Parchment paper base drawing archive digitization method based on panoramic image position synthesis technology

Abstract

The invention discloses a parchment paper base map file digitalization method based on a panoramic image position synthesis technology, and relates to the technical field of parchment paper base map file digitalization management. Comprising the following steps: S1, dividing a vegetable parchment base map file into a plurality of sampling points for continuous image sampling, and capturing point information under different exposure conditions; s2, performing image recombination on the point position information by utilizing a panoramic image position synthesis technology to obtain a two-dimensional plane image of the vegetable parchment base map file; and S3, performing digital image processing on the two-dimensional plane image of the vegetable parchment base map file to obtain a high-definition digital vegetable parchment base map file. The problem that high resolution, high reduction degree and high utilization rate cannot be achieved through a traditional vegetable parchment base drawing file digitalization technology is solved.

Description

Technical Field

[0001] This application relates to the field of digital management technology for tracing paper base map archives, and in particular to a method for digitizing tracing paper base map archives based on panoramic image synthesis technology. Background Technology

[0002] The digitization of traditional blueprint archives typically involves scanning. However, blueprint archives made of tracing paper are often old, with the paper becoming brittle and soft, or several pages pasted together. Digitizing these archives with a scanner often results in scanned images that do not meet the required pixel count and clarity, making a significant portion of the digitized blueprint information unreadable. This limits the digitization process for blueprint archives. The traditional scanning method for digitizing blueprint archives has many shortcomings and problems, necessitating the exploration of more effective methods for the digitization and management of these archives to improve the overall management level of paper blueprint archives. Summary of the Invention

[0003] The purpose of this application is to provide a method for digitizing tracing paper base maps based on panoramic image synthesis technology, in order to solve the problem that traditional tracing paper base map digitization technology cannot achieve high resolution, high fidelity, and high utilization.

[0004] To achieve the above objectives, this application adopts the following technical solution:

[0005] On the one hand, this application provides a method for digitizing tracing paper base maps based on panoramic image-level synthesis technology, including:

[0006] S1. Divide the tracing paper base image file into multiple sampling points for continuous image sampling to capture point information under different exposure conditions;

[0007] S2. Using panoramic image synthesis technology, the information of each point is reconstructed to obtain a two-dimensional planar image of the tracing paper base map archive;

[0008] S3. Perform digital image processing on the two-dimensional planar image of the tracing paper base file to obtain a high-definition digital tracing paper base file.

[0009] On the other hand, this application also provides a digitization device for tracing sulfuric acid paper base maps based on panoramic image-level synthesis technology, comprising:

[0010] The image sampling module is used to divide the tracing paper background file into multiple sampling points for continuous image sampling, capturing point information under different exposure conditions;

[0011] The image synthesis module is used to reconstruct images from various points using panoramic image synthesis technology to obtain a two-dimensional planar image of the tracing paper base map archive.

[0012] The digitization module is used to perform digital image processing on the two-dimensional planar image of the tracing paper base map archive to obtain a high-definition digitized tracing paper base map archive.

[0013] Based on the above technical solution, this application can achieve the following technical effects:

[0014] The digitization of tracing paper blueprints is achieved using panoramic image-level compositing technology. This involves continuous image sampling of the tracing paper blueprints, capturing point information under different conditions, calculating the optimal image features for each point, and then using panoramic image-level compositing technology to reconstruct the images. After digital image processing, the digitization of the tracing paper blueprints is completed. Compared to traditional image scanning, the digitized images produced using panoramic image-level compositing technology are clearer and brighter overall, with more complete and realistic details, and can be stored in a computerized archive management system platform. This solution is characterized by low cost, small memory footprint, and high reliability, making the storage, retrieval, processing, and access of historical tracing paper blueprints more convenient, fully realizing the value of the archives, and simultaneously protecting the original tracing paper blueprints in storage. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a method for digitizing tracing paper base maps based on panoramic image-to-image synthesis technology, provided in one embodiment of this application.

[0016] Figure 2 This is a sampled original image of the A0 sulfuric acid paper background file provided in one embodiment of this application;

[0017] Figure 3 This is a schematic diagram of a sulfuric acid paper background image sampling provided in an embodiment of this application;

[0018] Figure 4 This is a schematic diagram of high dynamic range photosynthesis of A0 sulfuric acid paper background file provided in one embodiment of this application;

[0019] Figure 5 This is a schematic diagram of SIFT feature point matching and synthesis of an A0 sulfuric acid paper background image file provided in an embodiment of this application;

[0020] Figure 6 This is a schematic diagram illustrating the inverse calculation of the homography matrix of an A0 sulfite paper background image file provided in one embodiment of this application;

[0021] Figure 7 This is a schematic diagram of the A0 sulfuric acid paper background image before white point restoration, provided in an embodiment of this application;

[0022] Figure 8This is a schematic diagram of the digitized A0 sulfuric acid paper background file provided in one embodiment of this application.

