A method for enhancing the detail of a single mine image based on fractal dimension maximization

Abstract

This application relates to the field of image enhancement technology, and in particular to a single-image mine detail enhancement algorithm based on fractal dimension maximization. The algorithm includes: acquiring the original image and calculating its gradient using the finite difference method; using the image gradient as a metric to perform fractal analysis on the original image to obtain its local fractal length and local fractal dimension data; dividing the local fractal dimension matrix into blocks, comparing the size of the local fractal dimensions within each block, and obtaining the maximum value within each block; performing pixel-by-pixel gradient reconstruction based on fractal theory, and combining the results to obtain the theoretically enhanced image gradient; calculating the enhanced image pixel values ​​from the reconstructed image gradient, the original image, and its gradient; and finally reconstructing the image. Utilizing multi-scale computation for fractal analysis of mine images can effectively capture many detailed information within the image. By maximizing the fractal dimension, it not only enhances important details in the image but also maintains the naturalness of the details and the realism of the image.

Description

Technical Field

[0001] This application relates to the field of image enhancement technology, and in particular to a method for enhancing the details of a single mine image based on fractal dimension maximization. Background Technology

[0002] In the construction of smart mines, the application of digital technologies has become an important means to promote the modernization of the mining industry, especially the widespread application of image processing and analysis technologies in mine monitoring, resource exploration, and equipment maintenance. As smart mines gradually achieve "unmanned" and "intelligent" operation, efficient image detail enhancement technologies will provide stronger support for mine safety management, production monitoring, and environmental monitoring. Applying image detail enhancement algorithms to smart mine construction can significantly improve the accuracy and efficiency of image processing, and bring innovative solutions to mine construction and management at multiple levels.

[0003] In various applications of smart mines, such as real-time monitoring of the ore mining process, fault diagnosis of mine equipment, and monitoring of the mining environment, high-quality image data is essential. Mine areas are often situated in complex terrain and environmental conditions, resulting in common problems such as unclear details and significant interference in images. Traditional image enhancement methods (such as histogram equalization and image sharpening) tend to overemphasize noise or produce severe artifacts when improving image contrast, affecting the actual usability of the images. Images in smart mines are highly diverse, involving multiple aspects such as geological exploration, equipment monitoring, and personnel safety. Each type of image has different detailed features and noise characteristics. Mine images contain complex backgrounds and lighting variations, making it difficult to optimize image processing algorithms, and noise is often difficult to distinguish from details.

[0004] Existing technologies often prioritize either noise suppression or detail preservation, making it difficult to achieve both simultaneously. While deep learning methods are effective, data annotation in mining environments is challenging and requires substantial computational resources, posing a bottleneck, especially in scenarios with high real-time requirements. Summary of the Invention

[0005] The technical problem this invention aims to solve is that existing image recognition algorithms have poor image detail enhancement effects.

[0006] Therefore, the present invention provides a method for enhancing the details of a single mine image based on fractal dimension maximization.

[0007] The technical solution adopted by this invention to solve its technical problem is:

[0008] A method for enhancing the details of a single mine image based on fractal dimension maximization includes the following steps:

[0009] Step 1: Obtain the original image and use the finite difference method to calculate the gradients in the vertical and horizontal directions of the original image;

[0010] Step 2: Perform fractal analysis on the original image, using the image gradient as a metric to obtain the local fractal length and local fractal dimension data of the original image;

[0011] Step 3: Divide the original image into blocks, compare the size of the local fractal dimension within each block, and obtain the maximum value of the local fractal dimension;

[0012] Step 4: Perform pixel-by-pixel gradient reconstruction and combine the results to obtain the enhanced image gradient;

[0013] Step 5: Calculate the enhanced image pixel values ​​from the reconstructed image gradient, the original image, and its gradient, and finally reconstruct the image.

