Method and system for reproducing the full appearance of paper cultural relics based on spectral imaging technology

Abstract

The present invention relates to the field of spectral imaging technology, and discloses a method and system for reproducing the full appearance of paper cultural relics based on spectral imaging technology. The present invention comprises the following steps: obtaining spectral image information of different parts of the cultural relics to be analyzed; performing data preprocessing according to the spectral image information to obtain preprocessed image information; performing linear combination according to the preprocessed image information to obtain a new spectral image; performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; performing integration according to the images at different resolutions to obtain an integrated image; performing reconstruction according to the integrated image to obtain the full appearance image information of the paper cultural relics. This method can improve the accuracy of the appearance reproduction of paper cultural relics.

Description

Technical Field

[0001] The present invention relates to the field of spectral imaging technology, and in particular to a method and system for reproducing the full appearance of paper cultural relics based on spectral imaging technology. Background Art

[0002] At present, optical imaging technology is widely used in many fields such as industry, agriculture, and military due to its non-contact and non-destructive characteristics. Traditional camera technology obtains the two-dimensional intensity information of the target in space through photosensitive film or CCD array. However, the interaction between light and matter depends not only on the light intensity information, but also on the spectral information such as light scattering, reflection, and transmission. Therefore, under the same lighting conditions, even the same target in human vision will be observed in different colors at different spatial positions, and visible light imaging technology cannot restore the true color of the target.

[0003] In the field of cultural relics protection, spectral technology can be used to quickly analyze the material characteristics of cultural relics, especially for paper cultural relics. Due to the different composition of paper cultural relics, the absorption peaks in the short-wave infrared region are different. The use of spectral cameras can achieve the full-color spectrum of paper cultural relics, providing a theoretical basis for the preservation and restoration of cultural relics. Especially for murals, due to the different composition of different murals, traditional visible light imaging may be covered by pigments and unable to distinguish their components, while spectral imaging technology can distinguish the material composition under the pigment, thus providing important information for the preservation and research of murals.

[0004] However, the existing spectral imaging technology is used to restore images, which relies on image processing technology at the same resolution and has low restoration accuracy. Summary of the invention

[0005] The present invention provides a method and system for reproducing the full appearance of paper cultural relics based on spectral imaging technology, so as to solve the technical problem that when restoring images using spectral imaging technology, the image processing technology under the same resolution is relied on and the restoration accuracy is not high.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a method for reproducing the full appearance of paper cultural relics based on spectral imaging technology, comprising:

[0007] Obtain spectral image information of different parts of the cultural relics to be analyzed;

[0008] Performing data preprocessing according to the spectral image information to obtain preprocessed image information;

[0009] Performing linear combination according to the preprocessed image information to obtain a new spectral image;

[0010] According to the new spectral image, performing different levels of decomposition to obtain a multi-filter sequence;

[0011] According to the multi-filter sequence, fusion processing is performed to obtain images at different resolutions;

[0012] Integrate the images at different resolutions to obtain an integrated image;

[0013] Reconstruction is performed based on the integrated image to obtain full appearance image information of the paper cultural relic.

[0014] As an optional implementation manner, the obtaining of spectral image information of different parts of the cultural relic to be analyzed includes:

[0015] Place the machine vision module at different positions of the cultural relics to be analyzed to obtain image information of the front, back, left, right, top and bottom areas;

[0016] Performing image analysis based on the image information of the front, back, left, right, top and bottom regions to obtain spectral information of the image;

[0017] Obtaining spectral image information according to the image information and spectral information of the image;

[0018] The image information of the front, back, left, right, top and bottom areas is subjected to image analysis, including light scattering, reflection and projection spectrum information.

[0019] As an optional implementation manner, performing data preprocessing according to the spectral image information to obtain preprocessed image information includes:

[0020] Performing filtering processing according to the spectral image information to obtain filtered image information;

[0021] Performing image registration according to the filtered image information to obtain preprocessed image information;

[0022] Among them, the filtering processing includes: eliminating noise, fringe interference, fringe pseudo-sum and interference of strong light sources in the hyperspectral image; image registration is to correct the image deviation caused by geometric deformation and position deviation caused by the uneven surface of the paper product during the process of capturing spectral image information.

[0023] As an optional implementation manner, performing linear combination according to the preprocessed image information to obtain a new spectral image includes:

[0024] According to the preprocessed image information, a judgment is made to obtain spectral images of different types and spectral images of the same type;

[0025] According to the different types of spectral images, linear combinations of different wavelengths are performed to obtain new spectral images at each wavelength;

[0026] According to the spectral images of the same type, linearly combining the same wavelength to obtain a new spectral image;

[0027] The linear combination method includes: multiple linear regression method and least partial squares method.

