Ancient book calculation image restoration method, terminal equipment and storage medium

Abstract

The invention discloses an ancient book calculation image restoration method, terminal equipment and a storage medium, and relates to the technical field of image restoration, and the method comprises the steps of 1, ancient book damage area analysis, 2, ancient book penetration feature analysis and 3, ancient book restoration processing. Therefore, the damaged areas can be ignored during subsequent permeation image restoration, the image restoration accuracy is improved, pixel point interval division is performed on each page to which the paper ancient book belongs, so that each pixel point of each pixel point composition area of the target image of each page to which the paper ancient book belongs in each target gray value interval is obtained, and the image restoration accuracy is improved. And according to the influence of the related points of the adjacent page and the back page on the ink of the page, the gray value of each pixel point is intelligently adjusted, and the abnormal pixel points are removed from the region formed by the pixel points, so that the restoration of the ink of the ancient book is guaranteed, and the accuracy of image restoration is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image restoration, and particularly relates to a method for restoring ancient book calculation images, a terminal device, and a storage medium. Background Art

[0002] Traditional restoration of ancient books mainly relies on manual methods. However, manual restoration is slow, inefficient, and it is difficult to ensure the consistency of the restoration results. In addition, for some large-area damages or complex image problems, manual restoration is more difficult. In contrast, digital restoration can convert ancient books into electronic data, which is convenient for long-term preservation and wide dissemination. Therefore, it is necessary to study the image restoration of ancient books.

[0003] The prior art, such as the method and system for digital display of cultural relics disclosed in the invention patent application with the publication number of CN117893709A, includes: collecting multi-point clouds of cultural relics, performing point cloud registration by calculating the cumulative transformation matrix to obtain an integrated point cloud; dividing the integrated point cloud into a series of block point clouds, extracting isosurfaces and generating a three-dimensional curved surface, discretizing the three-dimensional curved surface, and constructing a three-dimensional grid model; calculating the shadow factor of each point in the three-dimensional grid model to determine the shadow area; calculating the surface reflection component and refractive index based on the surface material and color of the cultural relic to determine the surface details; and constructing the final digital image of the cultural relic based on the surface of the cultural relic, combining the shadow area and the surface details.

[0004] The prior art, such as the image restoration method, device, and computer-readable medium disclosed in the invention patent application with the publication number of CN118014903A, includes: separately extracting the text content in the image for text content correction. When applied to the restoration of ancient book images, it can correct specific text types in ancient books such as poems, thus effectively restoring the problem of text errors and omissions. At the same time, when regenerating the image, the cross-attention mechanism is used, combining the position, content of the text, and the features of the input image, so that the restored image can restore text errors and omissions, improve clarity, and maintain the same image style as the input image, thereby more effectively realizing image restoration.

[0005] In view of the above solutions, the current ancient book image restoration technology lacks certain attention to the analysis of the influence of the back page and adjacent pages on ancient books. When originally writing on paper ancient books, due to problems such as uneven writing force, the writing ink is often uneven. And during long-term preservation, due to reasons such as moisture, the writing ink will seep outwards, causing the pages of ancient books to gradually become blurred. In addition to the influence of the writing ink on this page, if the writing ink at the corresponding points of the adjacent page and the back page is too heavy, it will also cause the problem of seepage at the corresponding points of this page, resulting in the problem of blurred pages of ancient books. If the influence of other pages on a single page is not considered, the accuracy of ancient book image restoration will be reduced. Summary of the Invention

[0006] The object of the present invention is to provide a method for repairing ancient book calculation images, a terminal device and a storage medium, which solve the problems existing in the background technology.

[0007] To solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect of the present invention, a method for repairing ancient book calculation images is provided, including: Step 1. Analysis of damaged areas of ancient books: Obtain the images of each page of the paper ancient book under the target color background and under each color background, and analyze each damaged area of each page of the paper ancient book.

[0008] Step 2. Analysis of penetration characteristics of ancient books: Analyze the images of each page of the paper ancient book after penetration fading treatment.

[0009] Step 3. Repair processing of ancient books: Send the images of each page of the paper ancient book after penetration fading treatment to the management person in charge.

[0010] In the second aspect of the present invention, a terminal device is provided, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a method for repairing ancient book calculation images as described above.

