A method and system for compensating for detection plate gap in security inspection image

Abstract

The present invention relates to image gap processing technology, and discloses a method and system for compensating for the gap of a detection plate in a security inspection image, wherein the method comprises step 1, determining the position of the gap of the detection plate, determining the position of the gap of the detection plate in the security inspection image; step 2, extracting the adjacent area of ​​the gap of the detection plate, extracting the adjacent area of ​​the gap of the detection plate according to the position of the gap of the detection plate determined in step 1; and step 3, processing the adjacent area of ​​the gap of the detection plate, processing the adjacent area of ​​the gap of the detection plate extracted in step 2 to obtain a processed image of the gap of the detection plate. The present invention reduces the width of the plate gap by adjusting the angle of the detection plate, and then compensates for the gap of the detection plate by a surrounding area compensation algorithm and a filtering algorithm based on similarity. The present invention compensates for the gap of the detection plate in the security inspection image more accurately and naturally.

Description

Technical Field

[0001] The invention relates to an image gap processing technology, and in particular to a method and a system for compensating for a detection plate gap in a security inspection image. Background Art

[0002] X-ray carry-on baggage inspection devices are used in carry-on baggage inspections at airports or large-scale event venues. X-ray carry-on baggage inspection devices usually generate grayscale images that indicate the amount of X-ray transmission or color images that are colored for each material based on the material being determined. In addition, the usual practice is that inspectors visually inspect the images to confirm the presence of dangerous goods, and if the inspectors find dangerous goods, the luggage is opened for inspection. In order to avoid missing data caused by missed X-rays, existing security inspection equipment often forms a gap between the last point of the previous detection plate and the first point of the next detection plate, which blocks the security inspection image.

[0003] For example, prior art 1: CN201811369163.1 cannot handle the gap of the detection plate well. Summary of the invention

[0004] The present invention aims at the problem that the prior art cannot properly handle the gap of the detection plate, and provides a method and system for compensating the gap of the detection plate in the security inspection image.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0006] A method for compensating for a detection plate gap in a security inspection image, the method comprising:

[0007] Step 1, determining the position of the gap of the detection plate, for determining the position of the gap of the detection plate in the security inspection image;

[0008] Step 2, extracting the area adjacent to the gap of the detection plate, extracting the area adjacent to the gap of the detection plate according to the gap position of the detection plate determined in step 1;

[0009] Step 3, processing the detection plate gap vicinity area, processing the detection plate gap vicinity area extracted in step 2 to obtain a processed detection plate gap image.

[0010] As a preferred method, the extraction of the adjacent area of ​​the detection plate gap is performed by extracting the adjacent area through the gap width and pixel grayscale value of the detection plate security inspection image, and the grayscale data of the extracted adjacent area is ;

[0011] when , ,in, ;

[0012] when , ,in, ;

[0013] in, is the grayscale data of the i-th row and j-th column, i is the row coordinate of the pixel, j is the column coordinate of the pixel, and I is the pixel row coordinate multiple of 64. is the pixel grayscale threshold.

[0014] Preferably, in step 3, the processing of the area adjacent to the gap of the detection plate is performed by using a similarity algorithm for the area adjacent to the gap of the detection plate.

[0015] Preferably, the adjacent region similarity algorithm includes:

[0016] Determine whether the detection plate is the same material by atomic number and output the gray value of the same material

[0017] ;

[0018] ;

[0019] in, is the first atomic number, is the second atomic number, is the first high energy gray value, is the first low-energy gray value, is the second highest energy gray value, is the second lowest energy gray value,

[0020] ; If P is less than P1, ;

[0021] Among them, P is the atomic number difference, P1 is the atomic number threshold, Grayscale values ​​outputted in accordance with atomic number;

[0022] Output the processed grayscale value by retaining the grayscale value ;

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] when, and ,but ;

[0028] in, is the maximum gray value, is the minimum gray value, Output grayscale minimum ratio, Output grayscale maximum ratio, The output grayscale value.

[0029] Preferably, the processing of the adjacent area of ​​the detection plate gap also includes interpolation processing, so as to obtain the interpolated gray value , the gray value Replace the grayscale value of the detection board ;

[0030] ;

[0031] ;

[0032] ;

[0033] in, is the interpolated gray value, is the average grayscale value of the i-th row; is the distance of the i-th row.

[0034] Preferably, the processing of the area adjacent to the gap of the detection plate in step 3 also includes filtering processing, which is performed by mean filtering.

[0035] In order to solve the above technical problems, the present invention also provides a system for compensating the gap of a detection plate in a security inspection image, which comprises:

[0036] A module for determining the gap position of the detection plate, for determining the gap position of the detection plate in the security inspection image;

[0037] A detection plate gap adjacent region extraction module is used to extract the detection plate gap adjacent region based on the detection plate gap position determined by the detection plate gap position determination module;

[0038] The processing module of the detection plate gap vicinity region processes the detection plate gap vicinity region extracted by the extraction module of the detection plate gap vicinity region to obtain a processed detection plate gap image.

