Ultra-depth-of-field microscopic scanning and ai image analysis method and system for ancient painting and calligraphy restoration

Abstract

The application provides an ultra-depth-of-field microscopic scanning and AI image analysis method and system for ancient book and painting restoration, relates to the field of image processing, and comprises the following steps: determining a scanning track and scanning parameters according to scanning related characteristic information of an ancient book and painting to be restored, the scanning track comprises a plurality of scanning track points, and the scanning parameters comprise a starting scanning height corresponding to each scanning track point; adjusting the spatial position of an ultra-depth-of-field three-dimensional microscope according to the scanning track and the starting scanning height corresponding to each scanning track point, acquiring a plurality of layers of images at each scanning track point through the ultra-depth-of-field three-dimensional microscope; stacking the plurality of layers of images of each scanning track point to generate a region image corresponding to each scanning track point, and splicing the region image corresponding to each scanning track point to generate a scanning image of the ancient book and painting to be restored; and determining damage characteristics of the ancient book and painting to be restored through a damage analysis model, so that the efficiency and quality of ancient book and painting restoration are improved.

Description

Technical Field

[0001] This invention relates to the field of image processing, and in particular to a method and system for ultra-depth-of-field microscopic scanning and AI image analysis for the restoration of ancient paintings and calligraphy. Background Technology

[0002] In the current process of restoring ancient paintings and calligraphy, microscopes are indispensable auxiliary tools. Traditional optical microscopes and super-depth-of-field microscopes are often used together to meet different observation needs. Optical microscopes are usually equipped with multiple objectives, with magnification ranging from 4x to 100x. When using them, it is necessary to first locate the target area and adjust the clarity using a low-power objective, and then gradually switch to a high-power objective for detailed observation. However, the field of view of a high-power objective is relatively small, making it difficult to directly locate the target area, and the working distance is short, which can easily damage the sample or the lens if not handled properly. In recent years, the application of super-depth-of-field microscopes in the restoration of ancient paintings and calligraphy has gradually increased. Compared with traditional microscopes, super-depth-of-field microscopes can achieve free zoom with a single objective, greatly simplifying the operation process. At the same time, super-depth-of-field microscopes, combined with CCD elements, provide digital image presentation, which not only has higher resolution but also reveals microscopic details more clearly. This is of great significance for analyzing microscopic damage in ancient paintings and calligraphy.

[0003] In existing technologies, ultra-depth-of-field microscopy requires extremely high flatness of the scanning surface. However, the microscopic unevenness of the surface of ancient paintings and calligraphy makes focusing during the scanning process exceptionally difficult, thus affecting scanning quality and efficiency. Furthermore, the fixed scanning platform dimensions of existing ultra-depth-of-field equipment are rigid and difficult to adapt to the large-format requirements of paintings and calligraphy. For example, the scanning stage of existing ultra-depth-of-field microscopes typically only supports samples up to A3 size (297mm × 420mm), while ancient paintings and calligraphy can easily reach several meters or even tens of meters in size. This means that a single scan can only cover a local area, requiring multiple stitching steps to achieve complete digitization. However, the stitching process easily introduces problems such as geometric distortion and color distortion. While handheld depth-of-field instruments are portable, their working mode is essentially "point sampling," allowing only magnified observation of local areas (e.g., a single scan range of approximately 10mm × 10mm), failing to achieve full-area depth-of-field information acquisition. This results in fragmented digitization results, making it difficult to meet the requirements of high-definition digitization of ancient paintings and calligraphy for global depth-of-field consistency and color continuity. Furthermore, a large-scale AI model image recognition system suitable for the characteristics of damage to ancient paintings and calligraphy has not yet been developed. Existing AI image recognition systems are mostly trained and recognized for general objects or scenes, lacking specialized training and recognition capabilities for damage to ancient paintings and calligraphy, thus failing to meet the practical needs of the field of ancient painting and calligraphy restoration.

[0004] Therefore, there is a need to provide ultra-depth-of-field microscopic scanning and AI image analysis methods and systems for the restoration of ancient paintings and calligraphy, in order to improve the efficiency and quality of the restoration. Summary of the Invention

[0005] This invention provides a super-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient calligraphy and paintings, comprising: an information acquisition module for acquiring scanning-related feature information of the ancient calligraphy and paintings to be restored; an automatic scanning module including a scanning device, a super-depth-of-field three-dimensional microscope, and a scanning control unit, wherein the super-depth-of-field three-dimensional microscope is mounted on the scanning device, and the scanning control unit is used to determine the scanning trajectory and scanning parameters based on the scanning-related feature information of the ancient calligraphy and paintings to be restored, wherein the scanning trajectory includes multiple scanning trajectory points, the scanning parameters include the starting scanning height corresponding to each scanning trajectory point, the scanning device is used to adjust the spatial position of the super-depth-of-field three-dimensional microscope according to the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point, and the super-depth-of-field three-dimensional microscope is used to acquire multi-layer images at each scanning trajectory point; an image processing module for stacking the multi-layer images of each scanning trajectory point to generate a region image corresponding to each scanning trajectory point, and stitching the region images corresponding to each scanning trajectory point to generate a scanned image of the ancient calligraphy and paintings to be restored; and a damage analysis module for determining the damage characteristics of the ancient calligraphy and paintings to be restored based on the scanned image of the ancient calligraphy and paintings to be restored using a damage analysis model.

[0006] Furthermore, the scanning device includes a frame, a vacuum suction cup honeycomb plate, a position adjustment component, and a laser ranging component. Both the vacuum suction cup honeycomb plate and the position adjustment component are mounted on the frame. The position adjustment component is positioned above the vacuum suction cup honeycomb plate. The ancient calligraphy or painting to be restored is placed on the vacuum suction cup honeycomb plate. The position adjustment component includes an X-axis coordinate adjustment device, a Y-axis coordinate adjustment device, and a Z-axis coordinate adjustment device. The Y-axis coordinate adjustment device is mounted on the X-axis coordinate adjustment device, and the Z-axis coordinate adjustment device is mounted on the Y-axis coordinate adjustment device. The ultra-depth-of-field 3D microscope is mounted on the Z-axis coordinate adjustment device. The laser ranging component is mounted on the Z-axis coordinate adjustment device and includes a laser ranging array composed of multiple laser ranging devices.

[0007] Furthermore, the scanning device is also used to adjust the position of the laser ranging component in the XY plane according to the preset ranging trajectory, wherein the XY plane is parallel to the vacuum suction cup honeycomb plate, the preset ranging trajectory includes multiple ranging trajectory points, the laser ranging component is used to acquire regional ranging information at each ranging trajectory point, and the scanning-related feature information of the ancient calligraphy and painting to be restored includes at least the regional ranging information corresponding to each ranging trajectory point; the scanning control unit determines the scanning trajectory according to the scanning-related feature information of the ancient calligraphy and painting to be restored, including: determining the scanning trajectory according to the regional ranging information corresponding to each ranging trajectory point.

[0008] Furthermore, the scanning control unit determines the scanning trajectory based on the regional ranging information corresponding to each ranging trajectory point, including: generating the concavity and convexity heights of multiple locations on the ancient calligraphy and painting to be restored based on the regional ranging information corresponding to each ranging trajectory point; establishing a trajectory generation constraint set, wherein the trajectory generation constraint set includes at least the shortest distance and the longest distance between two adjacent scanning trajectory points; establishing a multi-objective reward function, wherein the multi-objective reward function is related to the difference in concavity and convexity heights between two adjacent scanning trajectory points, the concavity and convexity heights of each scanning trajectory point, and the distance between two adjacent scanning trajectory points; and generating the scanning trajectory through the trajectory generation model based on the concavity and convexity heights of multiple locations on the ancient calligraphy and painting to be restored, the trajectory generation constraint set, and the multi-objective reward function.