[0028] As an optional implementation, performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence includes:

[0029] According to the new spectral image, regional division is performed to obtain an image corresponding to the spectral band;

[0030] According to the images corresponding to the spectral bands, multi-resolution analysis is performed to obtain resolution information;

[0031] Decomposing according to the resolution information to generate multiple filter sequences;

[0032] The region division includes dividing the image blocks, image columns, image rows or local regions, and the local regions are pre-set according to the characteristics of the cultural relics information.

[0033] As an optional implementation manner, performing fusion processing according to the multi-filter sequence to obtain images at different resolutions includes:

[0034] According to the multi-filter sequence, filtering at different scales is performed to obtain scale filtering information;

[0035] According to the scale filtering information, filtering in different dimensions is performed to obtain dimension filtering information;

[0036] According to the dimensional filtering information, grayscale calculation is performed at different resolutions to obtain image grayscale value information;

[0037] According to the image gray value information, images at different resolutions are obtained;

[0038] Wherein, the grayscale calculation at different resolutions is performed according to the dimensional filtering information, and the grayscale value is calculated by the following formula:

[0039]

[0040] In the formula, is the fused image at pixel position The gray value of is the low-resolution image at pixel location The gray value of is a high-resolution image in The gray value of and is the weight function of the shape filter, So A filter window with four pixel units spreading outward from the center; wherein x and y are the horizontal and vertical coordinate values ​​of a two-dimensional rectangular coordinate system established with the geometric center of the image as the origin, the long side as the x-axis, and the short side as the y-axis;

[0041] The fusion processing includes low-rank matrix fusion, high-rank matrix fusion, multi-view fusion based on linear combination, local weight sparse transformation coefficient fusion or wavelet fusion.

[0042] As an optional implementation manner, integrating the images at different resolutions to generate a new spectral image includes:

[0043] Performing weighted averaging on the images at different resolutions to obtain image mean information;

[0044] Calculating pixel criteria based on the image mean information to obtain criteria information;

[0045] According to the criterion information, principal component weight fusion is performed to obtain a new spectral image;

[0046] The performing weighted averaging according to the images at different resolutions includes: performing weight processing according to the grayscale values ​​of the images at different resolutions to obtain image mean information.

[0047] As an optional implementation, the reconstructing according to the new spectral image to obtain the full appearance image information of the paper cultural relic includes:

[0048] Comparing the new spectral image with the cultural relic to be analyzed to obtain comparison information;

[0049] Performing a difference elimination process according to the contrast information to obtain image difference elimination information;

[0050] Based on the image difference elimination information, compensation is performed to obtain the full appearance image information of the cultural relic.

[0051] In a second aspect, the present invention provides a system for reproducing the full appearance of paper cultural relics based on spectral imaging technology, comprising:

[0052] An image acquisition module is used to obtain spectral image information of different parts of the cultural relics to be analyzed;

[0053] A preprocessing module, used for performing data preprocessing according to the spectral image information to obtain preprocessed image information;

[0054] An information processing module, used for performing linear combination according to the preprocessed image information to obtain a new spectral image;

[0055] An information decomposition module, used for performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence;

[0056] A fusion processing module, used for performing fusion processing according to the multi-filter sequence to obtain images at different resolutions;

[0057] An information integration module, used for integrating the images at different resolutions to obtain an integrated image;

[0058] The information reconstruction module is used to reconstruct the integrated image to obtain the full appearance image information of the paper cultural relic.

[0059] In a third aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for reproducing the full appearance of paper cultural relics based on spectral imaging technology.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention provides a method, system and medium for reproducing the full appearance of paper cultural relics based on spectral imaging technology. The method is executed by a controller and includes: acquiring spectral image information of different parts of the cultural relics to be analyzed; performing data preprocessing according to the spectral image information to obtain preprocessed image information; performing linear combination according to the preprocessed image information to obtain a new spectral image; performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; performing integration according to the images at different resolutions to generate a new spectral image; and performing reconstruction according to the new spectral image to obtain the full appearance image information of the paper cultural relics.