[0039] The present invention has significant technical effects due to the adoption of the above technical solution:

[0040] The present invention reduces the plate gap width by adjusting the detection plate angle, and then compensates for the detection plate gap by using a surrounding area compensation algorithm and a filtering algorithm based on similarity.

[0041] The present invention can more accurately and naturally compensate for the detection plate gap in the security inspection image. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the present invention;

[0043] Figure 2 is the original image of the gap of the detection plate of the present invention;

[0044] Figure 3 Extracting the adjacent area image for the detection plate gap of the present invention;

[0045] Figure 4 The image is processed by the interpolation calculation of the gap of the detection plate of the present invention;

[0046] Figure 5 This is the image after the detection plate gap mean filtering process of the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0048] Example 1

[0049] A method for compensating for a detection plate gap in a security inspection image, the method comprising:

[0050] Step 1, determining the position of the gap of the detection plate, for determining the position of the gap of the detection plate in the security inspection image;

[0051] Step 2, extracting the area adjacent to the gap of the detection plate, extracting the area adjacent to the gap of the detection plate according to the gap position of the detection plate determined in step 1;

[0052] Step 3, processing the detection plate gap vicinity area, processing the detection plate gap vicinity area extracted in step 2 to obtain a processed detection plate gap image.

[0053] The extraction of the adjacent area of ​​the detection plate gap is carried out by the gap width and pixel gray value of the detection plate security inspection image. The grayscale data of the extracted adjacent area is ;

[0054] when , ,in, ;

[0055] when , ,in, ;

[0056] in, is the grayscale data of the i-th row and j-th column, i is the row coordinate of the pixel, j is the column coordinate of the pixel, and I is the pixel row coordinate multiple of 64. is the pixel grayscale threshold. Here the grayscale threshold is 1000.

[0057] In step 3, the processing of the area adjacent to the gap of the detection plate is performed by using a similarity algorithm of the area adjacent to the gap of the detection plate.

[0058] The neighboring region similarity algorithms include:

[0059] Determine whether the detection plate is the same material by atomic number and output the gray value of the same material ;

[0060] ;

[0061] ;

[0062] in, is the first atomic number, is the second atomic number, is the first high energy gray value, is the first low-energy gray value, is the second highest energy gray value, is the second lowest energy gray value,

[0063] ; If P is less than P1, ;

[0064] Among them, P is the atomic number difference, P1 is the atomic number threshold, Grayscale values ​​outputted in accordance with atomic number;

[0065] Output the processed grayscale value by retaining the grayscale value ;

[0066] ;

[0067] ;

[0068] ;

[0069] ;

[0070] when, and ,but ;

[0071] in, is the maximum gray value, is the minimum gray value, Output grayscale minimum ratio, Output grayscale maximum ratio, The output grayscale value.

[0072] The data in rows 58 to 63 are adjacent to the data in row 64. The data in each row must be calculated. The value is calculated from the data in row 64. Compare, Only values ​​less than 0.5 can be retained.

[0073] Line 64 Set is 34000, is 31000, and the 58th line is set is 33000, is 30000, the 64th is the standard, the R1 value of the 58th row is 1.1, and the R2 value of the 64th row is 1.096; the R1 value divided by the R2 value is 1.0036, and the ratio is between 0.9 and 1.1; the data in the 58th row should be retained.

[0074] Line 59 Set is 33000, The value of R1 in row 59 is 1.1, and the value of R2 in row 64 is 1.096. The value of R1 divided by R2 is 1.0036, and the ratio is between 0.9 and 1.1. Therefore, the data in row 59 should be retained. is 34166, The value is 29027, the 64th is the standard, the R1 value of the 60th row is 1.1, and the R2 value of the 64th row is 1.18; the R1 value divided by the R2 value is 1.07, and the ratio is between 0.9 and 1.1; the data of the 60th row should be retained.

[0075] Line 61 is 33541, The value is 29845, the 64th is the standard, the R1 value of the 61st row is 1.12, and the R2 value of the 64th row is 1.096; the R1 value divided by the R2 value is 1.025, and the ratio is between 0.9 and 1.1; the data of the 61st row should be retained.

[0076] Line 62 Set is 32584, The value is 30015, the 64th is the standard, the R1 value of the 62nd row is 1.085, and the R2 value of the 64th row is 1.096; the R1 value divided by the R2 value is 0.99, and the ratio is between 0.9 and 1.1; the data of the 62nd row should be retained.

[0077] Line 63 Set is 34784, The value is 31421, the 64th row is the standard, the R1 value of the 63rd row is 1.107, and the R2 value of the 64th row is 1.096; the R1 value divided by the R2 value is 1.01, and the ratio is between 0.9 and 1.1; the data of the 63rd row should be retained.

[0078] The processing of the area adjacent to the gap of the detection plate also includes interpolation processing to obtain the interpolated gray value , the gray value Replace the grayscale value of the detection board ;

[0079] ;

[0080] ;

[0081]

[0082] in, is the interpolated gray value, is the grayscale average of the i-th row; is the distance of the i-th row.

[0083] The processing of the area adjacent to the gap of the detection plate in step 3 also includes filtering processing, which is performed by mean filtering.