[0011] In the third aspect of the present invention, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for repairing ancient book calculation images as described in any one of the above are implemented.

[0012] The beneficial effects of the present invention are as follows: (1) In Step 1. Analysis of damaged areas of ancient books of the present invention, by initially detecting each damaged area of each page of the paper ancient book, when performing subsequent penetration image repair, these damaged areas can be ignored, improving the accuracy of image repair.

[0013] (2) In Step 2. Analysis of penetration characteristics of ancient books of the present invention, by dividing the pixel point intervals of each page of the paper ancient book, the pixel points of each pixel point composition area of the target image of each page of the paper ancient book in each target gray value interval are obtained, and according to the influence of relevant points on adjacent pages and the back page on the writing of this page, the gray values of each pixel point are intelligently adjusted, and abnormal pixel points are removed from each pixel point composition area, thereby ensuring the restoration of the writing of ancient books and improving the accuracy of image repair.

[0014] (3) In Step 3. Repair processing of ancient books of the present invention, by sending the repaired image to the person in charge, the digital preservation of ancient books is ensured. Brief Description of the Drawings

[0015] 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 the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic flowchart of the method of the present invention. Specific embodiments

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] Refer to Figure 1 As shown, the first aspect of the present invention provides an ancient book calculation image restoration method, including: Step 1. Analysis of damaged areas of ancient books: Obtain images of each page of the paper ancient book under the target color background and under each color background, and analyze each damaged area of each page of the paper ancient book.

[0019] In a specific embodiment, the method for obtaining images of each page of the paper ancient book under the target color background and under each color background is as follows: Through an intelligent robot, place the background light-emitting board on the back page of each page of the paper ancient book, and obtain images of each page of the paper ancient book under the target color background and under each color background through a camera.

[0020] In a specific embodiment of the present invention, the method for analyzing each damaged area of each page of the paper ancient book is as follows: Based on the images of each page of the paper ancient book under each color background, through gray-scale transformation, extract the gray-scale values of each pixel point of the images of each page of the paper ancient book under each color background.

[0021] Obtain the gray-scale values of the target color background and each color background from the local database. If the gray-scale value of a certain pixel point in the image of a certain page of the paper ancient book under each color background is the same as the gray-scale value of each color background, then mark the pixel point of the image of this page of the paper ancient book under the target color background as a damaged pixel point, so as to screen out each damaged pixel point of the images of each page of the paper ancient book under the target color background.

[0022] It should be noted that the local database is used to store the target color background, the gray values of each color background, the threshold of the number of damaged pixel points, each target gray value interval, the gray value of the page background, the adjacent pixel points and the back pixel points of each pixel point of each page to which the paper ancient book belongs, and the gray value decrease corresponding to each gray anomaly coefficient interval.

[0023] If a damaged pixel point of an image of a certain page to which the paper ancient book belongs is adjacent to another damaged pixel point under the target color background, then this damaged pixel point and the other damaged pixel point are merged into a region to be analyzed. And if there is another damaged pixel point adjacent to this region to be analyzed, then this other damaged pixel point is merged into this region to be analyzed, so as to obtain each region to be analyzed and the number of its damaged pixel points for each page to which the paper ancient book belongs.

[0024] Obtain the threshold of the number of damaged pixel points from the local database. If the number of damaged pixel points in a region to be analyzed of a certain page to which the paper ancient book belongs is greater than the threshold of the number of damaged pixel points, then this region to be analyzed is marked as a damaged region, so as to screen out each damaged region for each page to which the paper ancient book belongs.

[0025] Step 1. Analysis of damaged regions of ancient books in the present invention: By initially detecting each damaged region of each page to which the paper ancient book belongs, when subsequent osmotic image repair is carried out, these damaged regions can be ignored, thereby improving the accuracy of image repair.

[0026] Step 2. Analysis of osmotic characteristics of ancient books: Analyze the images of each page to which the paper ancient book belongs after osmotic fading treatment.

[0027] In a specific embodiment of the present invention, for the analysis of the images of each page to which the paper ancient book belongs after osmotic fading treatment, the specific analysis method is as follows: The image obtained by removing each damaged region from the image of each page to which the paper ancient book belongs under the target color background is marked as the target image, so as to obtain the target images of each page to which the paper ancient book belongs, and through gray-scale transformation, obtain the gray values of each pixel point of the target images of each page to which the paper ancient book belongs, and extract the gray values of each pixel point of the target images of the adjacent pages and the back pages of each page to which the paper ancient book belongs.

