TW201037631A - System and method for comparing images - Google Patents

Abstract

The present invention provides a system for comparing images. The system extracts skeletons of a first black and white image and a second black and white image, and thickens the first black and white image and the second black and white image. The system further compares the skeleton of the first black and white image with the thickened second black and white image, and compares the skeleton of the second black and white image with the thickened first black and white image, so as to obtain differences between the two black and white images. A related method is also disclosed.

Description

201037631 VI. Description of the Invention: [Technical Field of the Invention] [0001] The present invention relates to a system and method for image difference comparison between images. C prior art 3

[Reward to the secret time _, the simplest (9) branch Wei (four) image of each pixel value, find the area of the pixel value is different... In general, this method can only accurately compare the difference in pixel value, not _ For most practical image rhymes. When the target (four) in the two _ images is compared, the shape feature of the image can be extracted, and two image images are determined according to the shape feature. The methods for transferring the transition phase are Fourier transform and invariant moment. However, the amount of computation for extracting shape features tends to be relatively large, which is difficult to achieve when the computational power is insufficient, and the effect of fuzzy recognition of the target object is not ideal. [0003] The deviation is the same as the conventional image comparison method. In addition, when comparing an original image and a scanned image generated by scanning the original image less, due to the bug during scanning There are various reasons for scanner quality problems, which may cause some error points in the scanned image or when comparing, the possible comparison result is that the two images are not - again, and such a result may lead to the user's wrong judgment. . For example, the user needs to compare the original file of the contract with the scanned file after the contract is printed. If the scanning file has some error points due to the scanner problem, the traditional image comparison method will be used to obtain the two. The images are inconsistent, so the user may mistakenly believe that the contract has been tampered with. SUMMARY OF THE INVENTION 0S8III932 | Single Number A0101 Page 3 of 33 201037631 [0004] In view of the above, it is necessary to provide an image comparison system and method for comparing images by contour thickening and extracting the backbone. It does not erroneously determine that the compared image is inconsistent due to some error in the image. [0005] An image comparison system* running in a computer is used to compare differences in target objects in an image. The system includes: a backbone extraction module for extracting the backbone of the target object in the black and white image A2 to obtain the backbone image A3 'and extracting the backbone of the target object in the black and white image B2 to obtain the backbone®_3 profile bold module, For thickening the outer rim of the target object in the black and white image A2 to obtain the bold image A4, and thickening the outer contour of the target object in the black and white image B2 to obtain the bold image B4; image coverage a module for overlaying the bold image A4 on the backbone image B3, generating the overlay image $AB1 ' to obtain a portion of the black and white image B2 relative to the black and white image A2' and overlaying the bold image B4 On the backbone image A3, a cover image core 2 is generated to obtain a portion in which the black-and-white image B2 is smaller than the black-and-white image A2; and a result output module is used to output a comparison result of the black-and-white images A2 and B2. [0006] An image comparison method for comparing differences in target objects in two images. The method comprises the steps of: extracting the backbone of the target object in the black and white image B2 to obtain the backbone image B3; thickening the outer contour of the target object in the black and white image A2 to obtain the bold image A4; and the bold image A4 Covering the backbone image B3, generating the overlay image AB1 to obtain a portion of the black-and-white image B2 that is more than the black-and-white image A2; extracting the backbone of the target object in the black-and-white image A2 to obtain the backbone image A3; The outer contour of the target object in image B2 is bolded 'to obtain a bold image B4; the bold image B4 is overlaid on the backbone image A3' to generate an overlay image AB2 to obtain a black and white image B2 relative to 098111932 & Single bat number A0101 Page 4 / Total 33 page 0992019744-0 201037631 [0007] [0008] 0009 [0010] The portion of the black and white image A2 is less; and the output is compared with the black and white image A2 and B2 . Compared to the prior art, the present invention is easy to implement, and it is possible to prepare to compare the difference of the target object in the image without erroneously judging the compared image inconsistency due to some error on the image. [Embodiment] Referring to Figure 1, there is shown a functional block diagram of a preferred embodiment of the