[0084] If you want to fill the gap in row 64, the available adjacent data is the data in row 62. , the data of row 63 , the data of row 65 and row 66 ; The distance between row 62 and row 64 is 2, the distance between row 63 and row 64 is 1, the distance between row 65 and row 64 is 1, and the distance between row 66 and row 64 is 2, then:

[0085] =1 / (1+2+1+2)* +2 / (1+2+1+2)* +1 / (1+2+1+2)* +2 / (1+2+1+2)* .

[0086] Example 2

[0087] Based on Example 1, this example is a system for compensating for the gap of a detection plate in a security inspection image, which includes:

[0088] A module for determining the position of the gap of the detection plate, for determining the position of the gap of the detection plate in the security inspection image;

[0089] A detection plate gap adjacent region extraction module is used to extract the detection plate gap adjacent region based on the detection plate gap position determined by the detection plate gap position determination module;

[0090] The processing module of the detection plate gap vicinity region processes the detection plate gap vicinity region extracted by the extraction module of the detection plate gap vicinity region to obtain a processed detection plate gap image.

Claims

1. A method for compensating for a detection plate gap in a security inspection image, the method comprising: Step 1, determining the position of the gap of the detection plate, for determining the position of the gap of the detection plate in the security inspection image; Step 2, extracting the area adjacent to the gap of the detection plate, extracting the area adjacent to the gap of the detection plate according to the gap position of the detection plate determined in step 1; Step 3, processing the detection plate gap vicinity area, processing the detection plate gap vicinity area extracted in step 2 to obtain a processed detection plate gap image; The extraction of the adjacent area of ​​the detection plate gap is carried out by the gap width and pixel gray value of the detection plate security inspection image. The grayscale data of the extracted adjacent area is ; when , ,in, ; when , ,in, ; in, is the grayscale data of the i-th row and j-th column, i is the row coordinate of the pixel, j is the column coordinate of the pixel, and I is the pixel row coordinate multiple of 64. is the pixel grayscale threshold; the processing of the detection plate gap adjacent area in step 3 is performed by the detection plate gap adjacent area similarity algorithm; the adjacent area similarity algorithm includes: Determine whether the detection plate is the same material by atomic number and output the gray value of the same material ; ； ； in, is the first atomic number, is the second atomic number, is the first high energy gray value, is the first low-energy gray value, is the second highest energy gray value, is the second lowest energy gray value, ; If P is less than P1, ; Among them, P is the atomic number difference, P1 is the atomic number threshold, Grayscale values ​​outputted in accordance with atomic number; Output the processed grayscale value by retaining the grayscale value ; ; ; ; ; when, and ,but ; in, is the maximum gray value, is the minimum gray value, Output grayscale minimum ratio, Output grayscale maximum ratio, The output grayscale value.

2. A method for compensating for detection plate gaps in security inspection images according to claim 1, characterized in that: The processing of the area adjacent to the gap of the detection plate also includes interpolation processing to obtain the interpolated gray value , the gray value Replace the grayscale value of the detection board ; ; ； in, is the interpolated gray value, is the grayscale average of the i-th row; is the distance of the i-th row.

3. The method for compensating the gap of a detection plate in a security inspection image according to claim 1, characterized in that: The processing of the area adjacent to the gap of the detection plate in step 3 also includes filtering processing, which is performed by mean filtering.

4. A system for compensating the gap of a detection plate in a security inspection image, characterized in that: include: A module for determining the position of the gap of the detection plate, for determining the position of the gap of the detection plate in the security inspection image; A detection plate gap adjacent region extraction module is used to extract the detection plate gap adjacent region based on the detection plate gap position determined by the detection plate gap position determination module; A processing module for the detection plate gap vicinity region processes the detection plate gap vicinity region extracted by the extraction module for the detection plate gap vicinity region to obtain a processed detection plate gap image; The extraction of the adjacent area of ​​the detection plate gap is carried out by the gap width and pixel gray value of the detection plate security inspection image. The grayscale data of the extracted adjacent area is ; when , ,in, ; when , ,in, ; in, is the grayscale data of the i-th row and j-th column, i is the row coordinate of the pixel, j is the column coordinate of the pixel, and I is the pixel row coordinate multiple of 64. is the pixel grayscale threshold; the processing of the detection plate gap adjacent area in step 3 is performed by the detection plate gap adjacent area similarity algorithm; the adjacent area similarity algorithm includes: Determine whether the detection plate is the same material by atomic number and output the gray value of the same material ; ； ； in, is the first atomic number, is the second atomic number, is the first high energy gray value, is the first low-energy gray value, is the second highest energy gray value, is the second lowest energy gray value, ; If P is less than P1, ; Among them, P is the atomic number difference, P1 is the atomic number threshold, Grayscale values ​​outputted in accordance with atomic number; Output the processed grayscale value by retaining the grayscale value ; ; ; ; ; when, and ,but ; in, is the maximum gray value, is the minimum gray value, Output grayscale minimum ratio, Output grayscale maximum ratio, The output grayscale value.

Images