[0014] Furthermore, in step one, the gradients in the vertical and horizontal directions of the original image are calculated using the pixel-by-pixel difference method. ,in and These represent the directional difference values ​​in the X and Y directions, respectively. This represents the gradient of a pixel in an image.

[0015] Furthermore, in step two, a pixel is considered as a fractal set, and the pixel gradient is considered as a metric for the pixel. The dimension of the fractal set is... any point in a fractal set The corresponding density function is: ,in For density functions, in digital images, It is a constant. This indicates the scale of the fractal analysis. One standard deviation is , radius is Gaussian kernel, This represents the metric value calculated using the image gradient as a measure, where z is the integral element introduced for convolution integration.

[0016] Furthermore, in step two, the pixel point Local fractal dimension Local fractal length at a pixel ,satisfy .

[0017] Furthermore, in step three, the reconstructed image satisfies: ,in, Represents the reconstructed image pixels gradient value at, This represents the maximum fractal dimension within the local region.

[0018] Furthermore, in step four, the theoretical gradient value of the enhanced image is calculated based on the gradient of the reconstructed image and the metric value obtained by using the image gradient as a measure. : .

[0019] Furthermore, in step four, the detailed layer of the magnified image is superimposed onto the original image to enhance image details.

[0020] Furthermore, in step four, the difference between the enhanced gradient value and the original image gradient value is taken as the detail layer, then multiplied by an enhancement factor and superimposed on the original image to obtain the image with enhanced details: ,in, Represents the original image. This represents an image with enhanced details. It is an enhancing factor.

[0021] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the above-described method.

[0022] A computer device, comprising:

[0023] A memory on which computer programs are stored;

[0024] A processor for executing the computer program in the memory to implement the steps of the above method.

[0025] The beneficial effects of this invention are:

[0026] The image detail enhancement algorithm presented in this application can significantly improve the quality of mine images, helping to enhance automated monitoring and safety management, while reducing reliance on high-performance computing resources and improving the system's real-time performance and cost-effectiveness. This not only optimizes the production process but also ensures miners' safety and promotes the development of mines towards intelligence and automation.

[0027] This application employs a method that maximizes fractal dimension. Fractal dimension, through multi-scale analysis, can better capture many detailed information in mining area images (such as rock structure, mineral distribution, equipment status, etc.). This not only enhances important details in the image but also ensures the naturalness and realism of those details, which is particularly important for smart mine applications. For example, in mine environmental monitoring, enhancing image details can better identify abnormal changes or dangerous signs in the mining area, providing effective support for mine safety management. Attached Figure Description

[0028] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0029] Figure 1 This is a flowchart of the single-image mine detail enhancement method based on fractal dimension maximization in this invention.

[0030] Figure 2 This is a schematic diagram of the single-image mine detail enhancement method based on fractal dimension maximization in this invention.

[0031] Figure 3 This is a schematic diagram of the regression fitting algorithm for local fractal dimension and local fractal length in this invention.

[0032] Figure 4 This is a subjective comparison of the image detail enhancement algorithm of this invention with other existing algorithms for processing images of coal feeders in underground ventilation roadways.

[0033] Figure 5 This is a subjective comparison of the image detail enhancement algorithm of this invention with other existing algorithms for processing mine tunnel images. Detailed Implementation

[0034] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0035] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, features defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0036] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0037] Example 1

[0038] A single-image mine detail enhancement algorithm based on fractal dimension maximization is proposed, which consists of three modules: gradient calculation module, fractal analysis module, and image enhancement module.

[0039] The gradient calculation module is implemented using the pixel-by-pixel difference method.

[0040] The fractal analysis module starts from the image gradient, fits the data by transforming different scales, and finally solves for the slope and intercept of the fitted line, which are the local fractal dimension and local fractal length of the image.

[0041] The image enhancement module first divides the original image into blocks, taking the maximum value of the local fractal dimension within each block. Then, it inversely derives the theoretical gradient value of the enhanced image based on the relationship between gradient values. The difference is then used to obtain the detail layer, which is multiplied by an enhancement factor and superimposed on the original image to obtain the image with enhanced details.