image comparison system 1 of the present invention. The image comparison system 1 operates in a computer. The image comparison system 1 includes an image conversion module 10, a backbone extraction module 11, a contour thickening module 12, an image overlay module 13, and a result output module 14. The image conversion module 10 is configured to convert a color image to be compared into a black and white image to segment the target object. Black and white images are also called binary images. The image contains only two shades of black and white, with no intermediate transitions. The pixel value of a black and white image is usually 0 or 1, 0 for black and 1 for white. For convenience of explanation, the pixel value representing the target object in the black and white image is referred to as the target object pixel value, and the color of the target object in the black and white image is referred to as the foreground color, and the background color is referred to as the background color. See Figure 4 for a schematic representation of a black and white image. In the black and white image, the white portion is the target object and the black portion is the background. It should be understood that in other black and white images, it is also possible that the black portion is the target object and the white portion is the background color. In detail, in the present embodiment, for the color images A and B, the image conversion module 100 first converts A and B into grayscale images A1 and B1, respectively, using a conversion algorithm, and then grayscale images. A1 and B1 are binarized and converted into black and white images A2 and B2, respectively. Grayscale image refers to each pixel value Form No. A〇i〇i U98I11932 Page 5 of 33 The information of 201037631 is described by a quantized gray value, and the gray value is usually an integer. For example, an 8-bit grayscale image has 256 shades of gray, and the grayscale value ranges from 0 to 255. That is, an integer of 0-255 is used to describe different levels of gray from black to white, 〇 for black and 255 for white. The conversion algorithm for converting a color image into a grayscale image can be:

Gray = (R*〇.3 + G*.059 + B*0.11). [0014] [0014] The binarization process is to set a threshold value, the pixel value whose gray value is greater than or equal to the threshold value is taken as 1, and the pixel value whose gray value is smaller than the threshold value is 〇 . The binarization of grayscale images can have different binarization algorithms depending on the target object in the image. At present, the main binarization algorithms are global threshold method, local threshold method and dynamic threshold method. The simplest of these is the global threshold method, where the entire image is image binarized with a single threshold, such as setting the threshold to a median of 127 of 〇-255. It should be understood that if the image to be compared is originally a black and white image, the image conversion module may not be needed. The backbone extraction module 11 is configured to extract the backbone of the target object from the black and white image "OR" to obtain the backbone image "or B3. Hereinafter, the backbone of the target object in the black and white image A2 is extracted as an example to describe the backbone. The extraction module 11 extracts the target object backbone. In the embodiment, the backbone extraction module n extracts the pixel value of each point in a row or column for the black and white image A2, for any row (or column), If there are a plurality of consecutive target object pixel values in the row (or column), the plurality of consecutive target object pixel values are represented by the -target object pixel values. For example, in the middle of the plurality of consecutive target object pixel values A 098111932 Form No. A0101 Page 6 / Total 33 Page 0992019744-0 201037631 Pixel values to Table-1 No multiple consecutive target object pixel values. That is to say 'extracted eyes;;!;* The width is 1. For example, suppose the black and white picture: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , 1,111, hey, 〇, 1, after extracting the image backbone, the prime value is 0, L 〇, 〇, 〇, 0, 0, 1, 0, 0, 0, 0, and Figure 5 shows the black and white picture in Figure 4. The image of the skeleton obtained after the target object is extracted from the backbone. _The wheel |jj bold module 12 is used to bold the black and white image 八 or the outer wheel of the financial object to get the bold image A4 Or B4. Referring to Fig. 6 (A) and Fig. 6 (B), respectively, a black and white image and a schematic circle of a bold image generated after the outer contour of the target object in the black and white image is thickened. Please refer to FIG. 2 for the sub-function module diagram of the outline thickening module 12. [0016] The image overlay module 13 is used to overlay the bold image A4 on the backbone image B3 to generate an overlay image. Like AB1, $ gets the part of the backbone image B3 relative to the bold image A4, and puts the bold image 3 4 on the backbone image..., Q generates the overlay image AB2 to get the bold image A portion of B4 that is less than the backbone image A3. The portion of the backbone image B3 that is larger than the bold image A4, that is, the portion of the target object of the black-and-white image B 2 that is larger than the target object of the black-and-white image a 2 , And bold