Image Processing Device

Abstract

To provide an image processing apparatus for detecting difference between regions with high accuracy.SOLUTION: An image processing apparatus according to the present invention includes a control unit for dividing a first region of first drawing data representing an image of one page of first drawing data into a plurality of first partial regions, dividing a second region of second drawing data representing an image of one page of second drawing data into a plurality of second partial regions, extracting respective first feature amounts of the plurality of first partial regions and respective second feature amounts of the plurality of second partial regions, comparing a first distance between any of the first feature amounts and the second feature amount closest to the first feature amount and a second distance between any of the first feature amounts and the second feature amount closest to the first feature amount, selecting at least two or more second feature amounts in order of proximity to any of the first feature amounts, comparing a threshold value with the sum of the distances between the first feature amounts and the selected second feature amounts, and detecting the difference between the first partial regions and the second partial regions based on the result of comparison between the first distance and the second distance and the result of comparison between the sum and the threshold value.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to an image processing device. [Background technology]

[0002] A technique is known in which the similarity between the images of each page of two drawing data to be subjected to difference detection is calculated, a pair of pages for which difference detection is to be performed is identified based on the similarity, and difference detection is performed between the two drawing data for which the pair of pages has been identified. Also known is a technique in which, when an area for which difference detection is to be performed within a page is designated, difference detection is performed between each designated area (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-045564 Summary of the Invention [Problem to be solved by the invention]

[0004] When detecting differences between regions, the similarity between multiple components of each region may be used. The multiple components may be, for example, average pixel values ​​or a histogram of pixel values. However, even when the similarity between the components is high, it may not be possible to accurately detect differences between the regions.

[0005] For example, depending on the similarity calculation method used for difference detection, a high similarity may be calculated, or a low similarity may be calculated. This may result in variations in the accuracy of difference detection. For this reason, there is room for improvement in the detection of differences between regions.

[0006] Therefore, an object of the present invention is to provide an image processing device that detects differences between regions with high accuracy. [Means for solving the problem]

[0007] The image processing device of the present invention has a control unit that executes the following steps: a division process that divides first drawing data into a plurality of first partial regions from a first region representing an image of one page of the first drawing data, and divides second drawing data into a plurality of second partial regions from a second region representing an image of one page of the second drawing data; an extraction process that extracts a first feature value of each of the plurality of first partial regions and a second feature value of each of the plurality of second partial regions; a first comparison process that compares a first distance between any of the first feature values ​​and the second feature value closest to any of the first feature values ​​and a second distance between any of the first feature values ​​and the second feature value next closest to any of the first feature values; a second comparison process that selects at least two of the second feature values ​​in order of closest distance to any of the first feature values ​​and compares the sum of the distances between any of the first feature values ​​and the selected second feature value with a first threshold distance; and a detection process that detects a difference between the first partial region and the second partial region based on a first comparison result of the first distance and the second distance and a second comparison result of the sum of the distances with the first threshold distance.

[0008] In the aforementioned configuration, the first comparison process may compare the first distance with a specific second distance obtained by multiplying the second distance by a predetermined value that shortens the second distance.

[0009] In the above configuration, the second comparison process may compare an average distance based on the sum and the number of selected second features with a second threshold distance, and the detection process may detect the difference between the first partial region and the second partial region based on the first comparison result and a second comparison result between the average distance and the second threshold distance.

[0010] In the above configuration, the detection process may detect the difference between the first partial region and the second partial region based on first feature points possessed by the first partial region, second feature points possessed by the second partial region, and a predetermined feature point matching method using machine learning. [Effects of the Invention]

[0011] According to the present invention, it is possible to detect differences between regions with high accuracy. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is an example of a hardware configuration of an image processing device. [Figure 2] 1 is an example of a functional configuration of an image processing device. [Figure 3] (a) is an example of first medium data, and (b) is an example of second medium data. [Figure 4] 10 is a flowchart illustrating an example of processing executed by a control unit. [Figure 5] (a) is an example of a difference image, and (b) is another example of a difference image. [Figure 6] 10 is a flowchart illustrating an example of a matching process. [Figure 7] (a) is an example of pairing subregions based on the number of features. (b) is an example of pairing subregions based on the distance between features. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0014] First, the hardware configuration of the image processing device 100 will be described with reference to Fig. 1. The image processing device 100 includes a CPU (Central Processing Unit) 100A as a processor, and a RAM (Random Access Memory) 100B and a ROM (Read Only Memory) 100C as memories. The image processing device 100 also includes a network I / F (Interface) 100D and an HDD (Hard Disk Drive) 100E. An SSD (Solid State Drive) may be used instead of the HDD (Hard Disk Drive) 100E.