[0009] Furthermore, the scanning control unit generates scanning trajectories using a trajectory generation model based on the concavity and convexity heights of multiple locations on the ancient calligraphy and painting to be restored, a trajectory generation constraint set, and a multi-objective reward function. This includes: for each location, determining the difference in concavity and convexity height based on the concavity and convexity heights of adjacent locations; normalizing the difference in concavity and convexity heights of each location to generate a normalized difference in concavity and convexity heights for each location; determining multiple trajectory generation starting positions from multiple locations based on the normalized difference in concavity and convexity heights of each location; for each trajectory generation starting position, generating a scanning trajectory corresponding to the starting position using the trajectory generation model based on the concavity and convexity heights of multiple locations on the ancient calligraphy and painting to be restored, a trajectory generation constraint set, and a multi-objective reward function; establishing a fitness function, wherein the fitness function is related to the difference in concavity and convexity heights between two adjacent scanning trajectory points and the overlapping area of ​​any two scanning trajectory points; determining the fitness value of the scanning trajectory corresponding to each trajectory generation starting position; and generating scanning trajectories using a genetic algorithm based on the fitness value of the scanning trajectory corresponding to each trajectory generation starting position.

[0010] Furthermore, the scanning control unit determines the starting scanning height corresponding to the scanning trajectory point based on the scanning-related feature information of the ancient calligraphy and painting to be restored, including: interpolating the concave and convex heights of multiple positions of the ancient calligraphy and painting to be restored to generate the concave and convex heights corresponding to the scanning trajectory point; calculating the height difference between the concave and convex heights corresponding to the scanning trajectory point and the reference height; and determining the starting scanning height corresponding to the scanning trajectory point based on the height difference between the concave and convex heights corresponding to the scanning trajectory point and the reference height.

[0011] Furthermore, the scanning-related feature information of the ancient calligraphy and painting to be restored also includes material information, pigment type information, and color distribution characteristics; the scanning device also includes a supplementary lighting device; the scanning control unit determines the scanning parameters based on the scanning-related feature information of the ancient calligraphy and painting to be restored, including: determining supplementary lighting parameters based on material information, pigment type information, and color distribution characteristics, wherein the scanning parameters include supplementary lighting parameters, and the supplementary lighting parameters include color temperature and light intensity.

[0012] Furthermore, the scanning control unit determines the supplementary lighting parameters based on material information, pigment type information, and color distribution characteristics, including: acquiring the material information, pigment type information, color distribution characteristics, and optimal supplementary lighting parameters of multiple sample ancient paintings and calligraphy works; dividing the multiple sample ancient paintings and calligraphy works into multiple sample groups based on their material information, pigment type information, and color distribution characteristics through hierarchical clustering; determining the sample group to which the ancient painting and calligraphy work to be restored belongs based on its material information, pigment type information, and color distribution characteristics; determining similar sample ancient paintings and calligraphy works based on their material information, pigment type information, and color distribution characteristics, as well as the material information, pigment type information, and color distribution characteristics of the sample ancient paintings and calligraphy works included in the sample group to which the ancient painting and calligraphy work to be restored belongs; and determining the supplementary lighting parameters based on the optimal supplementary lighting parameters of the similar sample ancient paintings and calligraphy works to be restored.

[0013] Furthermore, the damage analysis model includes a defect analysis unit, a fracture analysis unit, a discoloration analysis unit, and a pest analysis unit. The defect analysis unit is used to generate a defect distribution map based on the scanned image of the ancient calligraphy and painting to be restored. The fracture analysis unit is used to generate a fracture distribution map based on the scanned image of the ancient calligraphy and painting to be restored. The discoloration analysis unit is used to generate a discoloration distribution map based on the scanned image of the ancient calligraphy and painting to be restored. The pest analysis unit is used to generate a pest distribution map based on the scanned image of the ancient calligraphy and painting to be restored.

[0014] This invention provides a super-depth-of-field microscopic scanning and AI image analysis method for the restoration of ancient calligraphy and paintings, applied to the aforementioned super-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient calligraphy and paintings. The method includes: acquiring scanning-related feature information of the ancient calligraphy and painting to be restored; determining the scanning trajectory and scanning parameters based on the scanning-related feature information, wherein the scanning trajectory includes multiple scanning trajectory points, and the scanning parameters include the starting scanning height corresponding to each scanning trajectory point; adjusting the spatial position of the super-depth-of-field three-dimensional microscope according to the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point, and acquiring multi-layer images at each scanning trajectory point using the super-depth-of-field three-dimensional microscope; stacking the multi-layer images of each scanning trajectory point to generate a region image corresponding to each scanning trajectory point, and stitching the region images corresponding to each scanning trajectory point to generate a scanned image of the ancient calligraphy and painting to be restored; and determining the damage characteristics of the ancient calligraphy and painting to be restored based on the scanned image using a damage analysis model.

[0015] Compared with existing technologies, the ultra-depth-of-field microscopic scanning and AI image analysis method and system for the restoration of ancient paintings and calligraphy provided by this invention have at least the following beneficial effects:

[0016] Obtaining scan-related feature information of ancient paintings and calligraphy to be restored covers key elements such as materials, pigments, and color distribution. This provides comprehensive and accurate basic data for subsequent scanning, image processing, and damage analysis, helping to grasp the characteristics of ancient paintings and calligraphy as a whole and formulate restoration strategies that are more in line with the actual situation.

[0017] Based on the acquired feature information, the scanning trajectory and scanning parameters are intelligently determined. A trajectory containing multiple scanning points is planned according to the characteristics of different ancient paintings and calligraphy, and an appropriate starting scanning height is set for each trajectory point. This makes the scanning process more targeted and precise, avoiding the blindness and unevenness that may exist in traditional scanning methods, and greatly improving scanning quality.

[0018] Based on the determined scanning trajectory and initial scanning height, the spatial position of the ultra-depth-of-field 3D microscope is precisely adjusted, realizing automated and intelligent scanning operations, reducing manual intervention, improving scanning efficiency, and ensuring the stability and repeatability of the scanning process.

[0019] The ultra-depth-of-field 3D microscope acquires multiple layers of images at each scanning trajectory point. This multi-layered image acquisition method can obtain detailed information at different depths on the surface of ancient paintings and calligraphy, providing a rich data source for subsequent image stacking processing and helping to more comprehensively reveal the original appearance of the ancient paintings and calligraphy. The multiple layers of images at each scanning trajectory point are stacked, and a specific algorithm fuses the multi-layered image information into a high-quality regional image, effectively reducing image noise, highlighting detailed information, and making the image clearer and more accurate. The regional images of each trajectory point are then stitched together to generate a complete scanned image of the ancient painting and calligraphy to be restored.

[0020] By analyzing scanned images using damage analysis models, the damage characteristics of ancient paintings and calligraphy to be restored can be accurately determined, such as the type of damage (e.g., breakage, fading, insect infestation), location, and extent of damage. This scientifically model-based analysis method avoids the subjectivity and errors that may exist in human judgment, providing restorers with objective and accurate damage information. Accurate damage characteristic information provides restorers with a strong basis for developing restoration plans, enabling them to select appropriate restoration materials and techniques based on different damage conditions, improving the accuracy and success rate of restoration, and maximizing the restoration of the original appearance and artistic value of the ancient paintings and calligraphy. Attached Figure Description

[0021] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0022] Figure 1 This is a schematic diagram of a super depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy, as shown in some embodiments of this specification.

[0023] Figure 2 These are schematic diagrams of the scanning apparatus shown in some embodiments of this specification;

[0024] Figure 3 This is a schematic flowchart illustrating the generation of scan trajectories according to some embodiments of this specification;

[0025] Figure 4 This is a structural schematic diagram of the damage analysis model shown in some embodiments of this specification;

[0026] Figure 5 This is a schematic diagram of the user interface of the scanning control unit according to some embodiments of this specification;

[0027] Figure 6 This is a schematic diagram of another user interface of the scanning control unit according to some embodiments of this specification;

[0028] Figure 7 These are schematic diagrams illustrating the damage characteristics of ancient paintings and calligraphy to be restored, based on some embodiments of this specification.