[0062] The present invention obtains spectral image information of different parts of cultural relics through a machine vision module, first performs denoising and standardization preprocessing on these data, and then uses the preprocessed image for linear combination to generate a new spectral image. Next, the image is decomposed at multiple levels to extract multi-filter sequences of different frequencies, and these sequences are fused to generate images at different resolutions. These images are integrated to form a new comprehensive spectral image, and finally the full appearance image information of the paper cultural relics is obtained through reconstruction, thereby realizing the comprehensive digital reproduction of the cultural relics. The present invention uses image spectral imaging technology, combines the spectral graph of the captured image and the original image to obtain the difference between the two, and obtains the full appearance image of the paper cultural relics. In this process, a clearer image is obtained, which improves the accuracy of the full appearance reproduction of the paper cultural relics. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a schematic diagram of a process for reproducing the full appearance of a paper cultural relic based on spectral imaging technology provided by the first embodiment of the present invention;

[0064] Figure 2 It is a schematic diagram of a structure for reproducing the full appearance of a paper cultural relic based on spectral imaging technology provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Reference Figure 1 The first embodiment of the present invention provides a method for reproducing the full appearance of paper cultural relics based on spectral imaging technology, comprising the following steps:

[0067] S11, obtaining spectral image information of different parts of the cultural relic to be analyzed;

[0068] S12, performing data preprocessing according to the spectral image information to obtain preprocessed image information;

[0069] S13, performing linear combination according to the preprocessed image information to obtain a new spectral image;

[0070] S14, performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence;

[0071] S15, performing fusion processing according to the multi-filter sequence to obtain images at different resolutions;

[0072] S16, integrating the images at different resolutions to obtain an integrated image;

[0073] S17, reconstructing the integrated image to obtain the full appearance image information of the paper cultural relic.

[0074] It should be noted that the acquisition and analysis of spectral image information of different parts of cultural relics is collected by machine vision modules, which are key components in modern industrial automation and intelligent manufacturing. They capture and analyze images through high-precision visual sensors to provide necessary visual information for the automation system. This module usually includes different types of cameras, such as CCD (charge-coupled device) cameras, CMOS (complementary metal oxide semiconductor) cameras and linear array cameras, each of which has unique advantages and application scenarios. CCD cameras are known for their high resolution, high sensitivity and excellent image quality, and are particularly suitable for applications that require high-quality image capture. CMOS cameras are favored for their fast imaging capabilities, low power consumption and cost-effectiveness, and are widely used in situations that require fast response. Linear array cameras are used for continuous object detection and measurement tasks with their expertise in high-speed scanning and precise measurement.

[0075] Exemplarily, in this embodiment, the machine vision module uses a CMOS camera. The CMOS camera collects the image data of the SMT patch to be inspected, and the generated digital image data contains detailed visual information of the SMT patch image to be inspected, which can be used for further image processing, analysis and decision making.

[0076] The present invention provides a method, system and medium for reproducing the full appearance of paper cultural relics based on spectral imaging technology. The method is executed by a controller, including: obtaining spectral image information of different parts of the cultural relics to be analyzed; performing data preprocessing according to the spectral image information to obtain preprocessed image information; performing linear combination according to the preprocessed image information to obtain a new spectral image; performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; performing integration according to the images at different resolutions to generate a new spectral image; performing reconstruction according to the new spectral image to obtain the full appearance image information of the paper cultural relics. The spectral image information of different parts of the cultural relics is obtained through a machine vision module, and the data are first preprocessed for denoising and standardization, and then the preprocessed image is used for linear combination to generate a new spectral image. Next, the image is decomposed at multiple levels to extract multi-filter sequences of different frequencies, and these sequences are fused to generate images at different resolutions. These images are integrated to form a new comprehensive spectral image, and finally the full appearance image information of the paper cultural relics is obtained through reconstruction, realizing the comprehensive digital reproduction of the cultural relics and improving the accuracy of the full appearance reproduction of paper cultural relics.

[0077] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0078] In step S11, the spectral image information of different parts of the cultural relic to be analyzed is obtained, including: placing a machine vision module at different positions of the cultural relic to be analyzed to obtain image information of the front, back, left, right, top, and bottom areas; performing image analysis based on the image information of the front, back, left, right, top, and bottom areas to obtain spectral information of the image; obtaining spectral image information based on the image information and the spectral information of the image; wherein, the image information of the front, back, left, right, top, and bottom areas is subjected to image analysis, including scattering, reflection, and projection spectral information of light.

[0079] It should be noted that the image information and the spectral information of the image refer to two aspects of the image. The image information refers to the surface features of the image, such as brightness and grayscale; the spectral information of the image refers to the information on uneven light distribution caused by scattering, reflection and projection during the imaging process.