picture B4 with respect to a small part of the backbone of the image of the person 3 i.e. less black and white image of the target object than a monochrome image B2 'portion of the target object knife. See Figure 3 for the sub-function module diagram of the image overlay module 13. [0017] The result output module 14 described in 0981II932 is configured to generate and output a comparison result of the black and white images A2 and B2 according to the processing result of the image overlay module 〖3, and the comparison result is nickname AGIGi 苐7 1/ A total of 33 pages 0982019744-0 201037631 The results are black and white images A2 and B2 are either inconsistent or inconsistent. Further, when the comparison results of the black and white images A2 and B2 are inconsistent, the result wheeling module 14 also colors the portion of the black and white image B2 that is larger than the black and white image A2 on the black and white image B2. And/or the portion where the black-and-white image B2 is smaller than the black-and-white image A2 is color-coded on the black-and-white image A2, and the black-and-white images A2 and B2 after the above-mentioned labeling are displayed. That is, when the target object of the black-and-white image B2 has a portion larger than the target object of the black-and-white image A2, or when the target object of the black-and-white image B2 has a smaller portion than the target object of the black-and-white image A2 The comparison result is that the black and white images A2 and B2 are inconsistent; otherwise, the comparison result is black and white images A2 and B2. [0019] Referring to FIG. 2, a sub-function module diagram of the outline thickening module 12 in FIG. 1 is shown. The outline thickening module 12 includes a setting sub-module 12〇, a first image acquiring sub-module 121, a coordinate value reading sub-module 122, a first pixel value reading sub-module 123, and a first judging sub-module. The group 124, the point acquisition sub-module 125 and the / coloring sub-module 126. The setting sub-module 1 defines a thickening matrix, which defines a point that needs to adopt a foreground color, that is, a color of the target object. The bold matrix may be a matrix of order, as shown in Fig. 7(1). The value at the center of the bold matrix is i, indicating the current point during the outer rim bucking operation. At the center of the bold matrix: the values of other locations outside are composed of (^, where i indicates that foreground coloring is required. '〇 indicates that foreground coloring is not required. It is well known that every two points in the two-dimensional plane image There are adjacent points, namely upper right, upper, upper left, right, left, lower right, lower, lower left. In the 3rd order bold matrix shown in Figure 7 (A), at the center of the matrix Up, Down, 098111932 Form No. A0101 Page 8 / Total 33 Page 0992019744-0 201037631 [0020] [0024] [0024] [0025] Left 'Right' is 1, top left, top right The lower left and lower right values are 〇, and the table π 'colors the four adjacent points of the top, bottom, left and right of the current point by the color of the target object. In addition, the setting sub-module 20 is also used for setting. The matrix coordinates of the above-mentioned bold matrix. In detail, the setting sub-module 13 〇 can set the coordinate value of the point at the center of the bold matrix (x, y), then its upper right, upper, upper left, right, left, right The coordinates of the lower, lower, and lower left eight points are (X"n), (X, yl), (x+l, yl) ' (x-b y), χΗ , y) , (xl, y+l) , (x, y+l) , (x+1, y+1). The matrix coordinates can be seen in the first diagram shown in Figure 7 (B) The image capturing sub-module 122 is used to read the first image. The first image is a black-and-white image A2 or B2. In the embodiment, the coordinate value reading sub-module 122 is used to read the first image. a coordinate value of each point of each line of an image. The first pixel value acquisition sub-module 丨23 is configured to read a pixel value of each point of each line of the first image. The first determining sub-module 124 is configured to determine whether the pixel value of the first nth point of the first image is the same as the target object pixel value in the first image. Further, the first determining sub-module 124 further And determining whether the η point is the last point of the third line, and whether the third line is the last line of the first image. The point obtaining sub-module 125 is used to be the first picture. When the pixel value of the ηth row and the ηth point of the image is the same as the target object pixel value of the first image, the matrix according to the above-defined thick matrix and the matrix of the bold matrix is numbered in the first figure form. [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] [0030] For example, the first point is known to be adjacent to the η point of the Nth line. For example, the first The coordinate value of the ηth point of the third line in the image is (x, y), and the point acquisition sub-module 125 is obtained according to the bold matrix shown in FIG. 7(A) and the matrix coordinates shown in FIG. 7(B). Get the four points of the coordinate values (X, y-1), (x, y + l), (H ' y ), (X + l, y). The first coloring sub-module 126 is configured to determine whether there is a point in the obtained Y points whose pixel value is different from the target object pixel value in the first image, and when there is such a point, use the The color of the target object in the first image is colored 'to create a bold image with the outer contour of the target object that thickens the first image. 