[0029] Figure 8-10 This is a schematic diagram of a region image shown according to some embodiments of this specification;

[0030] Figure 11 This is a flowchart illustrating a super-depth-of-field microscopic scanning and AI image analysis method for the restoration of ancient paintings and calligraphy, as shown in some embodiments of this specification.

[0031] In the diagram, 1 is the frame; 2 is the vacuum suction cup honeycomb panel; 3 is the X-axis coordinate adjustment device; 4 is the Y-axis coordinate adjustment device; 5 is the Z-axis coordinate adjustment device; and 6 is the ultra-depth-of-field 3D microscope. Detailed Implementation

[0032] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0033] Figure 1 These are schematic diagrams of modules of a super-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy, as shown in some embodiments of this specification. Figure 1 As shown, the ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy can include an information acquisition module, an automatic scanning module, an image processing module, and a damage analysis module.

[0034] The information acquisition module is used to acquire scan-related feature information of the ancient paintings and calligraphy to be restored.

[0035] Specifically, the scan-related feature information of the ancient paintings and calligraphy to be restored can include the regional ranging information corresponding to each ranging trajectory point.

[0036] The scanned information of ancient paintings and calligraphy to be restored can also include material information, pigment type information, and color distribution characteristics.

[0037] Material information refers to the type of material used to construct ancient paintings and calligraphy, such as paper (Xuan paper, bark paper, hemp paper, etc.) or silk (raw silk, sized silk, etc.). Different materials differ in their physical and chemical properties. Infrared spectroscopy, Raman spectroscopy, and other techniques can be used to analyze the chemical composition of the materials and determine the material information of the ancient paintings and calligraphy to be restored.

[0038] Pigment type information refers to the mineral pigments (such as cinnabar, azurite, malachite, etc.), plant pigments (such as phthalocyanine, gamboge, etc.), or chemically synthesized pigments used in ancient paintings and calligraphy. The chemical composition of the pigments is analyzed using techniques such as X-ray fluorescence spectroscopy and laser-induced breakdown spectroscopy to determine the pigment type information.

[0039] Color distribution characteristics refer to the spatial distribution patterns of colors in ancient paintings and calligraphy, including the types, concentrations, and distribution areas of colors. This involves statistically analyzing the pixel distribution of each color channel in the image to quantify the color distribution characteristics.

[0040] The automatic scanning module includes a scanning device, a super depth-of-field 3D microscope 6, and a scanning control unit, with the super depth-of-field 3D microscope 6 mounted on the scanning device.

[0041] Figure 2 These are schematic diagrams of the scanning device shown in some embodiments of this specification, such as... Figure 2 As shown, the scanning device includes a frame 1, a vacuum suction cup honeycomb plate 2, a position adjustment component, and a laser ranging component. Both the vacuum suction cup honeycomb plate 2 and the position adjustment component are mounted on the frame 1, with the position adjustment component positioned above the vacuum suction cup honeycomb plate 2. The ancient calligraphy or painting to be restored is placed on the vacuum suction cup honeycomb plate 2. The position adjustment component includes an X-axis coordinate adjustment device 3, a Y-axis coordinate adjustment device 4, and a Z-axis coordinate adjustment device 5. The Y-axis coordinate adjustment device 4 is mounted on the X-axis coordinate adjustment device 3, and the Z-axis coordinate adjustment device 5 is mounted on the Y-axis coordinate adjustment device 4. A super-depth-of-field 3D microscope 6 is mounted on the Z-axis coordinate adjustment device 5. The laser ranging component is mounted on the Z-axis coordinate adjustment device 5 and includes a laser ranging dot array composed of multiple laser ranging devices.

[0042] Specifically, the vacuum suction cup honeycomb panel 2 is made by firmly bonding two thin panels to both sides of a thicker honeycomb core material, forming a honeycomb sandwich structure. This honeycomb sandwich structure serves as the main structure of the vacuum suction cup. The honeycomb sandwich structure contains air channels or cavities, which connect to equipment such as a vacuum pump to achieve vacuum adsorption. Operators can place the ancient calligraphy or painting to be restored on the vacuum suction cup honeycomb panel 2, which will adsorb and fix the artwork, preventing movement during subsequent scanning.

[0043] The main function of the X-axis coordinate adjustment device 3 is to control the movement of the ultra-depth-of-field 3D microscope 6 in the horizontal direction (i.e., the X-axis direction). By adjusting the position of the microscope on the X-axis, scanning of different horizontal areas of ancient paintings and calligraphy can be achieved. The X-axis coordinate adjustment device 3 can be composed of components such as a motor, guide rail, and lead screw. The motor provides power to drive the lead screw to rotate, which in turn drives the moving parts (such as sliders or platforms) mounted on the guide rail to move along the X-axis direction. The guide rail provides support and guidance, ensuring the smooth operation of the moving parts.

[0044] Y-axis coordinate adjustment device 4 controls the movement of the ultra-depth-of-field 3D microscope 6 in another horizontal direction (i.e., the Y-axis direction). It works in conjunction with X-axis coordinate adjustment device 3, enabling the microscope to move freely on the two-dimensional plane of the ancient painting or calligraphy, achieving full-coverage scanning of the entire image. The structure of Y-axis coordinate adjustment device 4 is similar to that of X-axis coordinate adjustment device 3, also consisting of components such as a motor, guide rail, and lead screw. The difference is that it is mounted on the moving part of X-axis coordinate adjustment device 3. Thus, when X-axis coordinate adjustment device 3 moves, Y-axis coordinate adjustment device 4 and the microscope on it also move in the X-axis direction; while when the motor of Y-axis coordinate adjustment device 4 is working, it can drive the microscope to move independently in the Y-axis direction.

[0045] The main function of the Z-axis coordinate adjustment device 5 is to control the movement of the ultra-depth-of-field 3D microscope 6 in the vertical direction (i.e., the Z-axis direction). By adjusting the position of the ultra-depth-of-field 3D microscope 6 on the Z-axis, the distance between the ultra-depth-of-field 3D microscope 6 and the surface of the ancient painting / calligraphy can be adjusted to obtain the best scanning effect. The Z-axis coordinate adjustment device 5 may include an electric push rod and is also equipped with a high-precision position sensor (such as a grating ruler, encoder, etc.) to achieve precise control of the position of the ultra-depth-of-field 3D microscope 6 in the Z-axis direction. The electric push rod drives the ultra-depth-of-field 3D microscope 6 to move along the Z-axis direction, and the position sensor provides real-time feedback on the actual position information of the ultra-depth-of-field 3D microscope 6. The scanning control unit adjusts the extension length of the electric push rod according to the feedback information to ensure that the ultra-depth-of-field 3D microscope 6 can accurately reach the target position.

[0046] In some embodiments, the scanning device can also be used to adjust the position of the laser ranging component in the XY plane according to a preset ranging trajectory, wherein the XY plane is parallel to the vacuum suction cup honeycomb plate 2, the preset ranging trajectory includes multiple ranging trajectory points, the laser ranging component is used to acquire regional ranging information at each ranging trajectory point, and the scanning-related feature information of the ancient calligraphy and painting to be restored includes at least the regional ranging information corresponding to each ranging trajectory point, wherein the regional ranging information may include the distance measured to the surface of the ancient calligraphy and painting to be restored by each laser ranging device in the laser ranging point array when the laser ranging component is located at the ranging trajectory point.

[0047] Specifically, the preset ranging trajectory is a set of pre-planned path points in the XY plane. These points, called ranging trajectory points, guide the laser ranging component to move orderly within a specific area, ensuring comprehensive and systematic acquisition of ranging information from different locations on the ancient painting or calligraphy to be restored. A ranging trajectory covering the entire surface of the painting or calligraphy can be planned based on its length, width, and other dimensional parameters, as well as its approximate shape (e.g., rectangle, circle). For example, for a rectangular painting or calligraphy, a serpentine or grid-like trajectory can be planned from left to right and from top to bottom. Assuming a rectangular painting or calligraphy 100cm long and 80cm wide, the preset ranging trajectory can be set to place a ranging trajectory point every 10cm, forming a 10×8 grid, for a total of 80 ranging trajectory points.