[0015] The image processing device 100 may include at least one of an input I / F 100F, an output I / F 100G, an input / output I / F 100H, and a drive device 100I, as necessary. The CPU 100A to the drive device 100I are connected to each other via an internal bus 100J. In other words, the image processing device 100 can be realized by a computer.

[0016] An input device 11 is connected to the input I / F 100F. Examples of the input device 11 include a keyboard, a mouse, and a touch panel. A display device 12 is connected to the output I / F 100G. Examples of the display device 12 include an LCD display. A semiconductor memory 13 is connected to the input / output I / F 100H. Examples of the semiconductor memory 13 include a USB (Universal Serial Bus) memory and a flash memory. The input / output I / F 100H reads a predetermined program stored in the semiconductor memory 13. The input I / F 100F and the input / output I / F 100H each include, for example, a USB port. The output I / F 100G includes, for example, a display port.

[0017] A portable recording medium 14 is inserted into the drive device 100I. The portable recording medium 14 may be a removable disk such as a CD (Compact Disc)-ROM or a DVD (Digital Versatile Disc). The drive device 100I reads a predetermined program recorded on the portable recording medium 14. The network I / F 100D includes, for example, a LAN (Local Area Network) port and a communication circuit.

[0018] A predetermined program stored in at least one of ROM 100C, HDD 100E, and semiconductor memory 13 is temporarily stored in RAM 100B by CPU 100A. A predetermined program recorded on portable recording medium 14 is temporarily stored in RAM 100B by CPU 100A. By executing the stored predetermined program, CPU 100A realizes various functions described below and executes various processes described below. The predetermined program may be one that corresponds to the flowchart described below.

[0019] The functional configuration of the image processing device 100 will be described with reference to Figures 2 and 3. Note that Figure 2 shows the main functional parts of the image processing device 100.

[0020] As shown in Fig. 2, the image processing device 100 includes a storage unit 110, a control unit 120, an input unit 130, and an output unit 140. The storage unit 110 can be realized by the RAM 100B or HDD 100E described above. The control unit 120 can be realized by the CPU 100A described above. The input unit 130 can be realized by the input I / F 100F described above. The output unit 140 can be realized by the output I / F 100G described above. Therefore, the storage unit 110, the control unit 120, the input unit 130, and the output unit 140 are connected to one another.

[0021] Here, the storage unit 110 includes a first medium storage unit 111, a second medium storage unit 112, and a display drawing storage unit 113. At least one of the first medium storage unit 111, the second medium storage unit 112, and the display drawing storage unit 113 may be provided in an information processing device (not shown) different from the image processing device 100. In this case, the image processing device 100 may access the information processing device and refer to the stored contents of the first medium storage unit 111, the second medium storage unit 112, etc.

[0022] The first medium storage unit 111 stores first medium data. The first medium data is a data file or an electronic file of an information transmission medium. The information transmission medium includes documents such as reports and instructions. In this embodiment, as shown in FIG. 3(a), the first medium data 50 is a document created with multiple pages, but it may also be a document created with a single page. When the first medium data 50 is a document created with multiple pages, each document includes drawing data 51 and 52. The drawing data 51 and 52 are, for example, blueprints of a finished product or a part. The shapes of the drawing data 51 and 52 are different from each other.

[0023] The second medium storage unit 112 stores the second medium data. Like the first medium data 50, the second medium data is a data file or an electronic file of an information transmission medium. In this embodiment, as shown in FIG. 3(b), the second medium data 60 is also a document created with multiple pages, but it may also be a document created with a single page. The number of pages of the second medium data 60 may be the same as or different from the number of pages of the first medium data 50. When the second medium data 60 is a document created with multiple pages, each document includes drawing data 61, 62. The drawing data 61, 62 include, for example, blueprints of finished products or parts. The shapes of the drawing data 61, 62 are different from each other.