0 Refer to FIG. 3 for the sub-function module diagram of the image overlay module 13 in FIG. The image overlay module 13 includes a second image acquisition sub-module 130, a second pixel value reading sub-module 131, a second judging sub-module 132, an overlay sub-module 133, and a second shading sub-module. 34 and an image generation sub-module 丨35. The second image acquisition sub-module 130 is configured to acquire a second image and a third image that need to be covered by the image. In this embodiment, the second image and the second image are both black and white images, and the target object color is black, and the back scene color is white. The second image and the third image are a bold image Α4 and a backbone image Β3, respectively, or the second image and the third image are a bold image Β4 and a backbone image A3, respectively. The second pixel value reading sub-module 131 is configured to read pixel values of each point of each of the second image and the second image. In this embodiment, the pixel value is 〇 or 丨, where 〇 represents black and 1 represents white. The second determining sub-module 132 is configured to determine a pixel value of the second image in the second image, the nth 098111932 form number Α0101, the 10th page, the total page 33, the 0982019744-0 201037631 point, and the Nth image in the third image. Whether the pixel value of the ηth point of the line is the same. When the second image is different from the pixel value of the ηth point of the third image, the second determining sub-module 133 is further configured to determine the pixel of the ηth point of the second image in the second image. Whether the value is 0, that is, whether the point is black. Further, the second determining sub-module 132 is further configured to determine whether the nth point is the last point of the third line, and whether the second line is the most of the second image and the third image. Last line. [0031] The overlay sub-module 133 is configured to use, when the pixel value of the ηth point of the ninth line in the second image is the same as the pixel value of the ηth point of the third line in the third image, or Although the second image is different from the pixel value of the ηth point of the third image, but the pixel value of the ηth point of the second image is 0, 甩 the second image The second coloring sub-module 134 is used to cover the second image and the third image in the third image. If the pixel value of the dot is different, and the pixel value of the ηth point of the second line in the second image is not 0, the ηth point of the third line in the third image is colored to more clearly show the pixel value. More points. The image generation sub-module 135 of 〇 [_] is configured to generate an overlay image of the second image covering the third image, such as the overlay image ΑΒ1 and the overlay image ΑΒ2. Referring to Fig. 8, there is shown a flowchart of an embodiment of a preferred embodiment of the image comparison method of the present invention. [0035] In step S10, the image conversion module 10 converts the color images to be compared and the profit. The conversion algorithms are respectively converted into grayscale images A1 and B1. The conversion algorithm for converting a color image into a grayscale image may be: Gray = (R * 0.3 + G * .059 + B * 0.11). 098111S32 Form Compilation A01G1

Ms 1 1 , >> r\ n —r~·leli only/day K 0982019744-0 201037631 [0036] Step S11, the image conversion module 10 binarizes the grayscale images A1 and B1 , converted to black and white images A2 and B2, respectively. The binarization process is to set a threshold value, and the pixel value whose gray value is greater than or equal to the threshold value is 1 and the pixel value whose gray value is smaller than the threshold value is 0. The binarization of grayscale images can have different binarization algorithms depending on the target object in the image. At present, the main binarization algorithms include global threshold method, local threshold method and dynamic threshold method. The simplest of these is the global threshold method, in which the entire image is image binarized with a single threshold, such as setting the threshold to a median of 127 of 0-255. [0037] It should be noted that if the image to be compared is originally a black and white image, step S10 and step S11 may not be required. [0038] Step S12, the backbone extraction module 11 extracts the target object backbone from the black and white image B2 to obtain the backbone image B3. In detail, the backbone extraction module 11 extracts the pixel values of each point in rows or columns for the black and white image B2. For any row (or column), if there are multiple consecutive target object pixel values in the row (or column), the plurality of consecutive target object pixel values are represented by a target object pixel value. For example, the plurality of consecutive target object pixel values are represented by a middle one pixel value of the plurality of consecutive target object pixel values. That is to say, the extracted target object has a width of 1 . For example, suppose that the pixel value in the black and white image is 1 is the target