[0080] In step S12, data preprocessing is performed according to the spectral image information to obtain preprocessed image information, including filtering according to the spectral image information to obtain filtered image information; image registration is performed according to the filtered image information to obtain preprocessed image information; wherein the filtering includes: eliminating noise, fringe interference, fringe pseudo and strong light source interference in the hyperspectral image; image registration is to correct the image deviation caused by geometric deformation and position deviation caused by the uneven surface of the paper product in the process of capturing the spectral image information.

[0081] It should be noted that the noise elimination in the spectral image mainly includes:

[0082]

[0083] In the formula, It represents the image before filtering. It represents the image information after filtering. represents the Gaussian kernel function, It represents the coordinates required The distance between the horizontal axes, It represents the coordinates required The distance between the vertical coordinates, It represents the maximum value of the horizontal axis. It represents the maximum value of the vertical coordinate, wherein the coordinate system is established with the geometric center of the image as the origin, the long side as the x-axis, and the short side as the y-axis.

[0084] It should be noted that stripe interference, stripe pseudo-sum, and strong light source interference are mainly processed based on the area with obvious missing points on the image, and the missing information is obtained by taking the average based on the surrounding information of the missing points.

[0085] In step S13, a new spectral image is obtained by performing linear combination according to the preprocessed image information, including: judging according to the preprocessed image information to obtain spectral images of different types and spectral images of the same type; performing linear combination of different wavelengths according to the spectral images of different types to obtain new spectral images at each wavelength; performing linear combination of the same wavelength according to the spectral images of the same type to obtain a new spectral image; wherein the linear combination method includes: multiple linear regression method and least partial squares method.

[0086] It should be noted that the main difference between the different types of spectral images and the same type of spectral images is that the judgment is based on the wavelength of light. The wavelength span of light of different types of spectral images is above 300 nanometers, while the span of spectral images of the same type is below 300 nanometers.

[0087] It should be further noted that the least partial squares method includes:

[0088]

[0089] In the formula, It represents the actual spectrum information. represents the fitted spectral image information, where It represents the coefficient of fitting image information. It represents the intercept of the fitted image information. It represents the horizontal coordinate position of the image coordinate point, i represents the mark value information, It represents the total number of horizontal axes.

[0090] Among them, m can be calculated by the following formula:

[0091]

[0092] In the formula, It represents the horizontal coordinate position of the image coordinate point. It represents the ordinate position of the image coordinate point. It represents the total number of horizontal axes.

[0093] In step S14, different levels of decomposition are performed according to the new spectral image to obtain a multi-filter sequence, including: performing regional division according to the new spectral image to obtain an image corresponding to the spectral band; performing multi-resolution analysis according to the image corresponding to the spectral band to obtain resolution information; performing decomposition according to the resolution information to generate multiple filter sequences; wherein the regional division includes dividing the image into blocks, image columns, image rows or local areas, and the local area is pre-set according to the characteristics of the cultural relics information.

[0094] It should be noted that the multi-resolution analysis based on the image corresponding to the spectral band to obtain the resolution information refers to magnifying the image corresponding to the spectral band and obtaining the maximum magnification when the image gradually blurs. The maximum magnification at this time is the resolution information.

[0095] It should be further explained that the decomposition according to the resolution information is to classify images with different resolutions to obtain multiple filter sequences.

[0096] In step S15, the fusion process is performed according to the multi-filter sequence to obtain images at different resolutions, including:

[0097] According to the multi-filter sequence, filtering at different scales is performed to obtain scale filtering information;

[0098] According to the scale filtering information, filtering in different dimensions is performed to obtain dimension filtering information;

[0099] According to the dimensional filtering information, grayscale calculation is performed at different resolutions to obtain image grayscale value information;

[0100] According to the image gray value information, images at different resolutions are obtained;

[0101] Among them, the grayscale calculation at different resolutions is performed according to the dimensional filtering information, and the calculation can be performed using the following formula:

[0102]

[0103] In the formula, is the fused image at pixel position The gray value of is the low-resolution image at pixel location The gray value of is a high-resolution image in The gray value of and is the weight function of the shape filter, So A filter window with four pixel units spreading outward from the center; wherein x and y are the horizontal and vertical coordinate values ​​of a two-dimensional rectangular coordinate system established with the geometric center of the image as the origin, the long side as the x-axis, and the short side as the y-axis;

[0104] The fusion processing includes low-rank matrix fusion, high-rank matrix fusion, multi-view fusion based on linear combination, local weight sparse transformation coefficient fusion or wavelet fusion.

[0105] It should be noted that the and It is the weight function of the shape filter. The weight function is set by the user and can be a one-time linear function or a quadratic linear function. No specific limitation is made here.