[0042] Based on the above three modules, the specific method for enhancing the details of a single mine image based on fractal dimension maximization includes the following steps:

[0043] Step 1: Obtain the original image and calculate the gradients in the vertical and horizontal directions of the original image using the pixel-by-pixel difference method to prepare for subsequent image fractal analysis.

[0044] The directional difference values ​​are calculated using the finite difference method, and then the gradient is calculated using these values.

[0045] (1)

[0046] in and These represent the directional difference values ​​in the X and Y directions, respectively. This represents the gradient of an image pixel.

[0047] Step two involves performing fractal analysis on the original image to obtain local fractal length and local fractal dimension data, preparing for subsequent image enhancement.

[0048] If we consider each pixel of an image as a fractal set, and the set of all pixels as the union of these fractal sets, then the corresponding gradient can be seen as a metric. If the dimension of the fractal set is... Then, in the metric space defined using image gradient as a metric, any point in the fractal set... The corresponding density function is:

[0049] (2)

[0050] in Let be the density function. This indicates the scale of the fractal analysis. One standard deviation is , radius is Gaussian kernel, This represents the metric value calculated using the image gradient as a measure, where z is the integral element introduced for convolution integration.

[0051] Since we now use digital images, and in digital images each pixel is uniformly distributed, the density function... If is a constant, then it can be deduced that:

[0052] (3)

[0053] in, Represents pixels The local fractal dimension at that location, The local fractal length at the pixel.

[0054] By transforming different scales By fitting the data, we can obtain information about the scale. and their corresponding measure values exist If a straight line is in the coordinate system, then solving for the slope and intercept of the fitted line (4) will approximate the local fractal dimension and local fractal length of the image:

[0055] (4)

[0056] Figure 3 Two examples from the fitting process are given, each involving two pixels from image 56028 in the BSDS200 dataset. Figure 3 (a) The smaller plot shows the B channel of (21, 37), and the analytical expression of the regression line is: The fractal dimension was found to be 1.9894, and the local fractal length was 7.2253. The smaller plot in Figure (b) shows the G channel at (200, 266), and the regression line is expressed as follows: The fractal dimension is obtained as The local fractal length is .

[0057] Step 3: Divide the image into blocks, compare the size of the local fractal dimensions within each block, and obtain the maximum local fractal dimension. If the original image satisfies equation (4), then similarly, the reconstructed image after dividing the original image into blocks also satisfies the relationship of equation (4), and the reconstructed image satisfies:

[0058] (5)

[0059] in, Represents the reconstructed image pixels gradient value at, This represents the maximum fractal dimension within the local region.

[0060] Step four involves pixel-by-pixel gradient reconstruction, which is then combined to obtain the enhanced image gradient. The pixel values ​​of the enhanced image are calculated from the reconstructed image gradient, the original image, and its gradient, and finally, the image is reconstructed.

[0061] From equations (4) and (5), we can deduce equation (6). Thus, we have obtained the theoretical gradient value of the enhanced image. :

[0062] (6)

[0063] Furthermore, the reconstructed image includes:

[0064] An image can generally be broken down into a smoothing layer and a detail layer. Image detail can be enhanced by magnifying the detail layer and then overlaying it onto the original image.

[0065] (7)

[0066] in, Represents the original image. Indicates a smoothing layer. Representing the detail layer, This represents an image with enhanced details. It is an enhancing factor.

[0067] In this invention, the gradient value is considered as the image detail layer. The difference lies in that the difference between the enhanced gradient value and the original image gradient value is used as the detail layer, which is then multiplied by an enhancement factor and superimposed onto the original image to obtain the image with enhanced details.