object pixel value, assuming that the pixel value of all points in a black and white image is 1, 1, 1, 0, 0, 1, 1, 1, 1 , 1, 0, 0, 1, the pixel value of the line after extracting the image backbone is 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1. [0039] In step S1 3, the outline thickening module 12 boldens the outer contour of the target object in the black and white image A2 to generate a bold image A4. For the detailed flow of this step, please refer to 098111932 Form No. A0101 Page 12 / Total 33 Page 0992019744-0 201037631 [0040] [0044] [0044] [0044] [0045] [0046] 098111932 Show. In step S14, the image overlay module 13 overlays the bold image Α4 on the backbone image Β3 to generate an overlay image ΑΒ1 to obtain a portion of the backbone image Β3 with respect to the bold image Α4. For the detailed process of this step, see Figure 10. In step S1, the backbone extraction module 11 extracts the target object backbone from the black and white image Α2 to obtain the backbone image A3. The method of extracting the backbone image A3 can refer to the method of extracting the backbone image Β3 in step S12. In step S16, the outline thickening module 12 thickens the outer contour of the target object in the black and white image Β2 to generate a bold image Β4. The detailed process of this step is shown in Figure 9. In step S17, the image overlay module 13 overlays the bold image Β4 on the backbone image A3 to generate an overlay image ΑΒ2 to obtain a portion of the bold image Β4 with respect to the backbone image A3. See Figure 10 for the detailed process of this step. In step S18, the result output module 14 outputs a comparison result of the black and white images Α2 and Β2. Further, when the comparison result of the black and white images Α2 and Β2 is inconsistent, in this step, the result output module 14 also marks the black and white image Β2 in excess of the black and white image Α2 in black and white. The portion on the Β2 and the black-and-white image Β2 compared to the black-and-white image Α2 is color-coded on the black-and-white image Α2, and the black-and-white images Α2 and Β2 after the above-mentioned labeling are displayed. Referring to FIG. 9, which is a detailed implementation flowchart of steps S13 and S16 in FIG. 8, step S100, the setting sub-module 120 defines a bold matrix and sets the added form number Α0101. 13/33 I 0982019744-0 [0048] [0052] [0052] 098111932 The coordinates of the coarse matrix. The bold matrix may be (four) - an X-order matrix. WS1G1, the first image acquisition sub-module 121 acquires the first image. The first image described in the present embodiment is a black and white image A2 or a black and white image B2. In step S102, the coordinate value reading sub-module 122 reads the target value of all points of the Nth point of the first image, and N=1. The first pixel value acquisition sub-module eg reads the pixel values of all points in the Nth row of the first image. The first judging sub-module 124 determines that the pixel value of the nth point of the nth line of the first image is the target object pixel value of the first image. If the pixel values are the same, the flow advances to step S105. Otherwise, the pixel values are not the same', and the process proceeds to step S1Q8. In step SU) 5, the point acquisition sub-module 125 extracts the adjacent points of the Nth line from the η point in the first image according to the above-defined bold matrix and the matrix coordinates of the bold matrix. For example, 'the value of (n, y) is known to suppress the η point in the first image, according to the bold matrix shown in Fig. 7 (Α) and the matrix coordinates shown in Fig. 7 (B), The point acquisition sub-module 125 obtains four points whose coordinate values are (x ' y-1) '(X ' y+1) '(H, y), (χ + bu y ). Step S106: The first coloring sub-module 126 determines whether or not the 7 points obtained by the above are different from the point number of the image object of the first image. If there is a point in the Y points that the pixel value is different from the target object pixel value in the _th image, the flow proceeds to step S1Q?. Otherwise, if there is no point at which the pixel value is different from the pixel value of the target object in the first image, the flow proceeds to step S108. Form No. A0101 Page 14 of 33 0992019744-0 201037631 [0055] [0055] [0058] [0058] In step SI 07, the first coloring sub-module 126 uses the first The color of the target object in an image is colored to emphasize the outline of the target object of the first image. In step S108, the first determining sub-module 124 determines whether the nth point is the last point of the first line. If it is not the last point, the flow returns to step S104, where η = η + 1. If it is the last point, the flow advances to step S109. In step S109, the first determining sub-module 124 determines whether the third line is the last line of the first image. If it is not the last line, the flow returns to step S10 2, at which time Ν = Ν +1. If it is the last line, the process ends. Referring to Fig. 10, a detailed implementation flow chart of steps S14 and S17 in Fig. 8 is shown. In step S200, the second image acquisition sub-module 130 acquires the second image and the third image that need to be image-covered. In this embodiment, the second image and the third image are both black and white images, and the target object color is black and the background color is