[0106] It should be noted that the fused scale filter group includes four different scales and five dimensions, each scale is composed of three biquadric surfaces, and the five dimensions include horizontal, vertical, tilted 45°, tilted -45°, and horizontal and vertical 45°.

[0107] In step S16, the images at different resolutions are integrated to generate a new spectral image, including:

[0108] Performing weighted averaging on the images at different resolutions to obtain image mean information;

[0109] Calculating pixel criteria based on the image mean information to obtain criteria information;

[0110] According to the criterion information, principal component weight fusion is performed to obtain a new spectral image;

[0111] The performing weighted averaging according to the images at different resolutions includes: performing weighted averaging according to the grayscale values ​​of the images at different resolutions to obtain image mean information.

[0112] It should be noted that the weighted average is performed based on the images at different resolutions, the weighted average value can be 0.2, 0.8, and the sum of the weighted total values ​​must be 1, which is not specifically limited here.

[0113] In step S17, the reconstruction is performed based on the new spectral image to obtain the full appearance image information of the paper cultural relic, including:

[0114] Comparing the new spectral image with the cultural relic to be analyzed to obtain comparison information;

[0115] Performing a difference elimination process according to the contrast information to obtain image difference elimination information;

[0116] Based on the image difference elimination information, compensation is performed to obtain the full appearance image information of the cultural relic.

[0117] It should be noted that performing the de-difference processing according to the contrast information to obtain the image de-difference information includes performing subtraction according to the grayscale value of the contrast information to obtain the image de-difference information.

[0118] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0119] In this embodiment, a system for reproducing the full appearance of paper cultural relics based on spectral imaging technology is proposed. The system consists of the following key parts: spectral acquisition system, image preprocessing system, spectral synthesis system, hierarchical decomposition system, resolution fusion system, image integration system, and appearance reconstruction system. The spectral acquisition system is responsible for capturing spectral images of paper cultural relics in different bands using a hyperspectral camera or scanning device; the image preprocessing system is responsible for performing preliminary processing on the acquired spectral image data, including denoising, etc.; the spectral synthesis system is responsible for combining the preprocessed images using a specific algorithm, and fusing information from different bands through linear combination technology to generate new spectral images; the multi-level decomposition system is responsible for performing multi-level decomposition on the synthesized spectral image to extract image features of different frequencies and scales; the resolution fusion system is responsible for integrating the filter sequence generated by the multi-level decomposition, and generating images at multiple resolution levels through multi-scale fusion technology to ensure that key features can be maintained at different scales; the image integration system is responsible for integrating images of different resolutions; the appearance reconstruction system is responsible for generating a complete appearance image of the paper cultural relic through high-precision synthesis technology.

[0120] Step 1: Use high-precision machine vision modules to collect spectral image information from different angles of the cultural relics. Through comprehensive coverage of front, back, left, right, top and bottom, obtain the scattering, reflection and projection characteristics of light to ensure that all details on the surface of the cultural relics are captured.

[0121] Step 2: Perform preliminary processing on the acquired spectral image, including removing noise and fringe interference, and correcting the influence of strong light sources. Apply image registration technology to correct the geometric deformation and position deviation caused by the uneven surface of the paper, laying the foundation for subsequent processing.

[0122] Step 3: Analyze and judge the preprocessed image information, and generate a new image by linearly combining the spectral information of different wavelengths. Use multiple linear regression and least partial squares method to ensure that the combined spectral image can fully reflect the diverse characteristics of the cultural relics.

[0123] Step 4: Perform regional division and multi-resolution analysis on the newly generated spectral image. Decompose the image to generate multiple filter sequences according to the specific requirements of the spectral band. This process can extract the key parts of the cultural relic information that need attention.

[0124] Step 5: Fuse the filter sequences obtained by multi-level decomposition, and calculate the grayscale values ​​of images of different resolutions through filtering of scale and dimension. Apply low-rank matrix fusion or other methods to generate clear images at all resolutions.

[0125] Step 6: Perform weighted averaging and principal component weight fusion on the images at different resolutions to generate the final comprehensive spectral image. By comparing with the actual cultural relics, perform difference elimination and compensation processing to ensure that the reconstructed image accurately reproduces the complete appearance of the paper cultural relics.