[0048] The scanning control unit is used to determine the scanning trajectory and scanning parameters based on the scanning-related feature information of the ancient painting and calligraphy to be restored. The scanning trajectory includes multiple scanning trajectory points, and the scanning parameters include the starting scanning height corresponding to each scanning trajectory point. The scanning device is used to adjust the spatial position of the ultra-depth-of-field three-dimensional microscope according to the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point. The ultra-depth-of-field three-dimensional microscope is used to acquire multi-layer images at each scanning trajectory point.

[0049] In some embodiments, the scanning control unit can determine the scanning trajectory based on the area ranging information corresponding to each ranging trajectory point, specifically including:

[0050] Based on the regional ranging information corresponding to each ranging trajectory point, the concavity and convexity heights of multiple locations of the ancient calligraphy and painting to be restored are generated.

[0051] Establish a set of trajectory generation constraints, which includes at least the shortest distance and the longest distance between two adjacent scan trajectory points;

[0052] A multi-objective reward function is established, which is related to the difference in concavity and convexity height between two adjacent scan trajectory points, the concavity and convexity height of each scan trajectory point, and the distance between two adjacent scan trajectory points.

[0053] The trajectory generation model generates a scanning trajectory based on the concavity and convexity of multiple locations of the ancient painting and calligraphy to be restored, the trajectory generation constraint set, and the multi-objective reward function.

[0054] Specifically, check whether the regional ranging information corresponding to each ranging trajectory point is complete, that is, whether the data measured by each laser ranging device in the laser ranging point array exists. If there is missing data, it can be supplemented by interpolation based on the data of adjacent ranging points. For example, a linear interpolation method can be used, assuming that the distance and height changes between adjacent ranging points are linear, and the missing value can be estimated by calculating the slope of adjacent valid data points. Laser ranging may be affected by environmental interference, equipment errors, and other factors, resulting in noise in the measurement data. Filtering algorithms, such as median filtering, can be used to process the regional ranging information of each ranging trajectory point. Median filtering replaces the measurement value of each ranging point with the median of all measurements in its neighborhood, which can effectively remove impulse noise and make the data smoother.

[0055] The distance measurement information corresponding to each distance measurement trajectory point is stitched together to generate the overall distance measurement information.

[0056] To generate data on the surface elevation of ancient calligraphy and paintings, a reference plane needs to be determined. The least squares method can be used to fit the three-dimensional coordinates of all measurement points to obtain the best-fitting plane as the reference plane. The goal of the least squares method is to minimize the sum of the squares of the distances from all measurement points to this plane, thus obtaining a plane that best represents the overall height trend of the ancient calligraphy and paintings.

[0057] Multiple sampling points are selected. For each point, the vertical distance to the reference plane is calculated; this distance represents the height of the sampling point relative to the reference plane. If the point is above the reference plane, the height is positive, indicating a convex position; if the point is below the reference plane, the height is negative, indicating a concave position. The surface of the ancient painting or calligraphy to be restored can be divided into several regular regions, such as a grid. A sampling point is then taken at the center of each region. It is crucial to ensure that the sampling points are evenly distributed across the entire surface to avoid over- or under-sampling in any local area. For example, for an ancient painting or calligraphy measuring 100cm long and 80cm wide, it can be divided into a 10x8 grid, with each grid cell measuring 10cm x 10cm. Sampling points are then placed at the intersections of each grid cell, resulting in a total of 80 sampling points.

[0058] The trajectory generation constraint set is a collection of various limiting factors in the process of generating the scanning trajectory. It ensures that the generated scanning trajectory not only conforms to the actual operating capabilities of the scanning device, but also meets the needs of effectively scanning ancient paintings and calligraphy to be restored.

[0059] The shortest distance between two adjacent scanning trajectory points refers to the minimum permissible distance between the projection points of any two adjacent scanning trajectory points on the surface of the ancient painting or calligraphy during the scanning process. If adjacent scanning trajectory points are too close, the scanning device may frequently start and stop or adjust its posture during movement, thus affecting the stability and accuracy of the scan. Setting a minimum distance ensures that the scanning device has sufficient space for smooth operation during movement, reducing scanning deviations caused by mechanical motion errors. Furthermore, overly dense scanning trajectories increase scanning time and data processing volume, reducing scanning efficiency. By specifying a minimum distance, unnecessary repeated scanning can be avoided, improving scanning efficiency.

[0060] The longest distance between two adjacent scan trajectory points refers to the maximum allowable distance between the projection points of any two adjacent scan trajectory points on the surface of the ancient painting or calligraphy during the scanning process. If the distance between adjacent scan trajectory points is too far, it may cause omissions in the scanning area, making it impossible to fully obtain information about the surface of the ancient painting or calligraphy. Setting a maximum distance ensures that the scan trajectory can cover the entire surface of the ancient painting or calligraphy, avoiding scanning blind spots.

[0061] In addition to the shortest and longest distances between two adjacent scan trajectory points, the trajectory generation constraint set can also include other constraints, such as:

[0062] Distance between the scanning trajectory and the edge of the ancient calligraphy and painting: In order to avoid the scanning device from colliding with the edge of the ancient calligraphy and painting during the movement, it is necessary to specify the minimum safe distance between the scanning trajectory and the edge of the ancient calligraphy and painting.

[0063] Curvature limitation of scanning trajectory: In order to ensure that the scanning device can move smoothly along the scanning trajectory, the curvature of the scanning trajectory needs to be limited to avoid excessive bending.

[0064] If the height difference between adjacent trajectory points is too large, the scanning device needs to frequently adjust its height during movement. This not only increases the difficulty and error of scanning but may also damage the scanning device. A smaller height difference between adjacent trajectory points allows for a smoother scanning process, improving scanning accuracy and stability.

[0065] Super depth-of-field microscopy demands extremely high surface flatness. The microscopic unevenness of ancient paintings and calligraphy surfaces makes focusing during the scanning process exceptionally difficult, thus affecting scanning quality and efficiency. In areas with minimal variation in unevenness, the scanning device can maintain focus relatively easily, resulting in clear images. However, in areas with significant variations in unevenness, if the scanning trajectory is not rationally planned according to the unevenness, localized blurring or distortion may occur in the image. By incorporating the unevenness of the scanning trajectory points into a multi-objective reward function, the trajectory generation model can be guided to generate a more reasonable scanning trajectory, enabling the scanning device to better adapt to surface undulations during scanning and improving the overall image clarity.

[0066] The distance between two adjacent scan trajectory points affects scanning efficiency and quality. A shorter distance between two adjacent scan trajectory points increases scanning time and data processing volume, while a reasonable distance between two adjacent scan trajectory points ensures full coverage and high efficiency of the scanning area.

[0067] As an example only, a multi-objective reward function can be:

[0068]

[0069] Among them, R(S) t ,a t ,S t+1 (This is a multi-objective reward, current state S) t Includes the concavity / convexity height information H of the current scan trajectory point t Action a t The action of selecting the next scan trajectory point causes the state to transition to S. t+1 Its concave-convex height is H t+1 H max △L represents the maximum concave / convex height of the ancient painting or calligraphy to be restored. (t,t+1) △L represents the distance between the current scan trajectory point and the next scan trajectory point. max The maximum distance between two adjacent scanning trajectory points is preset, and a1, a2 and a3 are weights. a1, a2 and a3 are greater than 0, and a1+a2+a3=1.