white. The second image and the third image are respectively a bold image Α4 and a backbone image Β3, or the second image and the third image are a bold image Β4 and a backbone image A3, respectively. In step S201, the second pixel value reading sub-module 131 reads the pixel values of all points of the second image and the third line of the third image, and N=1. In this embodiment, the pixel value is 0 or 1, where 0 represents black and 1 represents white. In step S202, the second determining sub-module 132 determines whether the pixel values of the Nth and Nth points of the second image and the third image are the same, and n=l. If the pixel values are the same, the flow advances to step S204. Otherwise, if the pixel values are not the same, 098II1932 form code 53⁄4 A0101 page 15 / page 33 0982019744-0 [0059] 201037631 Then the flow proceeds to step S203. [0060] In step S203, the second determining sub-module 132 further determines whether the pixel value of the nth point of the Nth line in the second image is 0, that is, whether the point is black. If the pixel value at this point is 0, the flow advances to step S204. Otherwise, if the pixel value of the point is not 0, the flow advances to step S205. [0061] In step S204, the overlay sub-module 133 covers the ηth point of the third row in the third image with the ηth point of the third line in the second image. [0062] In step S205, the coloring sub-module 134 colors the nth point of the third line in the third image to more clearly represent the extra point. [0063] Step S206, the second determining sub-module 132 determines whether the nth point is the last point of the first line. If it is not the last point, the flow returns to step S202, where η = η + 1. If it is the last point, the flow advances to step S207. [0064] Step S207, the second determining sub-module 132 determines whether the third line is the last line of the second image and the third image. If it is not the last line, the flow returns to step S201, where Ν = Ν + 1. If it is the last point, the flow advances to step S208. [0065] Step S208, the image generation sub-module 135 generates an overlay image in which the second image covers the third image, that is, generates the overlay image ΑΒ1 or the overlay image ΑΒ2. The above are only the preferred embodiments of the present invention, and have been used in a wide range of ways, and other equivalent changes or modifications which are not departing from the spirit of the present invention should be included in the following. Within the scope of the patent application. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a functional block diagram of a preferred embodiment of an image comparison system of the present invention. 098111932 Form No. Α0101 Page 16 of 33 0982019744-0 201037631 [0067] FIG. 2 is a sub-function module diagram of the outline thickening module of FIG. 1. 3 is a sub-function module diagram of the image overlay module of FIG. 1. [0070] FIG. 4 is a schematic diagram of a black and white image. [0071] FIG. 5 is a schematic diagram of a backbone image obtained from the black and white image shown in FIG. 4. 6(A) and 6(B) show the intention of the black-and-white image and the bold image generated after the outer contour of the target object in the black-and-white image is thickened, respectively. 7(A) and 7(B) illustrate a matrix of a 3rd order bold matrix and the 3rd order bold matrix. 8 is a flow chart showing an implementation of a preferred embodiment of the image comparison method of the present invention. 9 is a detailed implementation flowchart of steps S13 and S16 in FIG. 8. [0076] FIG. 1 is a detailed implementation flowchart of steps S14 and S17 in FIG. [Main Component Symbol Description] [0077] Image Conversion Module 1 [0079] Backbone Extraction Module 11 [0080] Outline Bolding Module 12 [0081] Setting Sub-Module 12〇 [0082] First Image Acquisition Sub-Module 121 [0083] Coordinate Value Reading Sub-Module 1 2 2 098ii 1932 Form Number AOiOl _____ 0982019744-0 Brother 1 γ 贝 / Total 33 Page 201037631 [0084] First Pixel Value Read sub-module 123 [0085] first judging sub-module 124 [0086] first shading sub-module 126 [0088] image overlay module 13 [0089] second diagram Image acquisition sub-module 130 [0090] second pixel value reading sub-module 131 [0091] second judging sub-module 132 [0092] overlay sub-module 133 [0093] second shading sub-module 134 [0094] Image Generation Sub-Module 135 [0095] Result Output Module 14 098111932 Form Number A0101 Page 18 of 33 0982019744-0

Claims (1)

201037631 VII. *Application patent scope: 1. An image comparison system, running in a computer, for comparing the difference of target objects in an image. The system includes: a backbone extraction module for extracting black and white images Α 2 targets The backbone of the object, the backbone image A3, and the backbone of the target object in the black and white image Β2 are extracted to obtain the backbone image Β3; the contour bolding module is used to bold the outer contour of the target object in the black and white image Α2, To obtain a bold image Α4, and to bold the outer ο contour of the target object in the black and white image Β2 to obtain a bold image Β4; an image overlay module for overlaying the bold image Α4 in the backbone image On the Β3, the overlay image ΑΒ1 is generated to obtain a portion of the black and white image Β2 with respect to the black and white image Α2, and the bold image Β4 is overlaid on the backbone image A3 to generate the overlay image ΑΒ2 to obtain black and white. a portion of the image Β2 with respect to the black and white image Α2; and a result output module for generating and outputting a comparison result of the black and white images Α2 and Β2 according to the processing result of the image overlay module. ❹ 2. The image comparison system of claim 1, wherein the system further comprises: an image conversion module, configured to compare the image to be compared when the image to be compared is not a black and white image Convert to black and white images. 