[0126] In summary, the present invention provides a method, system and medium for reproducing the full appearance of paper cultural relics based on spectral imaging technology. The method is executed by a controller, including: obtaining spectral image information of different parts of the cultural relics to be analyzed; performing data preprocessing according to the spectral image information to obtain preprocessed image information; performing linear combination according to the preprocessed image information to obtain a new spectral image; performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; integrating according to the images at different resolutions to generate a new spectral image; reconstructing according to the new spectral image to obtain the full appearance image information of the paper cultural relics. The spectral image information of different parts of the cultural relics is obtained by a machine vision module, and the data are first preprocessed for denoising and standardization, and then the preprocessed images are linearly combined to generate a new spectral image. Next, the image is multi-level decomposed to extract multi-filter sequences of different frequencies, and these sequences are fused to generate images at different resolutions. These images are integrated to form a new comprehensive spectral image, and finally the full appearance image information of the paper cultural relics is obtained by reconstruction, so as to realize the comprehensive digital reproduction of the cultural relics. The present invention uses image spectral imaging technology to combine the spectrum of the captured image and the original image to obtain the difference between the two and obtain a full appearance image of the paper cultural relic. In this process, a clearer image is obtained, thereby improving the accuracy of reproducing the full appearance of the paper cultural relic.

[0127] Reference Figure 2 The second embodiment of the present invention provides a system for reproducing the full appearance of paper cultural relics based on spectral imaging technology, comprising:

[0128] An image acquisition module is used to obtain spectral image information of different parts of the cultural relics to be analyzed;

[0129] A preprocessing module, used for performing data preprocessing according to the spectral image information to obtain preprocessed image information;

[0130] An information processing module, used for performing linear combination according to the preprocessed image information to obtain a new spectral image;

[0131] An information decomposition module, used for performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence;

[0132] A fusion processing module, used for performing fusion processing according to the multi-filter sequence to obtain images at different resolutions;

[0133] An information integration module, used for integrating the images at different resolutions to obtain an integrated image;

[0134] The information reconstruction module is used to reconstruct the integrated image to obtain the full appearance image information of the paper cultural relic.

[0135] In one embodiment, the image acquisition module is used to acquire spectral image information of different parts of the cultural relic to be analyzed, including:

[0136] Place the machine vision module at different positions of the cultural relics to be analyzed to obtain image information of the front, back, left, right, top and bottom areas;

[0137] Performing image analysis based on the image information of the front, back, left, right, top and bottom regions to obtain spectral information of the image;

[0138] Obtaining spectral image information according to the image information and spectral information of the image;

[0139] The image information of the front, back, left, right, top and bottom areas is subjected to image analysis, including light scattering, reflection and projection spectrum information.

[0140] In one embodiment, the preprocessing module is used to perform data preprocessing according to the spectral image information to obtain preprocessed image information, including:

[0141] Performing filtering processing according to the spectral image information to obtain filtered image information;

[0142] Performing image registration according to the filtered image information to obtain preprocessed image information;

[0143] Among them, the filtering processing includes: eliminating noise, fringe interference, fringe pseudo-sum and interference of strong light sources in the hyperspectral image; image registration is to correct the image deviation caused by geometric deformation and position deviation caused by the uneven surface of the paper product during the process of capturing spectral image information.

[0144] In one embodiment, the information processing module is used to perform linear combination according to the preprocessed image information to obtain a new spectral image, including:

[0145] According to the preprocessed image information, a judgment is made to obtain spectral images of different types and spectral images of the same type;

[0146] According to the different types of spectral images, linear combinations of different wavelengths are performed to obtain new spectral images at each wavelength;

[0147] According to the spectral images of the same type, linearly combining the same wavelength to obtain a new spectral image;

[0148] The linear combination method includes: multiple linear regression method and least partial squares method.

[0149] In one embodiment, the information decomposition module is used to perform different levels of decomposition according to the new spectral image to obtain a multi-filter sequence, including:

[0150] According to the new spectral image, regional division is performed to obtain an image corresponding to the spectral band;

[0151] According to the images corresponding to the spectral bands, multi-resolution analysis is performed to obtain resolution information;

[0152] Decomposing according to the resolution information to generate multiple filter sequences;

[0153] The region division includes dividing the image blocks, image columns, image rows or local regions, and the local regions are pre-set according to the characteristics of the cultural relics information.