[0023] Figure 9 This is a flowchart of the process for digitizing sulfuric acid paper base map archives based on panoramic image synthesis technology, provided in one embodiment of this application. Detailed Implementation

[0024] The present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present application will become clearer from the following description and claims. It should be noted that the drawings are all in a very simplified form and are not to scale, and are only used to facilitate and clarify the illustration of the embodiments of the present application.

[0025] It should be noted that, in order to clearly illustrate the content of this application, several embodiments are provided to further explain the different implementations of this application. These embodiments are enumerated rather than exhaustive. Furthermore, for the sake of brevity, content mentioned in the preceding embodiments is often omitted in the following embodiments. Therefore, content not mentioned in the later embodiments can be referred to in the preceding embodiments.

[0026] Example 1

[0027] like Figure 1 The diagram shown is a flowchart illustrating a method for digitizing tracing paper base maps based on panoramic image-level synthesis technology provided in this embodiment. Figure 9 The diagram shown illustrates the workflow for digitizing tracing paper base maps using panoramic image synthesis technology, as provided in this embodiment. The method specifically includes the following steps:

[0028] S1. Divide the tracing paper base image file into multiple sampling points for continuous image sampling to capture point information under different exposure conditions;

[0029] In one embodiment, S1 includes:

[0030] Continuous image sampling of tracing paper base maps was performed using a flat light source and a macro lens.

[0031] In one embodiment, prior to continuously sampling images of the tracing paper underlay archive using a flat light source and a macro lens, the method further includes:

[0032] A backlighting method is used to ensure that the color temperature of the flat light source is constant and the same as that of the image acquisition device, and the tracing paper base image file is fixed at a certain distance from the flat light source.

[0033] In one embodiment, S1 includes:

[0034] Using the 0-level exposure of the calibrated image acquisition device as the anchor point, the tracing paper base map file was sampled sequentially at 0, 1, and -0.5 exposure levels by controlling the exposure time, thus obtaining the different drawing point information of the tracing paper base map file under the three exposure conditions.

[0035] In one embodiment, S1 involves dividing the tracing paper background file into multiple sampling points for continuous image sampling, including:

[0036] The overlap interval of each sampling point is kept small, while ensuring that the overlap interval of each sampling point guarantees a certain amount of SIFT matching feature point information.

[0037] In one specific embodiment, taking an A0 tracing paper base image file as an example, the A0 paper size is 841mm*1189mm. First, continuous image sampling of the tracing paper base image file is performed. To avoid the significant impact of lens distortion on the final sampling results, a 50mm equivalent focal length is used for the tracing paper base image file during the experiment. Figure 2 The image acquisition process for the A0 tracing paper base image file was conducted through repeated experiments. The original tracing paper base image file was divided into six sampling points, resulting in minimal overlap between sampling points while maintaining sufficient SIFT matching feature point information. The tracing paper base image file uses tracing paper, which has good light transmittance but poor ink adhesion and is fragile. To address these characteristics, a backlighting method was specifically adopted during image acquisition. A flat light source with a constant color temperature of 5500K was used, matching the color temperature setting of the image acquisition device, and a brightness greater than or equal to 25000 LUX. The base image file was fixed 0.2-0.5m from the flat light source. With all parameters of the image acquisition device locked, the 0-level exposure of the image acquisition device was calibrated as the anchor point. Exposure sampling was performed sequentially at 0, 1, and -0.5 levels by controlling the exposure time, obtaining different optical sampling information of the tracing paper base image under these three exposure conditions. The image sampling diagram of the tracing paper base image file is shown below. Figure 3 As shown.

[0038] S2. Using panoramic image synthesis technology, the information of each point is reconstructed to obtain a two-dimensional planar image of the tracing paper base map archive;

[0039] In one embodiment, S2 includes:

[0040] S21. Use SIFT matching feature point information to obtain the matching correspondence of pixels in the overlapping interval of sampling points, construct a coordinate transformation model between images to register overlapping areas, and unify the image coordinate system.

[0041] S22. In the unified image coordinate system, perform feature point rectangle fitting on the image of each point to obtain a complete image of the tracing paper base map archive;

[0042] S23. The complete image of the sulfuric acid paper base map is transformed and projected onto a two-dimensional plane using a spherical projection method;

[0043] S24. Based on the homography matrix principle, the two-dimensional planar image of the tracing paper background file is obtained by using inverse image transformation and image interpolation techniques.