3. The image comparison system of claim 1, wherein the outline bolding module comprises: a set sub-module for defining a bold matrix and setting a matrix coordinate of the bold matrix , wherein the bold matrix defines a point that needs to be colored by the color of the target object in the black and white image Α2 or Β2; 098111932 Form number ΑΟΙΟί 19th/33 I 0082019744-0 201037631 The first image acquisition sub-module, For acquiring a black and white image A2 or B2; a coordinate value reading submodule for reading a coordinate value of each point of each line of the black and white image A2 or B2; a first pixel value acquisition submodule for Reading the pixel value of each point of each line of the black and white image A2 or B2; the first determining submodule for determining whether the pixel value of the η point of the Nth line of the black and white image A2 or B2 is related to the black and white The pixel value of the target object in the image A2 or B2 is the same, and it is determined whether the ηth point is the last point of the first line, and whether the first line is the last line of the black and white image Α2 or Β2; the point acquisition submodule For black and white images Α 2 or Β 2 When the pixel value of the ηth point of the third line is the same as the target object pixel value in the black and white image Α2 or Β2, the matrix of the bold matrix and the matrix of the bold matrix are extracted in the black and white image Α2 or Β2 according to the definition. a first point of the νth line adjacent to the η point; and a first coloring sub-module, configured to determine whether the pixel value of the acquired point and the target object pixel value of the black and white image Α2 or Β2 Different points' and when such a point exists, the point is colored with the color of the target object in the black and white image Α2 or Β2. 4. The image comparison system of claim 1, wherein the image overlay module comprises: a second image acquisition sub-module for obtaining a bold image that requires image coverage. For the image and the backbone image, the bold image and the backbone image are a bold image Α4 and a backbone image Β3 or the bold image and the backbone image are a bold image Β4 and a backbone image A3; a two-pixel value reading sub-module, configured to read pixel values of each point of each of the bold image and the backbone image; and a second determining sub-module for determining a third image in the bold image The pixel of the ηth point 098111932 The 20th/page 33 form bat number Α0101 201037631 The value is the same as the pixel value of the η point of the Nth line in the backbone image, and it is determined whether the η point is the most The last point, and whether the third line is the last line of the above-mentioned bold image and the backbone image; the overlay sub-module is used for the pixel value and the backbone image of the ηth point of the third line in the bold image When the pixel value of the ηth point in the middle row is the same, or the image of the η point of the third line of the bold image and the backbone image The value is different, but when the color of the ηth point of the third line of the bold image is black, the η point of the third line in the backbone image is covered with the η point of the third line of the bold image; The sub-module is configured to: when the pixel value of the η 〇 point of the third image of the backbone image is different in the bold image, and the color of the η point of the third line in the bold image is white, the backbone image is In the image, the ηth point is colored with color; and the image generation sub-group is used to generate an overlay image formed by overwriting the backbone image with the bold image, wherein if the image is bold and the image is bold For the bold image Α4 and the backbone image Β3, the generated overlay image is ΑΒ1, and if the bold image and the backbone image are the bold image Β4 and the backbone image A3, the generated overlay image is ΑΒ 2. 5. An image comparison method for comparing difference differences of target objects in two images, the method comprising: a first backbone extraction step: extracting a backbone of a target object in a black and white image Β2, and obtaining a backbone image Β3 The first contour thickening step: bolding the outer contour of the target object in the black and white image Α2 to obtain a bold image Α4; the first image covering step: overwriting the bold image Α4 on the backbone image Β3 , generating an overlay image ΑΒ1 to obtain a portion of the black and white image Β2 relative to the black and white image Α2; a second backbone extraction step: extracting the backbone of the target object in the black and white image Α2, 0Q81HQ32 Form number Α0101 0982019744-0 201037631 Obtaining the backbone image A3; the second contour thickening step: thickening the outer contour of the target object in the black and white image B2 to obtain the bold image B4; second image covering step: overlaying the bold image B4 On the backbone image A3, the overlay image AB2 is generated to obtain a portion where the black-and-white image B2 is smaller than the black-and-white image A2; and the result output step outputs a comparison result of the black-and-white images A2 and B2. 