[0154] A fusion processing module is used to perform fusion processing according to the multi-filter sequence to obtain images at different resolutions, including:

[0155] According to the multi-filter sequence, filtering at different scales is performed to obtain scale filtering information;

[0156] According to the scale filtering information, filtering in different dimensions is performed to obtain dimension filtering information;

[0157] According to the dimensional filtering information, grayscale calculation is performed at different resolutions to obtain image grayscale value information;

[0158] According to the image gray value information, images at different resolutions are obtained;

[0159] Wherein, the grayscale calculation at different resolutions is performed according to the dimensional filtering information, and the grayscale value is calculated by the following formula:

[0160]

[0161] In the formula, is the fused image at pixel position The gray value of is the low-resolution image at pixel location The gray value of is a high-resolution image in The gray value of and is the weight function of the shape filter, So A filter window with four pixel units spreading outward from the center; wherein x and y are the horizontal and vertical coordinate values ​​of a two-dimensional rectangular coordinate system established with the geometric center of the image as the origin, the long side as the x-axis, and the short side as the y-axis;

[0162] The fusion processing includes low-rank matrix fusion, high-rank matrix fusion, multi-view fusion based on linear combination, local weight sparse transformation coefficient fusion or wavelet fusion.

[0163] The information integration module is used to integrate the images at different resolutions to generate a new spectral image, including:

[0164] Performing weighted averaging on the images at different resolutions to obtain image mean information;

[0165] Calculating pixel criteria based on the image mean information to obtain criteria information;

[0166] According to the criterion information, principal component weight fusion is performed to obtain a new spectral image;

[0167] The performing weighted averaging according to the images at different resolutions includes: performing weight processing according to the grayscale values ​​of the images at different resolutions to obtain image mean information.

[0168] The information reconstruction module is used to reconstruct the new spectral image to obtain the full appearance image information of the paper cultural relic, including:

[0169] Comparing the new spectral image with the cultural relic to be analyzed to obtain comparison information;

[0170] Performing a difference elimination process according to the contrast information to obtain image difference elimination information;

[0171] Based on the image difference elimination information, compensation is performed to obtain the full appearance image information of the cultural relic.

[0172] It should be noted that a system for reproducing the full appearance of paper cultural relics based on spectral imaging technology provided in an embodiment of the present invention is used to execute all the process steps of a method for reproducing the full appearance of paper cultural relics based on spectral imaging technology in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0173] In summary, the present invention provides a method, system and medium for reproducing the full appearance of paper cultural relics based on spectral imaging technology. The method is executed by a controller, including: obtaining spectral image information of different parts of the cultural relics to be analyzed; performing data preprocessing according to the spectral image information to obtain preprocessed image information; performing linear combination according to the preprocessed image information to obtain a new spectral image; performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; integrating according to the images at different resolutions to generate a new spectral image; reconstructing according to the new spectral image to obtain the full appearance image information of the paper cultural relics. The spectral image information of different parts of the cultural relics is obtained by a machine vision module, and the data are first preprocessed for denoising and standardization, and then the preprocessed images are linearly combined to generate a new spectral image. Next, the image is multi-level decomposed to extract multi-filter sequences of different frequencies, and these sequences are fused to generate images at different resolutions. These images are integrated to form a new comprehensive spectral image, and finally the full appearance image information of the paper cultural relics is obtained by reconstruction, so as to realize the comprehensive digital reproduction of the cultural relics. The present invention uses image spectral imaging technology to combine the spectrum of the captured image and the original image to obtain the difference between the two and obtain a full appearance image of the paper cultural relic. In this process, a clearer image is obtained, thereby improving the accuracy of reproducing the full appearance of the paper cultural relic.

[0174] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an image preprocessing program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the method for reproducing the full appearance of paper cultural relics based on spectral imaging technology are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned system embodiments are realized, such as the information processing module.

