Petersen graph to extract ternary features; construct a PLTP feature vector using a threshold function; S3: Calculate the Hamming distance between the PLTP feature vector of each pixel point of the gray-scale image and the PLTP feature vector of its adjacent points to generate an HDPLBP feature vector based on the Hamming distance; S4: Merge the statistical histograms of the descriptors of the PLTP feature vectors and the statistical histograms of the descriptors of the HDPLBP feature vectors into a joint histogram as the PLTP_HDPLTP texture feature of the image to be tested.

[0005] According to the above solution, in step S2, the specific steps are as follows: S21: Scan the grayscale image through the Petersen graph, directionally analyze the relationship between the pixels of the image, describe the local fluctuation trend of the relationship, and extract ternary features; S22: Calculate the gray difference structure of the ternary features, use the threshold function to judge the ternary features, and construct the PLTP feature vector.

[0006] Further, in step S21, the specific steps are as follows: Traverse the pixel points of the entire grayscale image using a 5×5 window according to the structure of the Petersen graph; According to the vertex relationship of the Petersen graph, 6 paths of ternary structures are formed from the center pixel to the edge pixel direction of the window. Define the pixel set in the path as: {[gray value of the center pixel, gray value of the inner ring pixel, gray value of the inner ring pixel]}, that is, the gray difference structure of each pixel point is obtained.

[0007] Further, in step S22, the specific steps are as follows: Control the conversion width through the first threshold, and use the binary threshold function to distinguish the value of the gray difference; Use the threshold function to describe the fluctuation trend of the local gray difference pair, and use addition to construct the microstructure of the ternary pattern to obtain ternary elements; Combine the ternary elements of 6 paths to form the PLTP feature vector of each pixel point.

[0008] Further, in step S3, the specific steps are as follows: S31: Calculate the Hamming distance between the PLTP feature vector of each pixel of the grayscale image and the PLTP feature vector of its adjacent pixel; S32: Calculate the mean value of the Hamming distances obtained in step S31; S33: Subtract the corresponding mean value from the Hamming distance and perform ternarization processing using the threshold function to obtain the HDPLBP feature vector based on the Hamming distance.

[0009] Further, in step S31, perform an exclusive OR operation bit by bit on the PLTP feature vector of each pixel of the grayscale image and the PLTP feature vector of its adjacent pixel according to the number of bits of the ternary number, and then sum to obtain the Hamming distance between the PLTP feature vectors of these two pixels.

[0010] Further, in step S33, the specific steps are as follows: Divide the difference between the Hamming distance and the mean by a second threshold; Combine the differences calculated above in a specific direction to form an HDPLBP feature vector based on the Hamming distance.

[0011] Further, in step S4, the specific steps are as follows: Convert the PLTP feature vector and the HDPLTP feature vector of each pixel point into a PLTP feature descriptor and an HDPLTP feature descriptor respectively; Calculate the histograms of the PLTP feature descriptor and the HDPLTP feature descriptor respectively; Use the concatenation method to combine the two histograms calculated above to form a combined PLTP_HDPLTP descriptor histogram, which is used as the PLTP_HDPLTP texture feature of the image to be measured.

[0012] An image texture feature extraction system based on the Hamming-Petersen graph An image acquisition and preprocessing sub-module, which is used to acquire the image to be measured and perform gray-scale preprocessing to obtain a gray-scale image; A PLTP sub-module, which is used to extract ternary features by traversing the gray-scale image through the Petersen graph; construct a PLTP feature vector by using a threshold function; An HDPLTP sub-module, which is used to calculate the Hamming distance between the PLTP feature vector of each pixel point of the gray-scale image and the PLTP feature vector of its adjacent points, and generate an HDPLBP feature vector based on the Hamming distance; A PLTP_HDPLTP sub-module, which is used to merge the statistical histograms of the descriptors of the PLTP feature vector and the descriptors of the HDPLBP feature vector into a combined histogram, which is used as the PLTP_HDPLTP texture feature of the image to be measured.

[0013] A computer memory, which stores a computer program executable by a computer processor, and the computer program executes an image texture feature extraction method based on the Hamming-Petersen graph.

[0014] The beneficial effects of the present invention are: 1. A method and system for extracting image texture features based on the Hamming-Petersen graph. By analyzing the relationship between pixels of an image through the Petersen graph orientation, using a threshold function and a structural pattern to describe the local fluctuation trend of the relationship, and constructing a local ternary pattern PLTP feature vector of the Petersen graph; calculating the Hamming distance between the central point of the PLTP code and its adjacent points to extract the spatial structure of the PLTP code, thereby generating an HDPLBP feature vector based on the Hamming distance; merging the statistical histograms of the PLTP and HDPLBP descriptors into a PLTP_HDPLTP texture feature histogram, which is more effective for image texture analysis than traditional texture descriptors, taking into account both local information and spatial distribution information, and realizing the function of completely extracting image texture features.