[0070] Understandably, the aforementioned multi-objective reward function assigns lower rewards to cases with large height differences. Because excessively large height differences between adjacent scanning trajectory points require frequent height adjustments during the scanning process, increasing scanning difficulty, errors, and potentially damaging the device. Therefore, it is desirable to minimize the height differences between adjacent scanning trajectory points to ensure a smoother scanning process and improve accuracy and stability. When selecting the next scanning trajectory point, the guided trajectory generation model tends to choose points with similar height differences to the current trajectory point, thereby reducing the frequency of height adjustments during the scanning process.

[0071] The greater the height of the convexity of the next scanning trajectory point, the greater the reward. When selecting the next scanning trajectory point, the guiding trajectory generation model tends to choose the trajectory point with a larger height of convexity, so that the scanning device can better adapt to surface undulations during the scanning process and avoid local blurring or distortion of the scanned image.

[0072] A short distance between two adjacent scan trajectory points increases scanning time and data processing volume, while a reasonable distance ensures full coverage and efficiency of the scanning area. Therefore, it is desirable for the distance between adjacent trajectory points to be neither too large nor too small, but close to the preset maximum distance, to guarantee scanning efficiency and quality. This can be achieved by setting a3×(△L)... (t,t+1) -△L max ) 2 The guide trajectory generation model selects an appropriate distance between adjacent trajectory points, so that the scanning trajectory covers the entire scanning area while avoiding an increase in scanning time and data processing volume due to excessively short distances, thereby improving scanning efficiency.

[0073] Figure 3 This is a schematic flowchart illustrating the generation of scan trajectories according to some embodiments of this specification, such as... Figure 3 As shown, in some embodiments, the scanning control unit generates a scanning trajectory based on the concavity and convexity of multiple locations of the ancient painting or calligraphy to be restored, a trajectory generation constraint set, and a multi-objective reward function, using a trajectory generation model. This includes:

[0074] For each location, the difference in concavity / convexity height is determined based on the concavity / convexity height of adjacent locations;

[0075] Normalize the concavity / convexity height difference value at each location to generate a normalized concavity / convexity height difference value at each location.

[0076] Based on the normalized difference in concavity and convexity height at each location, multiple trajectory generation starting positions are determined from multiple locations;

[0077] For each trajectory generation starting position, the trajectory generation model generates the scanning trajectory corresponding to the trajectory generation starting position based on the concavity and convexity height of multiple positions of the ancient painting and calligraphy to be restored, the trajectory generation constraint set, and the multi-objective reward function.

[0078] Establish a fitness function, which is related to the difference in concavity and convexity height between two adjacent scan trajectory points and the overlapping area of ​​scans between any two scan trajectory points;

[0079] Determine the fitness value of the scan trajectory corresponding to the starting position of each trajectory generation;

[0080] The scanning trajectory is generated by using a genetic algorithm to generate the fitness value of the scanning trajectory corresponding to the starting position of each trajectory.

[0081] Specifically, adjacent positions can be locations whose distance to the current position is less than a preset distance threshold. For each position, the variance of the convexity / concave height of adjacent positions can be calculated as the convexity / concave height difference value for that position. The convexity / concave height difference values ​​of different positions may have different orders of magnitude, and directly using these difference values ​​for comparison and analysis may lead to inaccurate results. The purpose of normalization is to map the convexity / concave height difference values ​​of different positions to a uniform range (usually [0,1]), eliminating the influence of orders of magnitude and making subsequent processing (such as determining the starting position of trajectory generation) more reasonable and effective. Min-Max Normalization can be used to normalize the convexity / concave height difference value for each position.

[0082] The position where the normalized difference in convex and concave height is greater than the preset threshold for the difference in convex and concave height can be used as the starting position for trajectory generation.

[0083] Understandably, the difference in surface height reflects the complexity of the surface of the ancient painting or calligraphy to be restored at a certain location and in its adjacent areas. A larger difference value indicates more drastic surface variations, increasing the scanning difficulty and complexity. A preset threshold for surface height difference is a critical value used to identify complex surface areas. When the normalized surface height difference at a certain location exceeds this threshold, that location and its adjacent areas can be considered to have high surface complexity. Choosing a region with high surface complexity as the starting point for trajectory generation ensures that the scanning trajectory begins from the most challenging area, thus better addressing the microscopic unevenness of the surface. Choosing a location with a small surface height difference as the starting point may result in repeated scanning in relatively flat areas, increasing scanning time and data processing volume. By selecting a location with a large surface height difference as the starting point, the scanning trajectory can cover more complex areas, reducing redundant scanning and improving scanning efficiency. By determining multiple trajectory generation starting points, multiple distinct scanning trajectories can be generated, providing more effective information for subsequent trajectory generation.

[0084] As an example only, the fitness function can be:

[0085]

[0086] Where F(S) is the fitness value, H n H represents the convexity / concave height corresponding to the nth scan trajectory point. n+1 The height of the concavity / convexity corresponding to the (n+1)th scan trajectory point, where N is the total number of scan trajectory points, and △S ij Let b1, b2, and b3 be the area of ​​overlap between the scanning regions of the i-th and j-th scanning trajectory points, where b1, b2, and b3 are weights, b1, b2, and b3 are greater than 0, and b1 + b2 + b3 = 1.

[0087] Understandable. The average of the sum of squares of the height differences between adjacent trajectory points was calculated. The height difference reflects the degree of variation in the scanning trajectory along the height direction. A larger difference indicates a more drastic change in height, potentially increasing scanning difficulty and error. By averaging the sum of squares, the fitness value of scanning trajectories with greater height variations is lower. The average of the sum of the overlapping areas of the scan regions among all trajectory points was calculated. The overlap of scan regions reflects the redundancy of the scan trajectory. A larger overlapping area indicates more repeated scans during the scanning process, increasing scan time and data processing volume. By averaging the overlapping area, the fitness value of scan trajectories with larger overlapping areas is lower. The number of trajectory points was taken into account. With a fixed scanning area, a higher number of trajectory points may mean a denser scan trajectory, but it may also increase scanning time and data processing volume. By taking the reciprocal, the fitness value of a scan trajectory with a higher number of trajectory points is lower.

[0088] Genetic algorithms are optimization algorithms that simulate natural selection and genetic mechanisms, suitable for solving complex optimization problems. The specific process of generating scan trajectories based on the fitness value of each trajectory's starting position using a genetic algorithm is as follows:

[0089] Initialize the population: Randomly generate a set of initial scan trajectories as the initial population for the genetic algorithm.

[0090] Fitness assessment: The fitness function is used to assess the fitness of each individual in the population (i.e., each scan trajectory).

[0091] Selection operation: Selects superior individuals to enter the next generation of the population based on their fitness value. Individuals with higher fitness values ​​have a greater probability of being selected.

[0092] Crossover operation: Performing a crossover operation on selected individuals generates new individuals (i.e., new scan trajectories). The crossover operation simulates the gene recombination process in biological heredity, which helps to produce better individuals.

[0093] Mutation operation: Mutation is performed on newly generated individuals to introduce a degree of randomness and increase population diversity. Mutation simulates the gene mutation process in biological heredity, helping to prevent the algorithm from getting trapped in local optima.

[0094] Iterative optimization: Repeatedly perform selection, crossover, mutation, and other operations until the termination condition is met (such as reaching the maximum number of iterations or the fitness value reaching a preset threshold). The best individual in the final population is the generated scan trajectory.

[0095] In some embodiments, the scanning control unit determines the starting scanning height corresponding to the scanning trajectory point based on the scanning-related feature information of the ancient painting or calligraphy to be restored, including:

[0096] Interpolate the concave and convex heights of multiple locations in the ancient calligraphy and painting to be restored to generate the concave and convex heights corresponding to the scanning trajectory points;

[0097] Calculate the height difference between the concave / convex height corresponding to the scan trajectory point and the reference height;

[0098] The starting scanning height corresponding to the scanning trajectory point is determined based on the height difference between the concave and convex heights of the scanning trajectory point and the reference height.