[0028] It should be noted that the page on the same paper as each page to which the paper ancient book belongs is the back page, and the page on the adjacent page but not on the same paper as each page to which the paper ancient book belongs is the adjacent page.

[0029] Obtain each target gray value interval from the local database, analyze the regions and their pixel points formed by each pixel point of the target images of each page to which the paper ancient book belongs in each target gray value interval, and accordingly analyze the gray target values of each pixel point of the regions formed by each pixel point of the target images of each page to which the paper ancient book belongs in each target gray value interval.

[0030] If the gray target value of a pixel in the area composed of pixels of the target image of a certain page of the paper ancient book in a certain target gray value range is not included in the target gray value range, then mark this pixel as an abnormal pixel; otherwise, mark this pixel as a normal pixel, so as to screen out the abnormal pixels and normal pixels of the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range.

[0031] Obtain the page background gray value from the local database, and use it as the gray value of each abnormal pixel in the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range. Remove the pixels in each target gray value range from the target image of each page of the paper ancient book, and mark the remaining pixels as the background pixels of each page of the paper ancient book, and use the page background gray value as the gray value of each background pixel of each page of the paper ancient book.

[0032] Use the gray target value of each normal pixel in the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range as the gray value of the corresponding pixel in the image after osmotic desalination processing.

[0033] In summary, the images after osmotic desalination processing for each page of the paper ancient book are obtained.

[0034] In a specific embodiment, the analysis of the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range and its pixels, the specific analysis method is: according to the gray values of the pixels of the target image of each page of the paper ancient book, map to obtain the pixels of the target image of each page of the paper ancient book in each target gray value range, and according to the method of each area to be analyzed of each page of the paper ancient book, similarly analyze to obtain the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range and its pixels.

[0035] In a specific embodiment of the present invention, the analysis of the gray target value of each pixel in the area composed of pixels of the target image of each page of the paper ancient book in each target gray value range, the specific analysis method is: obtain the adjacent pixels and back pixels of each pixel of each page of the paper ancient book from the local database.

[0036] It should be noted that the adjacent pixels of a certain pixel of a certain page of the paper ancient book are the corresponding pixels of the adjacent page and this page, and the back pixel is the corresponding pixel of the back page and this page.

[0037] According to the grayscale values of each pixel of the target image of each page of the paper ancient book, extract the grayscale values of the pixels, the grayscale values of adjacent pixels, and the grayscale values of the back pixels in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval, and further extract the grayscale values of the outermost pixels, the grayscale values of adjacent pixels, and the grayscale values of the back pixels in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval.

[0038] Calculate the grayscale anomaly coefficient of each outermost pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval.

[0039] Calculate the grayscale target value of each outermost pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval, and calculate the grayscale anomaly coefficient of each second-layer pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval based on this, and so on, until the grayscale target value of each pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval is calculated.

[0040] It should be noted that in the present invention, the calculation is gradually performed on each pixel of each layer in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval, and the calculation result of the upper layer will affect the calculation result of the lower layer, so as to ensure the accuracy of image restoration.

[0041] It should also be noted that the outermost pixels are the pixels in the area composed of the pixels of the target image of a certain page of the paper ancient book in a certain target grayscale value interval that are in contact with other pixels outside the area composed of the pixels. The second-layer pixels are the pixels in the area composed of the pixels of the target image of this page of the paper ancient book in this target grayscale value interval that are in contact with the outermost pixels, and so on to obtain the third-layer pixels, the fourth-layer pixels, and so on.

[0042] In a specific embodiment of the present invention, the specific analysis method for calculating the grayscale anomaly coefficient of each outermost pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval is as follows: According to the grayscale values of each pixel of the target image of each page of the paper ancient book, extract the grayscale values of the pixels adjacent to the outermost pixels in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval, and calculate the grayscale hazard coefficient β of the relevant pixels of each outermost pixel in the area composed of the pixels of the target image of each page of the paper ancient book in each target grayscale value interval xinr and the grayscale hazard coefficient ε of the back pixels xinr, where x represents the page number of each page, x = 1, 2,..., y, y is a positive integer greater than 2, i represents the number of each target gray value interval, i = 1, 2,..., j, j is a positive integer greater than 2, n represents the number of the area composed of each pixel point, n = 1, 2,..., m, m is a positive integer greater than 2, and r represents the number of each outermost pixel point, r = 1, 2,..., s, s is a positive integer greater than 2.