[0015] 2. Based on the Petersen graph model in graph theory, the present invention takes into account the spatial shape information of the texture, improving the robustness, discriminability and applicability of the texture feature extraction operator.

[0016] 3. The present invention takes into account the Hamming distance relationship of the PLTP feature, making the HDPLTP a secondary feature and improving the accuracy of image texture description.

[0017] 2. The present invention combines the ternary PLTP feature and the HDPLTP feature, and merges their statistical histograms into a joint histogram, enabling the texture feature quantity to more intuitively and effectively characterize the image texture condition, ensuring that the texture description ability is more robust and stable.

[0018] Of course, it is not necessary for any product implementing the present invention to simultaneously achieve all the above-mentioned advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is the flowchart of an embodiment of the present invention.

[0021] Figure 2 is the structural diagram of the Petersen graph of an embodiment of the present invention.

[0022] Figure 3 is the ternary feature structure diagram of the vertex relationship of the Petersen graph of an embodiment of the present invention.

[0023] Figure 4 is the texture picture of different kinds of items of an embodiment of the present invention.

[0024] In the figure: (a) and (b) are brown bread images; (c) and (d) are biscuit images.

[0025] Figure 5 are the PLTP and HDPLTP feature histograms of different kinds of items in the embodiments of the present invention.

[0026] Figure 6 is the local ternary pattern (HDPLTP) graph of the Petersen graph based on the Hamming distance in the embodiments of the present invention.

[0027] Figure 7 is a schematic diagram of the average value of the Hamming distance from the central PLTP code to 8 neighboring PLTP codes in the embodiments of the present invention. Specific embodiments

[0028] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0029] Embodiment 1 Refer to Figure 1 , the specific steps of an image texture feature extraction method based on the Hamming-Petersen graph are as follows: S1: Obtain the image to be measured and perform grayscale preprocessing to obtain a grayscale image; S2: Traverse the grayscale image through the Petersen graph to extract ternary features; construct a PLTP feature vector using a threshold function; S3: Calculate the Hamming distance between the PLTP feature vectors of each pixel point of the grayscale image and the PLTP feature vectors of its adjacent points, and generate an HDPLBP feature vector based on the Hamming distance; S4: Combine the statistical histograms of the descriptors of the PLTP feature vectors and the statistical histograms of the descriptors of the HDPLBP feature vectors into a joint histogram as the PLTP_HDPLTP texture feature of the image to be measured.

[0030] Further, in step S2, the specific steps are: S21: Scan the grayscale image through the Petersen graph, directionally analyze the relationship between the pixels of the image, describe the local fluctuation trend of the relationship, and extract ternary features; S22: Calculate the gray difference structure of the ternary features, use a threshold function to judge the ternary features, and construct a PLTP feature vector.

[0031] Further, in step S21, the specific steps are: Traverse the pixels of the entire grayscale image using a 5×5 window according to the structure of the Petersen graph; According to the vertex relationship of the Petersen graph, six paths with a ternary structure are formed from the central pixel to the edge pixels of the window. The pixel set in the path is defined as: {[the grayscale value of the central pixel, the grayscale value of the inner ring pixel, the grayscale value of the inner ring pixel]}, that is, the grayscale difference structure of each pixel point is obtained.

[0032] In the step S22, the specific steps are as follows: Control the conversion width through the first threshold, and use a binary threshold function to distinguish the value of the grayscale difference; Use the threshold function to describe the fluctuation trend of the local grayscale difference pair, and use addition to construct the microscopic structure of the ternary pattern to obtain ternary elements; Combine the ternary elements of the six paths to form the PLTP feature vector of each pixel point.

[0033] In the step S3, the specific steps are as follows: S31: Calculate the Hamming distance between the PLTP feature vector of each pixel of the grayscale image and the PLTP feature vector of its adjacent pixel; S32: Calculate the mean value of the Hamming distances obtained in step S31; S33: Subtract the corresponding mean value from the Hamming distance, and perform a ternary processing using a threshold function to obtain the HDPLBP feature vector based on the Hamming distance.