[0024] The above-mentioned first medium data 50 is stored in the first medium storage unit 111 based on an operation on the input device 11. The second medium data 60 is similarly stored in the second medium storage unit 112. In this embodiment, the first medium data 50 represents a comparison source for the second medium data 60, and the second medium data 60 represents a comparison destination or comparison object for the first medium data 50. Therefore, hereinafter, the drawing data 51, 52 will be referred to as base drawings 51, 52 as comparison sources, and the drawing data 61, 62 will be referred to as new drawings 61, 62 as comparison destination or comparison object.

[0025] The display drawing storage unit 113 stores images of drawings to be displayed on the display device 12. As will be described in detail later, the display drawing storage unit 113 stores an image of a drawing in which a base drawing image corresponding to the above-mentioned base drawing 51 is superimposed on a new drawing image corresponding to one of the new drawings 61, 62 corresponding to this base drawing image, and portions corresponding to the differences are expressed in different colors. The display drawing storage unit 113 also stores an image of a drawing in which a base drawing image corresponding to the above-mentioned base drawing 52 is superimposed on a new drawing image corresponding to the other of the new drawings 61, 62 corresponding to this base drawing image, and portions corresponding to the differences are expressed in different colors. The base drawing image is an example of first drawing data, and the new drawing image is an example of second drawing data. Both the base drawing image and the new drawing image are image data.

[0026] Returning to FIG. 2, the control unit 120 includes an image generation unit 121, an image processing unit 122, and a display unit 123.

[0027] The image generation unit 121 acquires the first medium data 50 from the first medium storage unit 111 and images the first medium data 50. That is, the image generation unit 121 generates a first medium image representing the first medium data 50 from the acquired first medium data 50. If the first medium data 50 is a document created with multiple pages, the first medium image also includes multiple page images. The multiple page images included in the first medium image include the base drawing image described above.

[0028] Similarly, the image generation unit 121 acquires the second medium data 60 from the second medium storage unit 112 and images the second medium data 60. That is, the image generation unit 121 generates a second medium image representing the second medium data 60 from the acquired second medium data 60. If the second medium data 60 is a document created with multiple pages, the second medium image also includes multiple page images. The multiple page images included in the second medium image include the new drawing image described above.

[0029] The image processing unit 122 performs various image processes on the first medium image, the second medium image, the base drawing image, and the new drawing image. Details of the image processing unit 122 will be described later, but for example, the image processing unit 122 compares multiple page images included in the first medium image with multiple page images included in the second medium image, and identifies page images that are similar to each other. The image processing unit 122 also divides an area representing a page image into multiple unit partial areas (hereinafter simply referred to as partial areas), and identifies partial areas that correspond to each other based on a known feature point matching method using machine learning.

[0030] For example, as shown in FIG. 3(a), the image processing unit 122 divides an area representing the entire page image included in the first medium image into a plurality of partial areas 71, 72, etc. Furthermore, as shown in FIG. 3(b), the image processing unit 122 divides an area representing the entire page image included in the second medium image into a plurality of partial areas 81, 82, etc. The shape of the partial areas may be rectangular or may be a shape other than rectangular (for example, circular). Furthermore, the number of partial areas corresponding to each other may be the same or different. Additionally, the image processing unit 122 monochromeizes (specifically, monochrome binarizes) each of the base drawing image and the new drawing image, and assigns different colors to each of the base drawing image and the new drawing image.

[0031] As a known feature point matching method, for example, the following documents 1 and 2 can be referred to. Reference 1: PF Alcantarilla, A. Bartoli, and AJ Davison. “KAZE features”, ECCV, (2012), pp.214?227. Reference 2: P. F, Alcantarilla, J. Nuevo, A. Bartoli, “Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces”, BMVC, (2013), pp.13.1-13.11.

[0032] The display unit 123 acquires an image of the drawing stored in the display drawing storage unit 113 and displays the acquired drawing on the display device 12. As described above, the display drawing storage unit 113 stores, for example, an image of the drawing in which parts corresponding to the differences between the base drawing image and the new drawing image are expressed in different colors. Therefore, the display unit 123 acquires and displays this drawing.