[0099] Specifically, interpolation algorithms such as linear interpolation, polynomial interpolation, and spline interpolation can be used to interpolate the concavity and convexity heights at multiple locations on the ancient painting or calligraphy to be restored, generating the concavity and convexity heights corresponding to the scan trajectory points. The reference height is a preset standard height. Calculating the height difference between the concavity and convexity heights corresponding to the scan trajectory points and the reference height allows us to understand the degree of deviation of each scan trajectory point relative to the reference height. The height difference can be obtained by directly subtracting the concavity and convexity height value corresponding to the scan trajectory point from the reference height value.

[0100] When the height difference between the convex / concave height corresponding to the scan trajectory point and the reference height is greater than the preset height interpolation threshold, the scan trajectory point is uneven. The sum of the height difference between the convex / concave height corresponding to the scan trajectory point and the reference height and the convex / concave height is obtained to get the starting scan height corresponding to the scan trajectory point.

[0101] Understandably, the surface of ancient paintings and calligraphy often exhibits damage and paper stress, resulting in an uneven texture. This unevenness makes it difficult for the ultra-depth-of-field microscope lens to maintain a stable focusing distance during scanning. Using a uniform starting scanning height would inevitably lead to some areas being accurately focused while others are blurry. By determining the starting scanning height for each scanning trajectory point using the method described above, the microscope lens can automatically adjust its scanning height according to the different unevenness of the ancient painting and calligraphy surface, ensuring that each point starts scanning at a constant height. This effectively avoids image blurring caused by differences in focusing position, guaranteeing clear and accurate scanned images and providing high-quality image data for subsequent restoration work.

[0102] For each scanning trajectory point, after the ultra-depth-of-field 3D microscope reaches that point using the X-axis and Y-axis coordinate adjustment devices, the Z-axis coordinate adjustment device is used to adjust the microscope to the starting scanning height corresponding to that point. It then moves downwards in fixed steps (e.g., 20µm), triggering the camera to capture an image each time it reaches a new imaging position. For example, if 15 images need to be captured at each point, the ultra-depth-of-field 3D microscope will move downwards along the Z-axis 14 times, each time moving 20µm. This allows for the acquisition of multiple layers of images at each scanning trajectory point.

[0103] In some embodiments, the scanning device further includes a supplementary lighting device.

[0104] In some embodiments, the scanning control unit determines scanning parameters based on the scanning-related feature information of the ancient painting or calligraphy to be restored, including:

[0105] Based on material information, pigment type information, and color distribution characteristics, the supplementary lighting parameters are determined. Among them, the scanning parameters include supplementary lighting parameters, which include color temperature and light intensity.

[0106] Understandably, ancient paintings and calligraphy vary in materials, pigments, and color distribution. Supplemental lighting equipment, by adjusting color temperature and light intensity, can highlight the detailed features of these works, such as brushstrokes and textures, aiding in subsequent image analysis and restoration. Specifically, different types of paper have varying light reflection and absorption characteristics. For example, Xuan paper is relatively thin and has high light transmittance, potentially requiring lower light intensity to avoid overexposure; while thicker papers may require higher light intensity to ensure image brightness. If the painting or calligraphy is on fabric, the fabric's texture and fiber structure affect light scattering and reflection. In this case, the color temperature and light intensity of the supplemental lighting equipment need to be adjusted according to the fabric's characteristics to highlight the fabric's texture and the details of the painting or calligraphy. Mineral pigments typically have high reflectivity and vibrant colors. To accurately reproduce the colors of these pigments, a suitable color temperature needs to be selected so that the supplemental light matches the spectral characteristics of the pigment. For example, some red mineral pigments can display their most realistic colors at specific color temperatures. Plant pigments have relatively soft colors and are more sensitive to light. Excessive light intensity may cause plant pigments to fade or distort their colors. Therefore, it is necessary to adjust the light intensity according to the characteristics of the plant pigments, and at the same time, select an appropriate color temperature to highlight their color features. If the colors of ancient paintings and calligraphy are rich and the contrast is high, a higher light intensity is needed to highlight the color gradation and details. At the same time, an appropriate color temperature should be selected according to the warm and cool distribution of the colors to make the colors more vivid and realistic. If the colors of ancient paintings and calligraphy are simple and the contrast is low, the light intensity can be appropriately reduced to avoid overexposure caused by excessive light. At the same time, the color temperature should be adjusted to enhance the contrast and clarity of the colors.

[0107] In some embodiments, the scanning control unit determines the supplementary lighting parameters based on material information, pigment type information, and color distribution characteristics, including:

[0108] Obtain material information, pigment type information, color distribution characteristics, and optimal supplementary lighting parameters for multiple samples of ancient paintings and calligraphy;

[0109] By split hierarchical clustering, multiple ancient paintings and calligraphy samples are divided into multiple sample groups based on their material information, pigment type information, and color distribution characteristics.

[0110] Based on the material information, pigment type information, and color distribution characteristics of the ancient calligraphy and painting to be restored, determine the sample group to which the ancient calligraphy and painting to be restored belongs;

[0111] Based on the material information, pigment type information, and color distribution characteristics of the ancient calligraphy and painting to be restored, and the material information, pigment type information, and color distribution characteristics of the sample ancient calligraphy and painting included in the sample group to which the ancient calligraphy and painting to be restored belongs, similar sample ancient calligraphy and painting are identified.

[0112] Based on the optimal supplementary lighting parameters of similar ancient paintings and calligraphy works to be restored, the supplementary lighting parameters are determined.

[0113] Specifically, the material and pigment types of the sample ancient paintings and calligraphy are encoded, and the color distribution features are normalized. Then, appropriate distance metrics (such as Euclidean distance and cosine similarity) are used to calculate the distance between the sample paintings and calligraphy, and clustering is performed. Through split hierarchical clustering, multiple sample paintings and calligraphy are divided into multiple sample groups based on the distance between them.

[0114] The characteristics of the ancient painting / calligraphy to be restored are compared with the characteristics of each sample group, and the similarity between them and each sample group is calculated. The same distance metric method used in the clustering process can be used. The sample group with the highest similarity is selected as the sample group to which the ancient painting / calligraphy to be restored belongs. This means that the ancient painting / calligraphy to be restored can find samples with the most similar characteristics within this sample group. Within the sample group to which the ancient painting / calligraphy to be restored belongs, the similarity between the ancient painting / calligraphy to be restored and each sample ancient painting / calligraphy is further calculated. According to the preset similarity threshold, sample ancient paintings / calligraphy with high similarity to the ancient painting / calligraphy to be restored are selected as similar samples. Similar samples are very similar to the ancient painting / calligraphy to be restored in terms of material, pigment type, and color distribution characteristics. Therefore, their supplementary lighting parameters have high reference value for determining the supplementary lighting parameters of the ancient painting / calligraphy to be restored. Statistical analysis is performed on the optimal supplementary lighting parameters of similar sample ancient paintings / calligraphy. The average method, weighted average method, etc. can be used. For example, the average of the optimal supplementary lighting parameters of all similar samples is calculated as the reference value of the supplementary lighting parameters of the ancient painting / calligraphy to be restored.

[0115] The image processing module is used to stack the multi-layer images of each scanning trajectory point to generate the region image corresponding to each scanning trajectory point, and to stitch the region images corresponding to each scanning trajectory point to generate the scanned image of the ancient painting and calligraphy to be restored.

[0116] Specifically, stacking operations integrate multiple layers of images of a scan trajectory point, fusing them into a single image using a specific algorithm. The basic principle is to analyze the information of each pixel in each layer of the image and synthesize the final pixel value according to certain rules (such as taking the average, maximum, and minimum values, or a weighted average based on pixel quality). After stacking operations, each trajectory point obtains an image that integrates information from multiple layers, such as... Figure 8-10 As shown, these images are the region images corresponding to the respective trajectory points. The region images contain comprehensive information about the area where the trajectory point is located under various scanning conditions, enabling a more complete and accurate reflection of the characteristics of the ancient calligraphy and painting in that area, such as color, texture, and details. These region images form the basis for subsequent image stitching.