[0034] Further, in the step S31, perform an exclusive OR operation bit by bit on the PLTP feature vector of each pixel of the grayscale image and the PLTP feature vector of its adjacent pixel according to the number of bits of the ternary number, and then sum to obtain the Hamming distance between the PLTP feature vectors of these two pixels.

[0035] In the step S33, the specific steps are as follows: Divide the difference between the Hamming distance and the mean value through the second threshold; Combine the differences calculated above in a specific direction to form the HDPLBP feature vector based on the Hamming distance.

[0036] In the step S4, the specific steps are as follows: Correspondingly convert the PLTP feature vector and the HDPLTP feature vector of each pixel point into a PLTP feature descriptor and an HDPLTP feature descriptor; Calculate the histogram of the PLTP feature descriptor and the histogram of the HDPLTP feature descriptor respectively; Use the concatenation method to combine the two histograms calculated above to form a combined PLTP_HDPLTP descriptor histogram, which is used as the PLTP_HDPLTP texture feature of the image to be tested.

[0037] In this embodiment, the relationship between pixels of an image is analyzed through the orientation of the Petersen graph. The threshold function and the structural pattern are used to describe the local fluctuation trend of the relationship, and the local ternary pattern PLTP feature vector of the Petersen graph is constructed. The Hamming distance between the center point of the PLTP encoding and its adjacent points is calculated to extract the spatial structure of the PLTP encoding, thereby generating the HDPLTP texture feature based on the Hamming distance. The statistical histograms of the PLTP and HDPLBP descriptors are combined into the PLTP_HDPLTP texture feature histogram, which is more effective for image texture analysis than traditional texture descriptors, taking into account both local information and spatial distribution information, and realizing the function of completely extracting image texture features.

[0038] Embodiment 2 The steps of this embodiment are the same as those of Embodiment 1, except that each step is applied to a specific example. Specifically, it includes the following steps: S1: Perform grayscale preprocessing on the image to be measured; S2: Traverse the grayscale image to be measured, extract ternary features through the Petersen graph structure, calculate the gray difference structure of the ternary features, and use the threshold function to judge the ternary features to obtain the local ternary pattern PLTP feature vector of the Petersen graph. The specific steps are as follows: Let x and y be the coordinates of the grayscale image . According to the structure of the Petersen graph, use a 5×5 window to traverse the pixel points of the entire grayscale image. As Figure 2 shown, the center pixel in the window to the edge element direction forms a ternary structure. Therefore, there are a total of 6 paths of ternary structure in each window. As Figure 3 , calculate the vertex relationship of the Petersen graph to extract ternary features, and the pixel set in the path is defined as: , where is the gray value of the center pixel, is the gray value of the inner ring pixel, is the gray value of the inner ring pixel. The pixel combinations corresponding to each path form six groups of ternary patterns constructed from the center vertex to the edge vertex direction:

[0039] In this way, each pixel point has 6 groups of gray difference structures:

[0040] The gray difference is divided into two levels, and a binary threshold function is used to process the value of the gray difference:

[0041] where the threshold T controls the conversion width and takes the value of 125.

[0042] For the comparison between ternary pixels, a threshold function is used to describe the fluctuation trend of local gray - level difference pairs, and the microstructure of the ternary pattern is constructed by addition, that is: Let be the unit step function, and the threshold T controls the conversion width. Described by a mathematical expression, it is:

[0043]

[0044] The PLTP texture feature of each pixel point is composed of the ternary elements of 6 paths combined together to form the local ternary pattern feature vector of the Petersen graph :

[0045] S3: Through the above - mentioned image PLTP vector, calculate the Hamming distance and its mean value between the PLTP vector of each pixel and its adjacent PLTP vectors. Subtract the mean value from the calculated Hamming distance and perform binarization processing with a threshold function to obtain the HDPLBP feature vector based on the Hamming distance. The specific steps are as follows: S31: Calculate the Hamming distance between the PLTP feature vector of the central pixel and the PLTP feature vectors of its adjacent pixels , to extract the spatial structure encoded by PLTP, as Figure 6 shown, and then obtain the local ternary pattern (HDPLTP) of the Petersen graph based on the Hamming distance:

[0046] where is the number of bits of the ternary number of the PLTP vector, represents the PLTP vector of the central pixel, is the PLTP vector of the i - th neighborhood, and ⊕ represents exclusive - or.