[0043] According to the gray values of each pixel point of the target image of each page of the paper ancient book, extract the gray values of each comparison pixel point of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval, and calculate the comparison pixel point anomaly coefficient φ of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval. xinr .

[0044] It should be noted that each comparison pixel point of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval is the pixel point adjacent to each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval on this page.

[0045] According to the gray value a of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval xinr , the gray value b of the adjacent pixel point xinr and the gray value c of the back pixel point xinr , calculate the gray anomaly coefficient of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval.

[0046]

[0047] In a specific embodiment of the present invention, the calculation of the relevant pixel point gray hazard coefficient and the back pixel point gray hazard coefficient of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval, the specific calculation method is: according to the gray value d of each pixel point adjacent to the adjacent pixel point of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval xinrp , where p represents the number of each pixel point adjacent to the adjacent pixel point, p = 1, 2,..., q, q is a positive integer greater than 2, calculate the adjacent pixel point gray hazard coefficient of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target gray value interval. where e represents the natural constant and q is the number of pixel points adjacent to the adjacent pixel point.

[0048] Similarly, calculate the gray - scale hazard coefficient of the back - side pixels of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval.

[0049] In a specific embodiment of the present invention, when calculating the abnormal coefficient of comparison pixels of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval, the specific calculation method is as follows: Based on the gray - scale value f of each comparison pixel of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval xinrt , where t represents the number of each comparison pixel, t = 1, 2,..., w, and w is a positive integer greater than 2, calculate the abnormal coefficient of comparison pixels of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval where w is the number of comparison pixels.

[0050] In a specific embodiment of the present invention, when calculating the gray - scale target value of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval, the specific calculation method is as follows: Obtain the gray - scale decrease value corresponding to each gray - scale abnormal coefficient interval from the local database, map to obtain the gray - scale decrease value of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval, and subtract the gray - scale decrease value from the gray - scale value of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval, so as to calculate the gray - scale target value of the outermost pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval.

[0051] It should be noted that the larger the gray - scale abnormal coefficient, the larger the corresponding gray - scale decrease value, and it is set by the staff.

[0052] Step 2. Analysis of the penetration characteristics of the ancient book: By dividing the pixel - point intervals of each page of the paper ancient book, the pixels of the region composed of each pixel point of the target image of each page of the paper ancient book in each target gray - scale value interval are obtained. According to the influence of the relevant points of the adjacent page and the back page on the ink of this page, the gray - scale values of each pixel are intelligently adjusted, and the abnormal pixels are removed from the region composed of each pixel point, so as to ensure the restoration of the ink of the ancient book and improve the accuracy of image restoration.

[0053] Step 3. Ancient - book restoration processing: Send the image of each page of the paper ancient book after penetration and fading processing to the management person in charge.

[0054] Step 3. Ancient book restoration processing of the present invention ensures the digital preservation of ancient books by sending the restored images to the person in charge.

[0055] The second aspect of the present invention provides a terminal device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of an ancient book calculation image restoration method as described above.

[0056] The third aspect of the present invention provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of an ancient book calculation image restoration method as described in any one of the above are implemented.

[0057] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements or use similar methods to replace the specific embodiments described, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A method for ancient book computational image restoration, characterized in that: include: Step 1. Analysis of damaged areas of ancient books: obtaining images of each page of the ancient paper book against a target color background and against various color backgrounds, and analyzing damaged areas of each page of the ancient paper book; Step 2. Analysis of penetration characteristics of ancient books: Analyze the images of each page of the ancient book after penetration and dilution treatment; Step 3. Ancient book restoration: Send the images of each page of the paper ancient book after penetration and dilution treatment to the person in charge of management.