[0068] (8)

[0069] Furthermore, the overall flow of the algorithm is shown in the pseudocode:

[0070] Input: Raw mine image

[0071] Output: High-quality mine images with enhanced details

[0072] For i = 1 to M:

[0073] For j = 1 to N:

[0074] First, calculate the directional difference values ​​in the X and Y directions using equation (1). Use it to calculate image gradient :

[0075] For r = 1 to R:

[0076] Perform Gaussian convolution operations on the image at each scale and store the results in a three-dimensional variable.

[0077]

[0078] end

[0079] After slicing the three-dimensional variables, pixel-by-pixel regression analysis is performed using equations (2) to (4) to solve the linear equation system and obtain the slope and intercept, which are the local fractal dimensions of the image. and local fractal length

[0080]

[0081] The image is divided into blocks based on its local fractal dimension, and the local fractal dimension within each block is... Pick ;

[0082] Based on image fractal theory, gradient reconstruction is performed using equations (4) to (6).

[0083]

[0084] Enhance details using equations (7) and (8)

[0085]

[0086] end

[0087] end

[0088] To visually demonstrate the effectiveness of the MFD (Detail Enhancement Method Based on Maximizing Fractional Dimension) algorithm in this invention, a comparison with several other image detail enhancement algorithms is provided. The compared algorithms include GIF, GGIF, WGIF, BFLS, TH, and ILS, representing common methods in the current image enhancement field. To verify the superiority of the algorithm in this invention, subjective visual effect comparison images and objective numerical evaluation metrics are provided on classic datasets. To objectively evaluate image quality, we selected the internationally accepted Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) as evaluation criteria, with equations (9) and (10) showing their calculation methods. PSNR measures the noise and distortion of an image, while SSIM evaluates the structural fidelity of the image; the combination of these two metrics provides a more comprehensive reflection of image quality.

[0089] (9)

[0090] (10)

[0091] in It is the maximum pixel value in the processed image. It is the mean square error. and The average brightness values ​​of the original image and the image to be calculated. and These are the variances of the original image and the image to be calculated, respectively. It is the covariance between the original image and the image to be calculated. and It is a constant term that has no practical meaning and serves a regulatory function.

[0092] Figure 4 and Figure 5 Two example images of mine operation sites are shown. Figure 4 This is a comparison chart showing the recognition performance of images of coal feeders in underground ventilation roadways. Figure 4The middle image (a) is the original image of the coal feeder in the ventilation tunnel; (a1) is the image processed using the GIF algorithm, with maximum values ​​of 34.97 dB and 0.9978 in PSNR and SSIM, respectively; (a2) is the image processed using the GGIF algorithm, with values ​​of 30.88 dB and 0.9853 in PSNR and SSIM, respectively; (a3) ​​is the image processed using the WGIF algorithm, with values ​​of 33.35 dB and 0.9976 in PSNR and SSIM, respectively; (a4) is the image processed using the BFLS algorithm, with values ​​of 34.97 dB and 0.9978 in PSNR and SSIM, respectively. The values ​​in the SSIM numerical evaluation are 27.87 dB and 0.9399, respectively; (a5) The inset is the image processed by the TH algorithm, with values ​​of 28.86 dB and 0.9700 in the PSNR and SSIM numerical evaluations, respectively; (a6) The inset is the image processed by the ILS algorithm, with values ​​of 28.68 dB and 0.9610 in the PSNR and SSIM numerical evaluations, respectively; (a7) The inset is the image processed by the MFD algorithm in this application, with values ​​of 35.68 dB and 0.9980 in the PSNR and SSIM numerical evaluations, respectively; (a8) The inset is the original image GT (ground truth).