[0047] S32: As Figure 7 shown, calculate the average value m of the Hamming distances from the central PLTP code to the 8 - neighborhood PLTP codes:

[0048] S33: Divide the difference between these Hamming distances and the average value into three levels using the threshold . When takes the value of 1:

[0049] Generally, to ensure the rotation invariance of the texture, similar to Rotation LBP, the circular neighborhood can be continuously rotated to obtain a series of texture values, and the minimum value is taken as the final texture value of the neighborhood. For multi-scale, it can be achieved by the size of the radius and the number of sampling points in the neighborhood. To compare patterns, before extracting texture features, registration and correction are required, so the rotation and scaling problems can be ignored. The s values of the 8 neighborhoods are combined in a specific direction to form an HDPLBP feature vector based on the Hamming distance. :

[0050] S4: Combine the statistical histograms of the descriptors of the PLTP vector and the statistical histograms of the descriptors of the HDPLBP vector into a joint histogram as the PLTP_HDPLTP texture feature of the image to be tested. The specific steps are as follows: Convert the PLTP feature vector and the HDPLTP feature vector of each pixel point into PLTP feature descriptors and HDPLTP feature descriptors : , , Calculate the histograms of the PLTP feature descriptors and the HDPLTP feature descriptors respectively, and combine the two using the concatenation method to form a joint PLTP_HDPLTP descriptor histogram: .

[0051] To better show the discrimination ability of the PLTP_HDPLTP texture feature of this embodiment, the texture pictures in Figure 4 are used as examples. Among them, Figure a and Figure b are brown bread images, and Figure c and Figure d are biscuit images. First, convert the color images into gray images respectively. Then extract the PLTP and HDPLTP features from the four texture images and perform histogram statistics as shown in Figure 5 . It can be clearly seen that the PLTP and HDPLTP feature histograms from the same kind of items are very similar. In contrast, the PLTP and HDPLTP feature histograms from different kinds of items are significantly different, especially in the range of 150 to 200. Therefore, from a visual perspective, the PLTP_HDPLTP of this embodiment has satisfactory discrimination ability.

[0052] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0053] Embodiment 3 This embodiment is used to implement the principle of the above method embodiment to construct an image texture feature extraction system based on the Hamming-Petersen graph, including an image acquisition and preprocessing sub-module, a PLTP sub-module, an HDPLTP sub-module, and a PLTP_HDPLTP sub-module; The image acquisition and preprocessing sub-module is used to acquire the image to be measured and perform grayscale preprocessing to obtain a grayscale image; The PLTP sub-module is used to extract ternary features by traversing the grayscale image through the Petersen graph; construct a PLTP feature vector using a threshold function; The HDPLTP sub-module is used to calculate the Hamming distance between the PLTP feature vector of each pixel point of the grayscale image and the PLTP feature vector of its adjacent points, and generate an HDPLBP feature vector based on the Hamming distance; The PLTP_HDPLTP sub-module is used to merge the statistical histograms of the descriptors of the PLTP feature vector and the statistical histograms of the descriptors of the HDPLBP feature vector into a joint histogram as the PLTP_HDPLTP texture feature of the image to be measured.

[0054] Each sub-module is mainly used to implement each step of the method embodiment, which will not be elaborated here.

[0055] It should be noted that according to the needs of implementation, each step / component described in this application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0056] This embodiment further includes a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor is enabled to execute the steps of an image texture feature extraction method based on the Hamming-Petersen graph.

[0057] This embodiment further provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by the processor, the processor is enabled to implement an image texture feature extraction method based on the Hamming-Petersen graph.

[0058] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0059] Furthermore, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0060] The present application is described with reference to the flowcharts of the method and computer program product according to Embodiment 1 of the present application and the block diagrams of the device (system) according to Embodiment 3. It should be understood that each process or block in the flowchart or block diagram, as well as the combination of processes or blocks in the flowchart or block diagram, can be implemented by computer program instructions.

[0061] These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a Hamming-Peterson graph-based image texture feature extraction system for implementing the functions specified in one process Figure 1 one process or multiple processes or blocks Figure 1 or multiple blocks.

[0062] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes or blocks Figure 1 or multiple blocks.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, thereby providing the steps of a Hamming-Peterson graph-based image texture feature extraction method for implementing the functions specified in one process Figure 1 one process or multiple processes or blocks Figure 1 or multiple blocks.

[0064] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design concepts disclosed by the present invention are within the protection scope of the present invention.

Claims

1. An image texture feature extraction method based on the Hamming-Petersen graph, characterized in that: It includes the following steps: S1: Obtain the image to be measured and perform grayscale preprocessing to obtain a grayscale image; S2: Extract ternary features by traversing the grayscale image using the Petersen graph; construct a PLTP feature vector using a threshold function; S3: Calculate the Hamming distance between the PLTP feature vectors of each pixel point in the grayscale image and the PLTP feature vectors of its adjacent points, and generate an HDPLBP feature vector based on the Hamming distance; S4: Combine the statistical histograms of the descriptors of the PLTP feature vectors and the statistical histograms of the descriptors of the HDPLBP feature vectors into a joint histogram as the PLTP_HDPLTP texture feature of the image to be measured.