[0117] The stitching order of the region images is determined based on the layout of the scan trajectory points. For example, if the scanning was performed from left to right and from top to bottom, the stitching order can also be followed accordingly. Starting with adjacent region images, feature matching, transform model estimation, and image fusion are performed to stitch the two images into a larger image. Then, the stitched image is stitched with the next adjacent region image, and so on, until all region images are stitched together.

[0118] Figure 5 , Figure 6 These are schematic diagrams of the user interface of the scanning control unit according to some embodiments of this specification, such as... Figure 5 , Figure 6 As shown, the operator can control the scanning status of the scanning device (e.g., start, pause, stop, etc.) through this user interface, and can also obtain the working information of the scanning device, such as the X-axis position, Y-axis position, Z-axis position, etc. through this user interface.

[0119] The damage analysis module is used to determine the damage characteristics of the ancient paintings and calligraphy to be restored based on the scanned images of the paintings and calligraphy to be restored using a damage analysis model.

[0120] Figure 4 These are structural schematic diagrams of the damage analysis model shown in some embodiments of this specification, such as... Figure 4 As shown, in some embodiments, the damage analysis model includes a defect analysis unit, a fracture analysis unit, a discoloration analysis unit, and a pest analysis unit. The defect analysis unit is used to generate a defect distribution map based on the scanned image of the ancient calligraphy and painting to be restored; the fracture analysis unit is used to generate a fracture distribution map based on the scanned image of the ancient calligraphy and painting to be restored; the discoloration analysis unit is used to generate a discoloration distribution map based on the scanned image of the ancient calligraphy and painting to be restored; and the pest analysis unit is used to generate a pest distribution map based on the scanned image of the ancient calligraphy and painting to be restored.

[0121] Specifically, the damage analysis unit is used to identify and locate damaged areas on the surface of ancient paintings and calligraphy. Damage may manifest as wear, missing pieces, scratches, etc., which can compromise the integrity and artistic value of the artwork. The damage analysis unit processes and analyzes the scanned images, using edge detection algorithms to identify the boundaries of damaged areas. It distinguishes damaged parts by comparing pixel features (such as color and texture) between normal and damaged areas. For example, a worn area may be lighter in color than the surrounding normal area, and its texture may change. The damage analysis unit can capture these differences and generate a damage distribution map. This map visually displays the location, shape, and extent of damaged areas on the ancient painting or calligraphy. Restorers can use this map to understand the severity and distribution of the damage, providing crucial information for subsequent restoration work, such as identifying areas requiring repair and selecting appropriate repair materials.

[0122] The fracture analysis unit is used to identify fracture marks on ancient paintings and calligraphy. Fracture is one of the more serious forms of damage to ancient paintings and calligraphy, potentially leading to the loss of content and structural destruction. The fracture analysis unit performs edge detection and morphological analysis on scanned images to identify the boundaries and features of fractured areas. Fractured areas typically appear as obvious cracks or break lines in the image, with pixel features significantly different from normal areas. By analyzing information such as the length, width, and direction of the break lines, the degree and location of the fracture can be determined. The fracture distribution map shows in detail the location and morphology of fractures on ancient paintings and calligraphy. Restorers can assess the severity of the fracture based on the distribution map and select appropriate restoration methods, such as splicing or filling, to restore the integrity of the ancient paintings and calligraphy.

[0123] The color change analysis unit is used to detect color changes in ancient paintings and calligraphy. Due to the passage of time and the influence of environmental factors (such as light, humidity, and temperature), the colors of ancient paintings and calligraphy may fade or change, affecting their artistic effect and historical value. The color change analysis unit performs color space conversion and color feature extraction on the scanned image, converting the image from the RGB color space to other color spaces more suitable for color analysis (such as HSV and Lab). Then, by comparing the color feature values ​​of different regions, such as hue, saturation, and brightness, the area and degree of color change are determined. For example, a color histogram can visually display the distribution of colors in the image; by comparing the color histograms of normal areas and discolored areas, differences in color change can be identified. The color change distribution map clearly shows the area and degree of color change on the ancient paintings and calligraphy. Restorers can understand the type and extent of discoloration based on the distribution map and select appropriate restoration materials and methods, such as color restoration and fading treatment, to restore the original colors of the ancient paintings and calligraphy.

[0124] The pest analysis unit is used to detect whether ancient paintings and calligraphy have been damaged by insects and the extent of such damage. Insect damage is one of the common threats to the preservation of ancient paintings and calligraphy. Insects eat away at the paper and pigments, causing damage such as holes and defects. The pest analysis unit performs texture analysis and shape recognition on scanned images to find traces left by insects. Insect traces usually have specific shape and texture features, such as holes and insect tunnels. Through image processing algorithms, such as template matching and machine learning algorithms, these features can be identified and the location and extent of the insect damage can be determined. For example, images of common insect traces can be collected in advance as templates, and template matching algorithms can be used to find similar areas in the scanned images. The pest distribution map visually shows the distribution of insect damage on ancient paintings and calligraphy. Restorers can assess the impact of insect damage on ancient paintings and calligraphy based on the distribution map and take corresponding prevention and control measures, such as insecticide treatment and repair of damage caused by insects, to protect the safety of the ancient paintings and calligraphy.

[0125] The damage analysis module can merge incomplete distribution maps, fracture distribution maps, color change distribution maps, and pest distribution maps to generate, for example, Figure 6 The diagram shows the damage characteristics of the ancient painting and calligraphy to be restored.

[0126] Figure 11 This is a flowchart illustrating a super-depth-of-field microscopic scanning and AI image analysis method for the restoration of ancient paintings and calligraphy, as shown in some embodiments of this specification. Figure 11 As shown, the ultra-depth-of-field microscopic scanning and AI image analysis method for the restoration of ancient paintings and calligraphy may include the following steps:

[0127] Obtain scanned feature information of the ancient paintings and calligraphy to be restored;

[0128] Based on the scanning-related feature information of the ancient paintings and calligraphy to be restored, the scanning trajectory and scanning parameters are determined. The scanning trajectory includes multiple scanning trajectory points, and the scanning parameters include the starting scanning height corresponding to each scanning trajectory point.

[0129] Based on the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point, the spatial position of the ultra-depth-of-field 3D microscope is adjusted, and multi-layer images are acquired at each scanning trajectory point through the ultra-depth-of-field 3D microscope.

[0130] Stack the multi-layer images of each scanning trajectory point to generate the region image corresponding to each scanning trajectory point, and stitch the region images corresponding to each scanning trajectory point to generate the scanned image of the ancient painting and calligraphy to be restored.

[0131] Based on the scanned images of the ancient paintings and calligraphy to be restored, the damage characteristics of the paintings and calligraphy to be restored are determined using a damage analysis model.

[0132] The ultra-depth-of-field microscopy and AI image analysis method used for the restoration of ancient paintings and calligraphy can be applied to the ultra-depth-of-field microscopy and AI image analysis system used for the restoration of ancient paintings and calligraphy, which will not be elaborated here.