[0175] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0176] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0177] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0178] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0179] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0180] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0181] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for reproducing the full appearance of paper cultural relics based on spectral imaging technology, characterized in that: include: Obtain spectral image information of different parts of the cultural relics to be analyzed; Performing data preprocessing according to the spectral image information to obtain preprocessed image information; According to the preprocessed image information, a linear combination is performed to obtain a new spectral image, including: According to the preprocessed image information, a judgment is made to obtain spectral images of different types and spectral images of the same type; according to the spectral images of different types, a linear combination of different wavelengths is performed to obtain new spectral images at each wavelength; according to the spectral images of the same type, a linear combination of the same wavelength is performed to obtain a new spectral image; Wherein, the linear combination method includes: multiple linear regression method and least partial squares method; According to the new spectral image, different levels of decomposition are performed to obtain a multi-filter sequence, including: According to the new spectral image, regional division is performed to obtain an image corresponding to the spectral band; according to the image corresponding to the spectral band, multi-resolution analysis is performed to obtain resolution information; according to the resolution information, decomposition is performed to generate multiple filter sequences; Wherein, the region division includes dividing the image blocks, image columns, image rows or local regions, and the local regions are pre-set according to the characteristics of cultural relics information; The step of decomposing the images according to the resolution information to generate multiple filter sequences includes: classifying images with different resolutions to obtain multiple filter sequences; According to the multi-filter sequence, fusion processing is performed to obtain images at different resolutions, including: According to the multi-filter sequence, filtering at different scales is performed to obtain scale filtering information; According to the scale filtering information, filtering in different dimensions is performed to obtain dimension filtering information; According to the dimensional filtering information, grayscale calculation is performed at different resolutions to obtain image grayscale value information; According to the image gray value information, images at different resolutions are obtained; Wherein, the grayscale calculation at different resolutions is performed according to the dimensional filtering information, and the grayscale value is calculated by the following formula: In the formula, is the fused image at pixel position The gray value of is the low-resolution image at pixel location The gray value of is a high-resolution image in The gray value of and is the weight function of the shape filter, So A filter window with four pixel units spreading outward from the center; wherein x and y are the horizontal and vertical coordinate values ​​of a two-dimensional rectangular coordinate system established with the geometric center of the image as the origin, the long side as the x-axis, and the short side as the y-axis; The fusion process includes low-rank matrix fusion, high-rank matrix fusion, multi-view fusion based on linear combination, local weight sparse transformation coefficient fusion or wavelet fusion; Integrate the images at different resolutions to obtain an integrated image; Reconstruction is performed based on the integrated image to obtain full appearance image information of the paper cultural relic.

2. The method for reproducing the full appearance of paper cultural relics based on spectral imaging technology according to claim 1, characterized in that: The step of obtaining spectral image information of different parts of the cultural relic to be analyzed includes: Place the machine vision module at different positions of the cultural relics to be analyzed to obtain image information of the front, back, left, right, top and bottom areas; Performing image analysis based on the image information of the front, back, left, right, top and bottom regions to obtain spectral information of the image; Obtaining spectral image information according to the image information and spectral information of the image; The image information of the front, back, left, right, top and bottom areas is subjected to image analysis, including light scattering, reflection and projection spectrum information.

3. The method for reproducing the full appearance of paper cultural relics based on spectral imaging technology according to claim 1, characterized in that: The step of performing data preprocessing according to the spectral image information to obtain preprocessed image information includes: Performing filtering processing according to the spectral image information to obtain filtered image information; Performing image registration according to the filtered image information to obtain preprocessed image information; Among them, the filtering processing includes: eliminating noise, fringe interference, fringe pseudo-sum and interference of strong light sources in the hyperspectral image; image registration is to correct the image deviation caused by geometric deformation and position deviation caused by the uneven surface of the paper product during the process of capturing spectral image information.

4. The method for reproducing the full appearance of paper cultural relics based on spectral imaging technology according to claim 1, characterized in that: The step of integrating the images at different resolutions to generate an integrated image comprises: Performing weighted averaging on the images at different resolutions to obtain image mean information; Calculating pixel criteria based on the image mean information to obtain criteria information; According to the criterion information, principal component weight fusion is performed to obtain an integrated image; The performing weighted averaging according to the images at different resolutions includes: performing weight processing according to the grayscale values ​​of the images at different resolutions to obtain image mean information.

5. The method for reproducing the full appearance of paper cultural relics based on spectral imaging technology according to claim 1, characterized in that: The step of reconstructing the integrated image to obtain the full appearance image information of the paper cultural relic includes: Comparing the integrated image with the cultural relic to be analyzed to obtain comparison information; Performing a difference elimination process according to the contrast information to obtain image difference elimination information; Based on the image difference elimination information, compensation is performed to obtain the full appearance image information of the cultural relic.

6. A system for reproducing the full appearance of paper cultural relics based on spectral imaging technology, used to implement the method for reproducing the full appearance of paper cultural relics based on spectral imaging technology as described in any one of claims 1 to 5, characterized in that: include: An image acquisition module is used to obtain spectral image information of different parts of the cultural relics to be analyzed; A preprocessing module, used for performing data preprocessing according to the spectral image information to obtain preprocessed image information; An information processing module, used for performing linear combination according to the preprocessed image information to obtain a new spectral image; An information decomposition module, used for performing different levels of decomposition according to the new spectral image to obtain a multi-filter sequence; A fusion processing module, used for performing fusion processing according to the multi-filter sequence to obtain images at different resolutions; An information integration module, used for integrating the images at different resolutions to obtain an integrated image; The information reconstruction module is used to reconstruct the integrated image to obtain the full appearance image information of the paper cultural relic.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for reproducing the full appearance of paper cultural relics based on spectral imaging technology as described in any one of claims 1 to 5.

Images