[0093] Figure 5 This is a comparison chart showing the recognition performance of images of mine tunnels. Figure 5 (b) The small image shows the original image of the mine tunnel. (b1) The small image is the image processed using the GIF algorithm, with PSNR and SSIM values ​​of 34.15 dB and 0.9842, respectively. (b2) The small image is the image processed using the GGIF algorithm, with PSNR and SSIM values ​​of 31.09 dB and 0.9542, respectively. (b3) The small image is the image processed using the WGIF algorithm, with PSNR and SSIM values ​​of 31.82 dB and 0.9698, respectively. (b4) The small image is the image processed using the BFLS algorithm, with PSNR and SSIM values ​​of 34.15 dB and 0.9842, respectively. The numerical evaluation values ​​of IM are 29.22 dB and 0.8979, respectively; (b5) The inset is the image processed by the TH algorithm, with numerical evaluation values ​​of 29.22 dB and 0.9083 for PSNR and SSIM, respectively; (b6) The inset is the image processed by the ILS algorithm, with numerical evaluation values ​​of 29.12 dB and 0.9046 for PSNR and SSIM, respectively; (b7) The inset is the image processed by the MFD algorithm in this application, with numerical evaluation values ​​of 36.15 dB and 0.9962 for PSNR and SSIM, respectively; (b8) The inset is the original image GT (ground truth).

[0094] From a visual perspective, the algorithm in this invention demonstrates a relatively ideal effect in both enhancing image details and avoiding excessive noise amplification. Other enhancement algorithms, to varying degrees, suffer from problems such as over-enhancement leading to image distortion and severe artifacts. Figure 4 , 5 Other algorithms in the model clearly amplify noise in the image excessively, resulting in a mosaic effect and severe color distortion in certain areas, with large patches of green and purple. These limitations restrict their widespread application in smart mine construction. Furthermore, this invention not only offers excellent detail enhancement but also causes relatively minor alterations to the original image, achieving maximum values ​​in both PSNR and SSIM evaluations.

[0095] This invention also provides Mean Opinion Score (MOS) test results. The MOS test is a widely used subjective standard method for evaluating image and video quality, particularly in fields such as communications, video processing, and image compression. The MOS test reflects human observers' perception of image or video quality by quantifying a set of user ratings.

[0096] Assume there is Each rater rates an image or video. The calculation formula is Equation (9), which is based on the opinions of a group of human observers on the quality of the image or video and calculates the average value.

[0097] (11)

[0098] in It is the first Each observer rates the image.

[0099] according to The test results (shown in Table 1) demonstrate that the algorithm in this invention performs optimally or nearly optimally on the BSDS200, RealSRSet, and T91 datasets, proving its outstanding performance in image enhancement. Particularly in processing low-quality images, this algorithm shows significant advantages over traditional methods, effectively improving image quality and conforming to the visual perception of most people, showcasing its stability and superiority in improving visual effects.

[0100] Table 1 MOS Test Results

[0101] To further illustrate the effectiveness of the algorithm, this invention also provides quantization comparison results with other algorithms on different datasets, including BSDS200, RealSRSet, and T91. The algorithms compared include GIF, GGIF, WGIF, BFLS, TH, ILS, and ZF, all of which are common methods in the current field of image detail enhancement. As shown in Table 2, the MFD algorithm model from this application demonstrates the best quantization results on all three datasets.

[0102] Table 2 Quantitative Comparison Results

[0103]

[0104] In summary, the algorithm in this invention demonstrates powerful image enhancement capabilities, resulting in clearer image details and a more natural visual effect. For high-contrast, color-rich images, the algorithm effectively preserves color saturation and detail levels, avoiding distortion caused by over-enhancement. Comparative results show that the algorithm not only improves image quality but also effectively preserves details, demonstrating greater potential. Compared to traditional methods, this algorithm outperforms traditional methods in preserving image details and structure, avoiding color distortion, excessive noise amplification, and severe gradient artifacts. Through a local fractal adaptive mechanism, the algorithm enhances visual effects while preserving the original image structure.

[0105] The detail enhancement method based on fractal dimension maximization proposed in this invention not only has significant academic value but also holds great potential in practical mine operations. It can further improve the quality and efficiency of image enhancement, providing more precise support for smart mines. The application of this algorithm in smart mine construction can effectively solve the problems of traditional image enhancement technologies, improve image analysis capabilities in mine monitoring, equipment management, and environmental protection, and promote the development of mines towards intelligence, efficiency, and safety.