[0133] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A super-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy, characterized in that, include: The information acquisition module is used to acquire scan-related feature information of the ancient paintings and calligraphy to be restored; An automatic scanning module includes a scanning device, a super depth-of-field 3D microscope, and a scanning control unit. The super depth-of-field 3D microscope is mounted on the scanning device. The scanning control unit is used to determine the scanning trajectory and scanning parameters based on the scanning-related feature information of the ancient painting or calligraphy to be restored. The scanning trajectory includes multiple scanning trajectory points, and the scanning parameters include the starting scanning height corresponding to each scanning trajectory point. The scanning device is used to adjust the spatial position of the super depth-of-field 3D microscope according to the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point. The super depth-of-field 3D microscope is used to acquire multi-layer images at each scanning trajectory point. The image processing module is used to stack the multi-layer images of each scanning trajectory point to generate the region image corresponding to each scanning trajectory point, and to stitch the region images corresponding to each scanning trajectory point to generate the scanned image of the ancient painting and calligraphy to be restored. The damage analysis module is used to determine the damage characteristics of the ancient paintings and calligraphy to be restored based on the scanned images of the paintings and calligraphy to be restored using a damage analysis model. The scanning device includes a frame, a vacuum suction cup honeycomb plate, a position adjustment component, and a laser ranging component. Both the vacuum suction cup honeycomb plate and the position adjustment component are mounted on the frame. The position adjustment component is positioned above the vacuum suction cup honeycomb plate. The ancient painting / calligraphy to be restored is placed on the vacuum suction cup honeycomb plate. The position adjustment component includes an X-axis coordinate adjustment device, a Y-axis coordinate adjustment device, and a Z-axis coordinate adjustment device. The Y-axis coordinate adjustment device is mounted on the X-axis coordinate adjustment device, and the Z-axis coordinate adjustment device is mounted on the Y-axis coordinate adjustment device. The ultra-depth-of-field 3D microscope is mounted on the Z-axis coordinate adjustment device. The laser ranging component is mounted on the Z-axis coordinate adjustment device, and the laser ranging component includes a laser ranging dot matrix composed of multiple laser ranging devices. The scanning device is also used to adjust the position of the laser ranging component in the XY plane according to the preset ranging trajectory, wherein the XY plane is parallel to the vacuum suction cup honeycomb plate, the preset ranging trajectory includes multiple ranging trajectory points, the laser ranging component is used to acquire regional ranging information at each ranging trajectory point, and the scanning-related feature information of the ancient painting and calligraphy to be restored includes at least the regional ranging information corresponding to each ranging trajectory point. The scanning control unit determines the scanning trajectory based on the scanning-related feature information of the ancient painting or calligraphy to be restored, including: The scanning trajectory is determined based on the regional ranging information corresponding to each ranging trajectory point.

2. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy as described in claim 1, characterized in that, The scanning control unit determines the scanning trajectory based on the area ranging information corresponding to each ranging trajectory point, including: Based on the regional ranging information corresponding to each ranging trajectory point, the concavity and convexity heights of multiple locations of the ancient calligraphy and painting to be restored are generated. Establish a set of trajectory generation constraints, wherein the set of trajectory generation constraints includes at least the shortest distance and the longest distance between two adjacent scan trajectory points; A multi-objective reward function is established, wherein the multi-objective reward function is related to the difference in concavity and convexity height between two adjacent scan trajectory points, the concavity and convexity height of each scan trajectory point, and the distance between two adjacent scan trajectory points; The trajectory generation model generates a scanning trajectory based on the concavity and convexity of multiple locations of the ancient painting and calligraphy to be restored, the trajectory generation constraint set, and the multi-objective reward function.

3. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy according to claim 2, characterized in that, The scanning control unit generates a scanning trajectory based on the concavity and convexity of multiple locations of the ancient painting or calligraphy to be restored, a trajectory generation constraint set, and a multi-objective reward function, using a trajectory generation model. This trajectory includes: For each location, the difference in concavity / convexity height is determined based on the concavity / convexity height of adjacent locations; Normalize the concavity / convexity height difference value at each location to generate a normalized concavity / convexity height difference value at each location. Based on the normalized difference in concavity and convexity height at each location, multiple trajectory generation starting positions are determined from multiple locations; For each trajectory generation starting position, the trajectory generation model generates the scanning trajectory corresponding to the trajectory generation starting position based on the concavity and convexity height of multiple positions of the ancient painting and calligraphy to be restored, the trajectory generation constraint set, and the multi-objective reward function. Establish a fitness function, wherein the fitness function is related to the difference in concavity and convexity height between two adjacent scan trajectory points and the overlapping area of ​​scans between any two scan trajectory points; Determine the fitness value of the scan trajectory corresponding to the starting position of each trajectory generation; The scanning trajectory is generated by using a genetic algorithm to generate the fitness value of the scanning trajectory corresponding to the starting position of each trajectory.

4. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy as described in claim 2, characterized in that, The scanning control unit determines the starting scanning height corresponding to the scanning trajectory point based on the scanning-related feature information of the ancient painting or calligraphy to be restored, including: Interpolate the concave and convex heights of multiple locations in the ancient calligraphy and painting to be restored to generate the concave and convex heights corresponding to the scanning trajectory points; Calculate the height difference between the concave / convex height corresponding to the scan trajectory point and the reference height; The starting scanning height corresponding to the scanning trajectory point is determined based on the height difference between the concave and convex heights of the scanning trajectory point and the reference height.

5. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy according to any one of claims 1-4, characterized in that, The scan-related feature information of the ancient paintings and calligraphy to be restored also includes material information, pigment type information, and color distribution characteristics; The scanning device also includes a supplementary lighting device; The scanning control unit determines scanning parameters based on the scanning-related feature information of the ancient painting and calligraphy to be restored, including: Based on material information, pigment type information, and color distribution characteristics, supplementary lighting parameters are determined. The scanning parameters include supplementary lighting parameters, which include color temperature and light intensity.

6. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy according to claim 5, characterized in that, The scanning control unit determines the supplementary lighting parameters based on material information, pigment type information, and color distribution characteristics, including: Obtain material information, pigment type information, color distribution characteristics, and optimal supplementary lighting parameters for multiple samples of ancient paintings and calligraphy; By split hierarchical clustering, multiple ancient paintings and calligraphy samples are divided into multiple sample groups based on their material information, pigment type information, and color distribution characteristics. Based on the material information, pigment type information, and color distribution characteristics of the ancient calligraphy and painting to be restored, determine the sample group to which the ancient calligraphy and painting to be restored belongs; Based on the material information, pigment type information, and color distribution characteristics of the ancient calligraphy and painting to be restored, and the material information, pigment type information, and color distribution characteristics of the sample ancient calligraphy and painting included in the sample group to which the ancient calligraphy and painting to be restored belongs, similar sample ancient calligraphy and painting are identified. Based on the optimal supplementary lighting parameters of similar ancient paintings and calligraphy works to be restored, the supplementary lighting parameters are determined.

7. The ultra-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy according to any one of claims 1-4, characterized in that, The damage analysis model includes a defect analysis unit, a fracture analysis unit, a discoloration analysis unit, and a pest analysis unit. The defect analysis unit generates a defect distribution map based on the scanned image of the ancient painting or calligraphy to be restored. The fracture analysis unit generates a fracture distribution map based on the scanned image of the ancient painting or calligraphy to be restored. The discoloration analysis unit generates a discoloration distribution map based on the scanned image of the ancient painting or calligraphy to be restored. The pest analysis unit generates a pest distribution map based on the scanned image of the ancient painting or calligraphy to be restored.

8. A method for super-depth-of-field microscopic scanning and AI image analysis for the restoration of ancient paintings and calligraphy, applied to the super-depth-of-field microscopic scanning and AI image analysis system for the restoration of ancient paintings and calligraphy as described in any one of claims 1-7, characterized in that, include: Obtain scanned feature information of the ancient paintings and calligraphy to be restored; Based on the scanning-related feature information of the ancient paintings and calligraphy to be restored, the scanning trajectory and scanning parameters are determined. The scanning trajectory includes multiple scanning trajectory points, and the scanning parameters include the starting scanning height corresponding to each scanning trajectory point. Based on the scanning trajectory and the starting scanning height corresponding to each scanning trajectory point, the spatial position of the ultra-depth-of-field 3D microscope is adjusted, and multi-layer images are acquired at each scanning trajectory point through the ultra-depth-of-field 3D microscope. Stack the multi-layer images of each scanning trajectory point to generate the region image corresponding to each scanning trajectory point, and stitch the region images corresponding to each scanning trajectory point to generate the scanned image of the ancient painting and calligraphy to be restored. Based on the scanned images of the ancient paintings and calligraphy to be restored, the damage characteristics of the paintings and calligraphy to be restored are determined using a damage analysis model.

Images