[0044] In one embodiment, prior to S21, the method further includes:

[0045] The brightness difference of each point under different exposure conditions is used to solve the weighting problem, and high dynamic range light synthesis is performed on the information of each point through alternating exposure.

[0046] In one specific embodiment, after sampling the image of the tracing paper background, the brightness difference between different exposure information of each point is used to solve for weights, and high dynamic range light synthesis is performed on the image of each point through alternating cyclic exposure (e.g., Figure 4 A0 sulfuric acid paper base image archive (high dynamic range photosynthesis) is used to increase the information factors of the dot matrix image such as contrast, thereby presenting a clearer brightness level and providing more valuable data information for subsequent matching and synthesis work.

[0047] During the sampling process at each sampling point, images are inevitably acquired from different viewpoints and perspectives. Therefore, it is necessary to utilize SIFT feature points to find the matching correspondence of pixels in overlapping image regions, construct a coordinate transformation model between images, accurately register overlapping areas, and unify the image coordinate system. Within this coordinate system, feature point rectangle fitting is performed on each synthesized raster image to obtain the complete image of the sampled object, such as... Figure 5 As shown. Based on synthetic sampling, a projection transformation is obtained in the overlapping region according to registration, and a similarity transformation is used in the non-overlapping region. A transformation model for transition is calculated in the boundary region between the two transformations. The projection parameter vector field is obtained based on the homography matrix principle, and the spatial transformation parameters of the region are obtained. The actual scene is projected onto a two-dimensional plane through perspective transformation using spherical projection. The transformation matrix is ​​then used with inverse image transformation and image interpolation techniques to estimate the spatial mapping relationship between images, and the two-dimensional plane image is obtained by inverse calculation.

[0048] By using panoramic image-level technology for synthesis, one can obtain, for example... Figure 6 The high-precision digital base map archive shown provides ample raw data support for subsequent image information enhancement.

[0049] S3. Perform digital image processing on the two-dimensional planar image of the tracing paper base file to obtain a high-definition digital tracing paper base file.

[0050] In one embodiment, S3 includes:

[0051] Histograms of two-dimensional planar images of tracing paper base maps are analyzed. By utilizing the density jump relationship between uniform grayscale regions in the low-frequency and high-frequency parts of the image, a high-pass filtering method in the spectral domain is used to enhance the high-frequency spatial part and suppress the low-frequency part for sharpening, thus obtaining high-definition digital tracing paper base maps.

[0052] In one specific embodiment, by analyzing the image histogram and utilizing the density jump relationship between uniform grayscale regions in the low-frequency and high-frequency parts of the image, a high-pass filtering method in the spectral domain is used to allow the high-frequency parts of the image to pass smoothly, enhancing the spatial high-frequency components and suppressing the low-frequency components to achieve sharpening. This makes the contour edges of the image clearer, while further reducing the contrast difference in the bright areas of the image, thereby completing white point restoration and obtaining a high-definition digital tracing paper base image archive, such as... Figure 7 and Figure 8 As shown.

[0053] In summary, this method employs panoramic image-level synthesis technology to digitize tracing paper base maps. By continuously sampling images of the tracing paper base maps, it captures point information under different conditions, calculates the optimal image features for each point, and uses panoramic image-level synthesis technology to reconstruct the images. Through digital image processing, the digitization of the tracing paper base maps is achieved. Compared to traditional image scanning, the digitized images produced using panoramic image-level synthesis technology are clearer and brighter overall, with more complete and realistic details, and can be stored in a computer archive management system platform. This solution is characterized by low cost, small memory footprint, and high reliability, making the storage, retrieval, processing, and access of historical tracing paper base maps more convenient, fully realizing the inherent value of the archives, and simultaneously protecting the original tracing paper base maps in storage.

[0054] Example 2

[0055] This embodiment provides a device for digitizing tracing archives based on panoramic image-to-image synthesis technology on tracing paper. The device includes:

[0056] The image sampling module is used to divide the tracing paper background file into multiple sampling points for continuous image sampling, capturing point information under different exposure conditions;

[0057] The image synthesis module is used to reconstruct images from various points using panoramic image synthesis technology to obtain a two-dimensional planar image of the tracing paper base map archive.

[0058] The digitization module is used to perform digital image processing on the two-dimensional planar image of the tracing paper base map archive to obtain a high-definition digitized tracing paper base map archive.