2. The image texture feature extraction method based on the Hamming-Petersen graph according to claim 1, characterized in that: In the step S2, the specific steps are: S21: Scan the grayscale image using the Petersen graph, directionally analyze the relationship between the pixels of the image, describe the local fluctuation trend of the relationship, and extract ternary features; S22: Calculate the gray difference structure of the ternary features, use a threshold function to judge the ternary features, and construct a PLTP feature vector.

3. The image texture feature extraction method based on the Hamming-Petersen graph according to claim 2, wherein: In the step S21, the specific steps are: Traverse the pixel points of the entire grayscale image using a 5×5 window according to the structure of the Petersen graph; According to the vertex relationship of the Petersen graph, 6 paths of ternary structure are formed from the center pixel to the edge pixel direction of the window, and the pixel set in the path is defined as: {[the gray value of the center pixel, the gray value of the inner ring pixel, the gray value of the inner ring pixel]}, that is, the gray difference structure of each pixel point is obtained.

4. A method for extracting image texture features based on the Hamming-Petersen graph according to claim 3, characterized in that: In the step S22, the specific steps are: Control the conversion width through the first threshold, and use a binary threshold function to distinguish the value of the gray difference; Use a threshold function to describe the fluctuation trend of the local gray difference pair, and use addition to construct the micro-structure of the ternary pattern to obtain ternary elements; Combine the ternary elements of 6 paths to form the PLTP feature vector of each pixel point.

5. The method for extracting image texture features based on the Hamming-Petersen graph according to claim 2, wherein: In the step S3, the specific steps are: S31: Calculate the Hamming distance between the PLTP feature vectors of each pixel in the grayscale image and the PLTP feature vectors of its adjacent pixels; S32: Calculate the mean value of the Hamming distances obtained in step S31; S33: Subtract the corresponding mean value from the Hamming distance and perform ternarization processing using a threshold function to obtain an HDPLBP feature vector based on the Hamming distance.

6. The image texture feature extraction method based on the Hamming-Petersen graph according to claim 5, characterized in that: In the step S31, perform an exclusive OR operation bit by bit on the PLTP feature vectors of each pixel in the grayscale image and the PLTP feature vectors of its adjacent pixels according to the number of digits of the ternary number, and then sum to obtain the Hamming distance between the PLTP feature vectors of these two pixels.

7. The method for extracting image texture features based on Hamming-Petersen graph according to claim 6, wherein: In the step S33, the specific steps are: Divide the difference between the Hamming distance and the mean value by the second threshold; Combine the calculated differences in a specific direction to form an HDPLBP feature vector based on the Hamming distance.

8. A method for extracting image texture features based on Hamming-Petersen graph according to claim 7, characterized in that: In the step S4, the specific steps are: Correspondingly convert the PLTP feature vector and the HDPLTP feature vector of each pixel point into a PLTP feature descriptor and an HDPLTP feature descriptor; Calculate the histogram of the PLTP feature descriptor and the histogram of the HDPLTP feature descriptor respectively; Use the concatenation method to combine the two histograms calculated above to form a combined PLTP_HDPLTP descriptor histogram, which serves as the PLTP_HDPLTP texture feature of the image to be measured.

9. An image texture feature extraction system based on the Hamming-Petersen graph, characterized in that: An image acquisition and preprocessing sub-module for acquiring the image to be measured and performing gray-scale preprocessing to obtain a gray-scale image; A PLTP sub-module for extracting ternary features by traversing the gray-scale image through the Petersen graph; Construct a PLTP feature vector using a threshold function; An HDPLTP sub-module for calculating the Hamming distance between the PLTP feature vector of each pixel point of the gray-scale image and the PLTP feature vector of its adjacent points, and generating an HDPLBP feature vector based on the Hamming distance; A PLTP_HDPLTP sub-module for merging the statistical histogram of the descriptors of the PLTP feature vector and the statistical histogram of the descriptors of the HDPLBP feature vector into a combined histogram, which serves as the PLTP_HDPLTP texture feature of the image to be measured.

10. A computer memory, characterized in that: It stores a computer program executable by a computer processor, and this computer program executes an image texture feature extraction method based on the Hamming-Petersen graph as described in any one of claims 1 to 8.

Images