6. The image comparison method according to claim 5, wherein, if the image to be compared is the color images A and B, the method further comprises: the color image A to be compared and B is converted into grayscale images A1 and B1 by a conversion algorithm respectively; a threshold is set; and the pixel values of the grayscale images A1 and B1 whose grayscale values are greater than or equal to the threshold are taken as 1, and A pixel value whose gray value is smaller than the threshold value is 0, and black and white images A2 and B2 are generated. 7. The image comparison method of claim 6, wherein the threshold is a median value of 127 between 0 and 255. 8. The image comparison method of claim 5, wherein the first backbone extraction step or the second backbone extraction step comprises: extracting each of the black and white images A2 or B2 by row or column a pixel value of a point; and when there are a plurality of consecutive target object pixel values in each row or column, the plurality of consecutive target object pixel values are represented by a target object pixel value. 9. The image comparison method of claim 5, wherein the first contour thickening step or the second contour thickening step comprises: (A) defining a bold matrix and setting the bold matrix The matrix coordinates, its 098111932 form number A0101 page 22 / total page 33 0982019744-0 201037631 in this bold matrix defines the point required to color the color of the target object in black and white image A2 or B2; (B) get black and white Image A2 or B2; - (C) Read the coordinate value of each point of the Nth line of the black and white image A2 or B2, at this time N = 1; (D) Read the Nth of the black and white image A2 or B2 (P) determining whether the pixel value of the nth point of the Nth line of the black and white image A2 or B2 is the same as the target object pixel value of the black and white image Α2 or Β2, at this time η= ι ; 〇 (F) when the pixel value of the η point of the Nth line of the black and white image A2 or B2 is the same as the pixel value of the target object of the black and white image Α2 or Β2, the bold matrix and the bold according to the above definition The matrix coordinates of the matrix are taken out in the black and white circle image Α2 or Β2 and the η point of the third line (G) When there is a point in the above-mentioned acquired points whose pixel value is different from the pixel value of the target object in the black and white image Α2 or Β2, the target in the black and white image 八2 or Β2 is used. The color of the object is colored by the point; (Η) determining whether the ηth point is the end point of the Nfe, wherein if the 〇^ point is not the last point of the Nth line, the step is returned. (E ), at this time, n=n+l, or if the ηth point is the last point of the Nth line, proceed to step (I); and (I) determine whether the third line is a black and white image Α2 or Β2 The last line, if not the last line, returns to step (C), at which point Ν = Ν +1. The image comparison method of claim 5, wherein the first image covering step or the second image covering step comprises: ' (a) obtaining an image that requires image coverage a bold image and a backbone image, the bold image and the backbone image are a bold image A4 and a backbone image B3 or the bold image and the backbone image are a bold image B4 and a backbone image A3 ; 098Π1932 Form No. A010I Page 23 of 33 0982019744- 201037631 (b) Read the pixel value of each point of the above bold image and the backbone image, at this time N=1; (c) Judgment plus Whether the pixel value of the nth point of the Nth line in the coarse image is the same as the pixel value of the ηth point of the Nth line in the backbone image, where η = ι, · (d) when the 1st line in the bold image When the pixel value of the nth point is the same as the pixel value of the nth line and the ηth point in the backbone image, or although the pixel value of the ηth point of the ninth point in the bold image is different in the bold image, the bold image is bold When the color of the third point of the image is black, the η point of the third line in the bold image is used to cover the η point of the third line in the backbone image; (e) In the coarse image, the pixel value of the first point of the backbone image is different, and when the color of the Nth point and the ηth point in the bold image is white, the ηth point of the third line in the backbone image is colored; (1) Determining whether the η point is the last point of the first order, wherein if it is not the last point, returning to step (c), in step (4) (4) Η the η point is the last point of the third line Go to step (g); (g) Determine whether the Nth is the last line of the bold image and the backbone image, where 'Right is not the last line, then return to step (8), step (b) "-N + l 'If the Nth line is the last line, proceed to step (1); and (8) generate a cover image of the bold image overlay backbone image. 098111932 Form No. A0101 Page 24 of 33 0982019744 -0