[0059] In summary, this device employs panoramic image-level synthesis technology to digitize tracing paper blueprint archives. By continuously sampling images of the tracing paper blueprint archives, it captures the point information of the drawings under different conditions, calculates the optimal image features for different point information, and uses panoramic image-level synthesis technology to reconstruct the images of each point information. Through digital image processing, the digitization of the tracing paper blueprint archives is achieved. Compared to traditional image scanning, the digitized images produced using panoramic image-level synthesis technology are clearer and brighter overall, with more complete and realistic details, and can be stored in a computer archive management system platform. This solution features low cost, small memory footprint, and high reliability, making the storage, retrieval, processing, and access of historical tracing paper blueprint archives more convenient, fully realizing the inherent value of the archives, and simultaneously protecting the original tracing paper blueprint archives in storage.

[0060] Example 3

[0061] In another feasible embodiment, this embodiment provides a device for digitizing tracing paper base maps based on panoramic image-to-image synthesis technology, the device specifically including:

[0062] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the steps as described in any of the above method embodiments.

[0063] Example 4

[0064] In another feasible embodiment, this embodiment provides a storage medium for digitizing tracing paper base maps based on panoramic image-to-image synthesis technology, wherein the storage medium may specifically include:

[0065] The storage medium stores a processing program for digitizing tracing paper base maps based on panoramic image bit synthesis technology. When the processing program for digitizing tracing paper base maps based on panoramic image bit synthesis technology is executed by a processor, it implements the steps as described in any of the above method embodiments.

[0066] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for digitizing tracing paper base maps based on panoramic image-level synthesis technology, characterized in that, include: S1. Divide the tracing paper base image file into multiple sampling points for continuous image sampling to capture point information under different exposure conditions; S2. Using panoramic image synthesis technology, the information of each point is reconstructed to obtain a two-dimensional planar image of the tracing paper base map archive; S3. Perform digital image processing on the two-dimensional planar image of the tracing paper base file to obtain a high-definition digital tracing paper base file.

2. The method according to claim 1, characterized in that, S1 includes: Continuous image sampling of tracing paper base maps was performed using a flat light source and a macro lens.

3. The method according to claim 2, characterized in that, Before continuously sampling images of the tracing paper underlay archive using a flat light source and a macro lens, the method further includes: A backlighting method is used to ensure that the color temperature of the flat light source is constant and the same as that of the image acquisition device, and the tracing paper base image file is fixed at a certain distance from the flat light source.

4. The method according to claim 3, characterized in that, S1 includes: Using the 0-level exposure of the calibrated image acquisition device as the anchor point, the tracing paper base map file was sampled sequentially at 0, 1, and -0.5 exposure levels by controlling the exposure time, thus obtaining the different drawing point information of the tracing paper base map file under the three exposure conditions.

5. The method according to claim 1, characterized in that, In step S1, the tracing paper background file is divided into multiple sampling points for continuous image sampling, including: The overlap interval of each sampling point is kept small, while ensuring that the overlap interval of each sampling point guarantees a certain amount of SIFT matching feature point information.

6. The method according to claim 5, characterized in that, S2 includes: S21. Use SIFT matching feature point information to obtain the matching correspondence of pixels in the overlapping interval of sampling points, construct a coordinate transformation model between images to register overlapping areas, and unify the image coordinate system. S22. In the unified image coordinate system, perform feature point rectangle fitting on the image of each point to obtain a complete image of the tracing paper base map file; S23. The complete image of the sulfuric acid paper base map is transformed and projected onto a two-dimensional plane using a spherical projection method; S24. Based on the homography matrix principle, the two-dimensional planar image of the tracing paper background file is obtained by using image inverse transformation and image interpolation techniques.

7. The method according to claim 6, characterized in that, Before S21, it also includes: The brightness difference of each point under different exposure conditions is used to solve the weighting problem, and high dynamic range light synthesis is performed on the information of each point through alternating exposure.

8. The method according to claim 1, characterized in that, S3 includes: Histograms of two-dimensional planar images of tracing paper base maps are analyzed. By utilizing the density jump relationship between uniform grayscale regions in the low-frequency and high-frequency parts of the image, a high-pass filtering method in the spectral domain is used to enhance the high-frequency spatial part and suppress the low-frequency part for sharpening, thus obtaining high-definition digital tracing paper base maps.

9. A device for digitizing tracing archives based on panoramic image-to-image synthesis technology on tracing paper, characterized in that, include: The image sampling module is used to divide the tracing paper base file into multiple sampling points for continuous image sampling, capturing point information under different exposure conditions; The image synthesis module is used to reconstruct images from various points using panoramic image synthesis technology to obtain a two-dimensional planar image of the tracing paper base map archive. The digitization module is used to perform digital image processing on the two-dimensional planar image of the tracing paper base file to obtain a high-definition digitized tracing paper base file.

10. An electronic device, characterized in that, include: processor; And a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 8.

Images