[0106] Example 2

[0107] This application provides a computer device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement a single-frame mine image detail enhancement method based on fractal dimension maximization as provided in the above method embodiments.

[0108] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits can be wholly or partially embodied in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuit can be a single, independent processing module, or wholly or partially integrated into other components of a computer device (or mobile device). As involved in the embodiments of this application, the data processing circuit serves as a processor control (e.g., selection of a variable resistor termination path connected to an interface). The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to a rolling bearing fault intelligent diagnosis method in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing one of the aforementioned methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device is used to receive or send data via a network. Specific examples of the network described above may include wireless networks provided by the communication providers of the computer equipment. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module for wireless communication with the Internet. The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer equipment (or mobile device).

[0109] Example 3

[0110] This application embodiment also provides a computer-readable storage medium, which can be disposed in a server to store at least one instruction or at least one program related to implementing a single-frame mine image detail enhancement method based on fractal dimension maximization provided in the method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the single-frame mine image detail enhancement method based on fractal dimension maximization provided in the above-described method embodiment. Optionally, in this embodiment, the storage medium can be located in at least one of multiple network servers in a computer network. Optionally, in this embodiment, the storage medium can include, but is not limited to, various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0111] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined by the scope of the claims.

Claims

1. A method for enhancing the details of a single mine image based on fractal dimension maximization, characterized in that, Includes the following steps, Step 1: Obtain the original image and use the finite difference method to calculate the gradients in the vertical and horizontal directions of the original image; Step 2: Perform fractal analysis on the original image, using the image gradient as a metric to obtain the local fractal length and local fractal dimension data of the original image; In step two, pixels Local fractal dimension The local fractal length at pixel x ,satisfy r represents the scale of the fractal analysis. Represents the gradient of pixels in an image. This represents the measure value calculated using the image gradient as a metric. Step 3: Divide the original image into blocks, compare the size of the local fractal dimension within each block, and obtain the maximum value of the local fractal dimension; Step 4: Perform pixel-by-pixel gradient reconstruction and combine the results to obtain the enhanced image gradient; Step 5: Calculate the enhanced image pixel values ​​from the reconstructed image gradient, the original image, and its gradient, and finally reconstruct the image; The reconstructed image satisfies: ,in, Represents the reconstructed image pixels gradient value at, This represents the maximum value of the fractal dimension within the local region; The theoretical gradient value of the enhanced image is derived from the gradient of the reconstructed image and the metric value calculated using the image gradient as a measure. : ; The difference between the enhanced gradient value and the original image gradient value is considered as the detail layer. This layer is then multiplied by an enhancement factor and superimposed onto the original image to obtain the image with enhanced details. ,in, Represents the original image. This represents an image with enhanced details. It is an enhancing factor.

2. The method for enhancing the detail of a single mine image based on fractal dimension maximization according to claim 1, characterized in that, In step one, the gradients in the vertical and horizontal directions of the original image are calculated using the pixel-by-pixel difference method. ,in and These represent the directional difference values ​​in the X and Y directions, respectively. This represents the gradient of a pixel in an image.

3. The method for enhancing the detail of a single mine image based on fractal dimension maximization according to claim 1, characterized in that, In step two, a pixel is considered as a fractal set, and the pixel gradient is considered as a metric for the pixel. The dimension of the fractal set is... any point in a fractal set The corresponding density function is: ,in For density functions, in digital images, It is a constant. This indicates the scale of the fractal analysis. One standard deviation is , radius is Gaussian kernel, Represents the gradient of pixels in an image. This represents the measure value calculated using the image gradient as a metric, where z is the integral element introduced for convolution integration.

4. The method for enhancing the detail of a single mine image based on fractal dimension maximization according to claim 1, characterized in that, In step four, the detailed layer of the image is magnified and then superimposed onto the original image to enhance image details.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-4.

6. A computer device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-4.

Images