[0033] Next, the processing executed by the control unit 120 will be described with reference to FIGS.

[0034] 4, the image generation unit 121 first generates an image of the medium data (step S1). More specifically, the image generation unit 121 acquires the first medium data 50 from the first medium storage unit 111 and generates a first medium image. The image generation unit 121 also acquires the second medium data 60 from the second medium storage unit 112 and generates a second medium image.

[0035] Once the medium data has been imaged, the image processing unit 122 identifies similar pages (step S2). Specifically, the image processing unit 122 compares the multiple page images included in the first medium image with the page images included in the second medium image for each page image, and calculates the similarity between the page images. After calculating the similarity, the image processing unit 122 identifies the page images with the highest calculated similarity as similar pages. This allows similar pages to be uniquely identified. In this embodiment, for example, page images including the characters "FIG. 1" are identified as similar pages (see FIGS. 3(a) and (b)).

[0036] When a similar page is identified, the image processing unit 122 divides one region into partial regions (step S3). That is, the image processing unit 122 divides each of the two page images identified as similar pages into a plurality of partial regions from one region corresponding to the entire page image. After region division, the image processing unit 122 performs a matching process between the two page images identified as similar pages (step S4). The matching process is a process of identifying the correspondence between the partial regions included in one page image and the partial regions included in the other page image using the feature point matching method described above. Details of the matching process will be described later.

[0037] After the matching process is completed, the image processing unit 122 moves one of the partial regions for which a correspondence has been identified to the other, thereby aligning the positions of the base drawing image and the new drawing image (step S5). After aligning the positions of the base drawing image and the new drawing image, the image processing unit 122 converts the base drawing image to monochrome and assigns green color alone (step S6). Green is one of the three primary colors of light, and can be expressed as (R, G, B) = (0, 255, 0) in a color representation of brightness classified into 256 gradations in the RGB format. In the brightness classified into 256 gradations, the numerical data "255" represents the brightest brightness. By the processing of step S6, the base drawing image can be expressed in green.

[0038] When the processing of step S6 is completed, the image processing unit 122 converts the new drawing image to monochrome and assigns red color alone (step S7). Red is one of the three primary colors of light, and can be expressed as (R, G, B) = (255, 0, 0) in RGB color representation. By the processing of step S7, the new drawing image can be expressed in red. Alternatively, green may be assigned to the new drawing image, and red may be assigned to the base drawing image.

[0039] When the processing of step S7 is completed, the image processing unit 122 superimposes the base drawing image and the new drawing image on a blue background (step S8). Blue is one of the three primary colors of light, and can be expressed as (R, G, B) = (0, 0, 255) in RGB color representation. When the base drawing image and the new drawing image are superimposed on a blue background, (R, G, B) = (255, 255, 255) is obtained, and therefore white can be expressed.

[0040] In this way, the portion of the white background that contains only the green base drawing image can be expressed as magenta, including pink, because (R,G,B) = (255,255,255) - (0,255,0) = (255,0,255). Similarly, the portion of the white background that contains only the red new drawing image can be expressed as cyan, including light blue, because (R,G,B) = (255,255,255) - (255,0,0) = (0,255,255). Furthermore, the overlapping portion of the white background containing the green base drawing image and the red new drawing image can be expressed as blue, because (R,G,B) = (255,255,255) - (0,255,0) - (255,0,0) = (0,0,255).

[0041] When the processing of step S8 is completed, the image processing unit 122 stores an image of such a drawing in the display drawing storage unit 113. When the image of the drawing is stored in the display drawing storage unit 113, the display unit 123 displays the image of the drawing on the display device 12 (step S9), and the processing ends. As a result, as shown in Figures 5(a) and (b), the base drawing image and the new drawing image are superimposed, and an image of the drawing that is partially expressed in different colors appears on the display device 12.

[0042] 5(a), the differences between the base drawing image corresponding to the base drawing 51 and the new drawing image corresponding to the new drawing 62 appear on the display device 12 as difference images P1 and P2 of different colors. In this case, the difference image P1, which is part of the base drawing image, is displayed in magenta, and the difference image P2, which is part of the new drawing image, is displayed in cyan. Then, the superimposed image P3, which is the superimposed portion of the base drawing image and the new drawing image, is displayed in blue.