2. The ancient book computer image restoration method according to claim 1, characterized in that: The specific analysis method of analyzing the damaged areas of each page of the ancient paper book is as follows: According to the images of each page of the paper ancient book under the background of each color, the grayscale value of each pixel point of the image of each page of the paper ancient book under the background of each color is extracted through grayscale transformation; Obtain the target color background and the grayscale values ​​of each color background from the local database. If the grayscale values ​​of a certain pixel point of the image of a certain page of the ancient paper book under each color background are the same as the grayscale values ​​of each color background, then mark the pixel point of the image of the page of the ancient paper book under the target color background as a damaged pixel point, thereby screening the damaged pixel points of the image of each page of the ancient paper book under the target color background; If a damaged pixel of an image of a page of an ancient paper book under the target color background is adjacent to another damaged pixel, the damaged pixel and the other damaged pixel are merged into one area to be analyzed, and if there is another damaged pixel adjacent to the area to be analyzed, the other damaged pixel is merged into the area to be analyzed, thereby obtaining the areas to be analyzed and the number of damaged pixels of each page of the ancient paper book; The threshold value of the number of damaged pixels is obtained from the local database. If the number of damaged pixels in a certain area to be analyzed on a page of an ancient paper book is greater than the threshold value of the number of damaged pixels, the area to be analyzed is marked as a damaged area, thereby screening the damaged areas of each page of the ancient paper book.

3. The ancient book computer image restoration method according to claim 2, characterized in that: The specific analysis method of analyzing the images of each page of the ancient book after the penetration and dilution treatment is as follows: The image of each page of the ancient paper book under the target color background after removing the damaged areas is marked as the target image, so as to obtain the target image of each page of the ancient paper book, and through grayscale transformation, the grayscale value of each pixel point of the target image of each page of the ancient paper book is obtained, and the grayscale value of each pixel point of the target image of the adjacent page of each page of the ancient paper book and the grayscale value of each pixel point of the target image of the back page are extracted; Obtain each target grayscale value interval from the local database, analyze and obtain the pixel point composition area and each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval, and accordingly analyze the grayscale target value of each pixel point of the pixel point composition area of ​​the target image of each page of the paper ancient book in each target grayscale value interval; If the grayscale target value of a certain pixel point in a certain pixel point composition area of ​​a target image of a certain page of an ancient paper book is not included in the target grayscale value interval, the pixel point is marked as an abnormal pixel point, otherwise, the pixel point is marked as a normal pixel point, thereby screening out the abnormal pixels and normal pixels in the pixel point composition area of ​​each target grayscale value interval of each page of the ancient paper book; Obtain the page background grayscale value from the local database, and use it as the grayscale value of each abnormal pixel point in the target image of each page of the paper ancient book in each target grayscale value interval. Remove each pixel point in each target grayscale value interval from the target image of each page of the paper ancient book, and mark the remaining pixel points as each background pixel point of each page of the paper ancient book, and use the page background grayscale value as the grayscale value of each background pixel point of each page of the paper ancient book; The grayscale target values ​​of each normal pixel point in each pixel point composition area of ​​each target grayscale value interval of the target image of each page of the paper ancient book are used as the grayscale value of the corresponding pixel point of the image after the penetration and fading process; In summary, the images of each page of the ancient paper book after penetration and fading treatment are obtained.

4. The ancient book computer image restoration method according to claim 3, characterized in that: The specific analysis method of analyzing the grayscale target values ​​of each pixel point in the area composed of each pixel point in each target grayscale value interval of the target image of each page of the paper ancient book is as follows: Obtain the adjacent pixel points and back pixel points of each pixel point of each page of the paper ancient book from the local database; According to the grayscale value of each pixel of the target image of each page of the paper ancient book, the grayscale value of each pixel of the target image of each page of the paper ancient book in each target grayscale value interval constitutes an area composed of each pixel, the grayscale value of adjacent pixels and the grayscale value of the back pixel, and then the grayscale value of each outermost pixel of the target image of each page of the paper ancient book in each target grayscale value interval constitutes an area composed of each pixel, the grayscale value of adjacent pixels and the grayscale value of the back pixel; Calculate the grayscale anomaly coefficient of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval; Calculate the grayscale target values ​​of each outermost pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval, and calculate the grayscale anomaly coefficient of each second layer pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval based on this, and so on, until the grayscale target value of each pixel point of the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval is calculated.