[0043] Furthermore, as shown in FIG. 5(b), the difference between the base drawing image corresponding to the base drawing 52 and the new drawing image corresponding to the new drawing 61 appears on the display device 12 as a difference image Q1 of a different color. In this case, the difference image Q1, which is a part of the base drawing image, is displayed in magenta. However, the new drawing image is superimposed entirely on the base drawing image. Therefore, the new drawing image is displayed as a blended image in blue as a superimposed image Q3.

[0044] In this way, the image processing device 100 according to this embodiment can extract the differences between the base drawing image and the new drawing image based on the color differences using the three primary colors of light. Therefore, the amount of data processing can be reduced compared to when data processing is performed that does not rely on color differences using the three primary colors of light. Furthermore, the image of the drawing displayed on the display device 12 allows, for example, a person in charge of reviewing the old and new drawings to easily distinguish the differences between the drawings.

[0045] Next, the above-mentioned matching process will be described in detail with reference to Figures 6 and 7. As described above, when the process of step S3 is completed, the image processing unit 122 starts the matching process. Note that the order of the processes of steps S12 and S13 described below is not particularly limited, and either step S12 or S13 may be performed first (i.e., the process order may be reversed).

[0046] First, as shown in Fig. 6, the image processing unit 122 extracts features (step S11). More specifically, the image processing unit 122 extracts features of each of a plurality of partial regions in the comparison source as first features and features of each of a plurality of partial regions in the comparison destination as second features. For example, if any of the partial regions in the comparison source has multiple points A, X (e.g., pixels, or local or minute regions including multiple pixels as elements), the image processing unit 122 extracts first features of the points A, X, etc. If any of the partial regions in the comparison destination has multiple points B, C, Y, etc., the image processing unit 122 extracts second features of the points B, C, Y, etc.

[0047] Each of the points A, X, etc. has a plurality of components (for example, lightness, saturation, brightness, average pixel value (or RGB value), variance of pixel values, histogram of pixel values, etc.) as a first feature. Similarly, the points B, C, Y, etc. also have a plurality of components as a second feature. Therefore, the points A and X may be called first feature points, and the points B, C, Y may be called second feature points. For example, the point X has lightness as a component x1, saturation as a component x2, ..., component x n The points A, B, C, and Y are basically the same as the point X, so detailed explanations will be omitted.

[0048] When the processing of step S11 is completed, the image processing unit 122 compares the distances as a first comparison processing (step S12). More specifically, the image processing unit 122 first calculates a first distance between any one of the first feature amounts and a second feature amount that is closest to any one of the first feature amounts. Next, the image processing unit 122 calculates a second distance between any one of the first feature amounts and a second feature amount that is next closest to any one of the first feature amounts. Then, the image processing unit 122 compares the first distance with the second distance.

[0049] For example, the image processing unit 122 calculates the distance L(A,B) between points A and B as the first distance, and calculates the distance L(A,C) between points A and C as the second distance. Here, the image processing unit 122 can calculate, for example, the distance L(X,Y) using the following calculation formula. Similarly, the image processing unit 122 can also calculate the distance L(A,B) and the distance L(A,C) using this calculation formula. Using the distance L(X,Y), the image processing unit 122 can determine the similarity between the feature amount of point X and the feature amount of point Y. Similarly, using the distance L(A,B) and the distance L(A,C), the image processing unit 122 can determine the similarity between the feature amount of point A and the feature amount of point B, or the similarity between the feature amount of point A and the feature amount of point C. <Calculation formula> Distance L(X,Y)={(x1-y1) 2 +(x2-y2) 2 +···+(x n -y n ) 2}} 0.5

[0050] After calculating the distances L(A,B) and L(A,C), the image processing unit 122 uses the number of pairs of elements of the partial regions that have unique feature amounts (hereinafter referred to as element pairs) to select partial region candidates (hereinafter referred to as pairing candidates) for which a correspondence relationship is to be identified (paired). Specifically, the image processing unit 122 selects partial regions that have the largest number of point pairs in which the feature amounts of points within the partial regions match as pairing candidates. The image processing unit 122 determines that the feature amounts match when the distance L between two points is the smallest compared to the distance L between other two points.

[0051] An element pair having a unique feature is required to satisfy the following inequality, which compares, for example, the distance L(A,B) between point A and point B, which is the shortest distance and a candidate pair for point A, with the distance L(A,C) between point A and point C, which is the next shortest distance from point B and a candidate pair for point A. If the distance L(A,B) between point A in the source partial area and point B in the target partial area is the shortest, the feature values ​​of points A and B are very similar. Therefore, the image processing unit 122 can determine that the feature values ​​match. The predetermined value can be set as a threshold to a positive number less than 1.0, such as 0.5 or 0.6, which shortens the second distance. <Inequalities> Distance L(A,B)<predetermined value x distance L(A,C)

[0052] As a result, as shown in FIG. 7(a), the image processing unit 122 can select pairing candidates for a plurality of corresponding partial areas (referred to as areas in FIG. 7(a)) #1 to #5. For example, the partial area candidates corresponding to partial area #3 of the base drawing image are partial area #2 and partial area #3 of the new drawing image. Here, the number of point pairs in which the feature amounts of points in partial area #3 of the base drawing image and points in partial area #2 of the new drawing image match is 80. On the other hand, the number of point pairs in which the feature amounts of points in partial area #3 of the base drawing image and points in partial area #3 of the new drawing image match is 40. Therefore, the image processing unit 122 determines partial area #3 of the base drawing image and partial area #2 of the new drawing image, which have the larger number of point pairs, as partial area pairing candidates.

[0053] After completing the process of step S12, the image processing unit 122 performs a second comparison process by comparing the total distance with a threshold distance (step S13). For example, the image processing unit 122 selects several to a dozen point pairs (for example, at least two or more, such as five, ten, or fifteen) in ascending order of distance L, and compares the total distance, which is the sum of the distances L of the selected point pairs, with the first threshold distance. Then, the image processing unit 122 selects a pairing candidate if the total distance is less than the first threshold distance. The first threshold distance is set to a value in the hundreds, such as a threshold distance of 300 or 500.

[0054] On the other hand, the image processing unit 122 may select pairing candidates when the average distance obtained by dividing the sum of the distances L of the selected point pairs by the number of the selected point pairs is less than the second threshold distance. Here, if several tens of numerical values ​​such as a threshold distance of "30" or a threshold distance of "50" are set as the second threshold distance, the image processing unit 122 can select pairing candidates of corresponding multiple partial areas (described as areas in FIG. 7(b)) #1 to #5, as shown in FIG. 7(b). For example, the partial area candidates corresponding to partial area #3 of the base drawing image are partial area candidates #2 and #3 of the new drawing image.

[0055] Here, the average distance L between a point in partial area #3 of the base drawing image and a point in partial area #2 of the new drawing image is "10." On the other hand, the average distance L between a point in partial area #3 of the base drawing image and a point in partial area #3 of the new drawing image is "13." Therefore, the image processing unit 122 determines partial area #3 of the base drawing image and partial area #2 of the new drawing image, which have a short average distance L, as partial area pairing candidates. In this way, in the second comparison process, the image processing unit 122 determines partial area pairing candidates that identify a correspondence relationship using the shortness of the distance between the feature amounts of the elements of the partial areas.

[0056] When the process of step S13 is completed, the image processing unit 122 detects the difference between the partial regions (step S14) and ends the matching process. More specifically, the image processing unit 122 finally determines a pair of a comparison source partial region and a comparison target partial region based on each pairing candidate determined in the processes of steps S12 and S13, and detects the difference between the partial regions. Therefore, as shown in Figures 7(a) and 7(b), the image processing unit 122 pairs, for example, partial region #1 of the base drawing image with partial region #1 of the new drawing image as partial regions having a corresponding relationship.

[0057] As shown in FIG. 7(a), the image processing unit 122 selects the partial region #5 of the base drawing image and the partial region #5 of the new drawing image as pairing candidates. However, as shown in FIG. 7(b), the image processing unit 122 excludes the partial region #5 of the base drawing image and the partial region #5 of the new drawing image from the selection of pairing candidates. This is because the average distance L between the partial region #5 of the base drawing image and the partial region #5 of the new drawing image exceeds the second threshold distance. In this case, the image processing unit 122 may determine that the partial region #5 has been deleted from the base drawing image and added to the new drawing image. In this way, the image processing unit 122 can detect the difference between the partial regions in the base drawing image and the partial regions in the new drawing image based on each pairing candidate, which is the comparison result determined in each process of steps S12 and S13.