5. The ancient book computer image restoration method according to claim 4, characterized in that: The specific analysis method for calculating the grayscale abnormality coefficient of each outermost pixel point in the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval is as follows: According to the grayscale value of each pixel of the target image of each page of the ancient paper book, the grayscale values ​​of each outermost pixel of the target image of each page of the ancient paper book in each target grayscale value interval and each pixel adjacent to the adjacent pixel are extracted, and the grayscale hazard coefficient β of the related pixel of each outermost pixel of the target image of each page of the ancient paper book in each target grayscale value interval is calculated. xinr and the grayscale hazard coefficient of the back pixel ε xinr , where x represents the number of each page, x=1,2,...,y, y is a positive integer greater than 2, i represents the number of each target gray value interval, i=1,2,...,j, j is a positive integer greater than 2, n represents the number of each pixel region, n=1,2,...,m, m is a positive integer greater than 2, r represents the number of each outermost pixel, r=1,2,...,s, s is a positive integer greater than 2; According to the grayscale value of each pixel of the target image of each page of the ancient paper book, the grayscale value of each comparison pixel of each outermost pixel of the target image of each page of the ancient paper book in each target grayscale value interval is extracted, and the comparison pixel abnormality coefficient φ of each outermost pixel of the target image of each page of the ancient paper book in each target grayscale value interval is calculated. xinr ; According to the gray value a of each outermost pixel point of the target image of each page of the ancient book in each target gray value interval, xinr , gray value b of adjacent pixels xinr and the gray value c of the back pixel xinr , calculate the grayscale anomaly coefficient of each outermost pixel point in the target image of each page of the ancient book in each target grayscale value interval 6. The ancient book computer image restoration method according to claim 5, characterized in that: The specific calculation method of calculating the relevant pixel grayscale hazard coefficients of each outermost pixel of each pixel point composition area of ​​each target image of each page of the paper ancient book in each target grayscale value interval and the back pixel grayscale hazard coefficient is: According to the gray value d of each pixel point adjacent to each pixel point in the outermost layer of the target image of each page of the ancient book in each target gray value interval, xinrp , where p represents the number of each pixel point adjacent to the adjacent pixel point, p = 1, 2, ..., q, q is a positive integer greater than 2, and the grayscale hazard coefficient of the adjacent pixel points of each outermost pixel point in the target image of each page of the ancient paper book in each target grayscale value interval is calculated Where e is represented as a natural constant, and q is the number of pixels adjacent to adjacent pixels; Similarly, the grayscale hazard coefficient of the back side pixels of each outermost pixel in the pixel composition area of ​​each pixel in each target grayscale value interval of each page of the target image of the ancient paper book is calculated.

7. The ancient book computer image restoration method according to claim 5, characterized in that: The specific calculation method of calculating the comparison pixel point abnormality coefficient of each outermost pixel point of each pixel point composition area of ​​each target gray value interval of the target image of each page of the paper ancient book is as follows: According to the gray value f of each comparison pixel point of each outermost pixel point of each pixel point composition area in each target gray value interval of each page of the target image of the ancient book, xinrt , where t represents the number of each comparison pixel point, t = 1, 2, ..., w, w is a positive integer greater than 2, and the comparison pixel point abnormality coefficient of each outermost pixel point of the target image of each page of the ancient paper book in each target gray value interval is calculated Where w is the number of compared pixels.

8. The ancient book computer image restoration method according to claim 4, characterized in that: The specific calculation method for calculating the grayscale target value of each outermost pixel point in the area composed of each pixel point of the target image of each page of the paper ancient book in each target grayscale value interval is: The grayscale decrease value corresponding to each grayscale anomaly coefficient interval is obtained from the local database, and the grayscale decrease value of each outermost pixel point of the target image of each page of the ancient book in each target grayscale value interval is mapped to obtain the grayscale decrease value of each outermost pixel point of the target image of each page of the ancient book in each target grayscale value interval. The grayscale value of each outermost pixel point of the target image of each page of the ancient book in each target grayscale value interval is subtracted from the grayscale decrease value, so as to calculate the grayscale target value of each outermost pixel point of the target image of each page of the ancient book in each target grayscale value interval.

9. A terminal device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a method for computer image restoration of ancient books as described in any one of claims 1-8.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for computer image restoration of ancient books described in any one of claims 1-8 are implemented.

Images