[0058] As described above, the image processing unit 122 pairs partial regions with each other and accurately detects differences between the partial regions through a matching process including the first comparison process and the second comparison process. Note that although partial regions of drawings have been described as an example, the image processing unit 122 may also identify partial regions of characters in the same way as drawings and identify correspondences between them.

[0059] As described above, the image processing device 100 according to this embodiment includes a control unit 120, and the control unit 120 includes an image processing unit 122. In the process of step S3, the image processing unit 122 performs a division process to divide each of the two page images identified as similar pages into a plurality of partial regions from one region corresponding to the entire page image. Next, in the process of step S11, the image processing unit 122 performs an extraction process to extract the feature amount of each of the plurality of partial regions of the comparison source and the feature amount of each of the plurality of partial regions of the comparison target as first feature amounts and second feature amounts, respectively.

[0060] Then, in step S12, the image processing unit 122 performs a first comparison process to compare the first distance with the second distance. The first distance is the distance between any one of the first feature amounts and a second feature amount that is closest to any one of the first feature amounts. The second distance is the distance between any one of the first feature amounts and a second feature amount that is next closest to any one of the first feature amounts.

[0061] In step S13, the image processing unit 122 selects at least two or more second feature amounts in descending order of distance to any one of the first feature amounts. After selecting the second feature amounts, the image processing unit 122 executes a second comparison process in which the sum of the distances between any one of the first feature amounts and the selected second feature amount is compared with a first threshold distance. Alternatively, the image processing unit 122 executes a second comparison process in which the average distance based on the sum of the distances and the number of selected second feature amounts is compared with a second threshold distance.

[0062] Then, in the process of step S14, the image processing unit 122 executes a detection process to detect the difference between the partial regions based on the first comparison result of the first distance and the second distance and the second comparison result of the distance sum and the first threshold distance. Alternatively, the image processing unit 122 executes a detection process to detect the difference between the partial regions based on the first comparison result and the second comparison result of the average distance and the second threshold distance. These processes enable the detection of the difference between the partial regions to be performed with high accuracy.

[0063] Although the preferred embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and variations are possible within the scope of the gist of the present invention as set forth in the claims. [Explanation of symbols]

[0064] 50 First Media Data 51,52 Base drawing 60 Second Media Data 61,62 New drawings 71,72,81,82 partial area 100 Image processing device 120 control section

Claims

1. a division process for dividing the first drawing data into a plurality of first partial regions from a first region representing an image of one page of the first drawing data, and dividing the second drawing data into a plurality of second partial regions from a second region representing an image of one page of the second drawing data; an extraction process of extracting a first feature amount of each of the plurality of first partial regions and a second feature amount of each of the plurality of second partial regions; a first comparison process of comparing a first distance between any one of the first feature amounts and the second feature amount closest to any one of the first feature amounts with a second distance between any one of the first feature amounts and the second feature amount next closest to any one of the first feature amounts; a second comparison process of selecting at least two of the second feature amounts in order of decreasing distance from any one of the first feature amounts, and comparing a sum of the distances between any one of the first feature amounts and the selected second feature amounts with a first threshold distance; a detection process for detecting a difference between the first partial area and the second partial area based on a first comparison result between the first distance and the second distance and a second comparison result between the sum and the first threshold distance; An image processing device having a control unit that executes the above.

2. the first comparison process compares the first distance with a specific second distance obtained by multiplying the second distance by a predetermined value that shortens the second distance; 2. The image processing device according to claim 1, wherein:

3. the second comparison process compares an average distance based on the sum and the number of selected second feature amounts with a second threshold distance; the detection process detects the difference between the first partial region and the second partial region based on the first comparison result and a second comparison result between the average distance and the second threshold distance.

3. The image processing device according to claim 1, wherein the image processing device is a computer.

4. the detection process detects the difference between the first partial region and the second partial region based on first feature points of the first partial region, second feature points of the second partial region, and a predetermined feature point matching method using machine learning; 3. The image processing device according to claim 1, wherein the image processing device is a computer.

Images