An automatic positioning and degumming process for flexographic printing based on image recognition technology

Abstract

The invention relates to the technical field of image processing, and specifically discloses an automatic positioning and degumming process for flexographic printing based on image recognition technology. Based on camera position data and light source position data, a three-channel pixel value of each pixel point in an image is obtained, and a grayscale value of the pixel point is calculated and obtained; the grayscale value of the pixel point in the image is binarized; the pixel point area value of each colloid connected region is traversed to obtain, and it is judged whether it is within the effective glue connected area value range; then the characteristic shape expression value of the connected region is calculated and obtained, and compared with the characteristic shape expression threshold value, and the invalid colloid thickness value at each pixel point coordinate is calculated based on the invalid colloid signal; the invalid colloid is removed by laser, so as to solve the problem that adhesive residue is easy to remain in the pattern area during the flexographic printing production process, and the distribution of the glue layer on the flexographic plate is detected by image recognition technology to realize automatic positioning and degumming, which can ensure the cleanliness of the pattern area and protect the non-target area at the same time.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to an automatic positioning and degumming process for flexographic printing based on image recognition technology. Background Art

[0002] Flexographic printing is a printing technology that uses flexible plates. It is suitable for a variety of materials and can be printed on uneven and soft surfaces. It has a fast printing speed and is suitable for mass production. The production cost of flexographic plates is low and it is suitable for long-term repeated use. In flexographic printing, gluing is a key process used to transfer ink evenly to the printing material. Gluing can improve the surface tension of the printing material and enhance the adhesion of the ink, thereby achieving high-quality printing effects. During the printing process, due to equipment errors, excessive glue or uneven distribution, some non-printing areas may have excess glue remaining. These residual colloids may contaminate other materials or cause blurring and printing defects, affecting the accuracy and durability of the printing equipment.

[0003] Therefore, the degumming process aims to remove excess glue from non-printing areas to ensure printing quality. Traditional mechanical removal or manual inspection cannot accurately locate the residual glue area, which may lead to incomplete removal or excessive cleaning. Manual cleaning or semi-automatic cleaning methods are time-consuming, and manual inspection relies heavily on the operator's experience, which can easily lead to missed inspections or misjudgments, and unstable degumming quality:

[0004] Therefore, the present application provides an automatic positioning and degumming process for flexographic printing based on image recognition technology, which utilizes image recognition technology to accurately identify the shape, position and distribution of excess colloid, thereby achieving an efficient, accurate and rapid degumming process. Summary of the invention

[0005] The object of the present invention is to provide an automatic positioning and degumming process for flexographic printing based on image recognition technology to solve the above-mentioned problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An automatic positioning and degumming process for flexographic printing based on image recognition technology comprises the following steps:

[0008] Step 1: Based on the camera position data and the light source position data, the incident angle value θ of the light source is calculated and adjusted, and the image of the printing plate surface is collected. Then, the coordinates of the pixels in the image are marked, and the three-channel pixel value of each pixel in the image is obtained, and the grayscale value of the pixel is calculated and obtained;

[0009] Step 2: Binarize the grayscale values ​​of pixels in the image, determine and obtain the colloid pixels, and then mark them;

[0010] Step 3: Based on the marked pixels containing colloids, traverse and obtain the pixel area value of each colloid connected region, and record it as LS; determine whether the pixel area LS of the connected region is within the valid colloid connected area value range [LSmin, LSmax]; obtain a feature judgment signal or an invalid colloid signal;

[0011] Step 4: Based on the characteristic judgment signal, calculate and obtain the characteristic shape performance value XB of the connected area, and compare the characteristic shape performance value XB with the characteristic shape performance threshold Xby, and obtain a valid colloid signal or an invalid colloid signal;

[0012] Step 5: Based on the invalid colloid signal, obtain the pixel coordinate set of the invalid colloid connected area, traverse the invalid colloid on each pixel in the pixel coordinate set through the laser sensor, obtain the laser scanning data of each pixel coordinate, and calculate the invalid colloid thickness value QC on each pixel coordinate; select the corresponding laser energy density through the laser energy density relationship table to remove the invalid colloid.

[0013] As a further solution of the present invention: the camera position data includes the camera horizontal distance value Lca, and the light source position data includes the light source height value Hg; then, by Calculate and obtain the incident angle value θ of the light source.

[0014] As a further solution of the present invention: the grayscale value of the pixel in the image is obtained by:

[0015] Mark the pixel in the upper left corner of the image as the origin (0, 0), then record the horizontal column of pixels as the X-axis direction and the vertical column as the Y-axis direction, and obtain the coordinates of each pixel as (x, y);

[0016] Extract the red, green, and blue channel pixel values ​​of each pixel in the image and mark them as the red channel pixel value R （x，y） , green channel pixel value G （x，y） and blue channel pixel value B （x，y） ;

[0017] pass Calculate the pixel gray value H （x，y） , where a is the preset proportional coefficient of the red channel, b is the preset proportional coefficient of the green channel, c is the preset proportional coefficient of the blue channel, and a, b and c are all greater than 0.

[0018] As a further solution of the present invention: in step 2, the step of marking the pixel points where the colloid exists on the surface includes: traversing the gray value of each pixel point, and marking the gray value H of the pixel point （x，y） Compare with the pixel grayscale threshold HY;

[0019] If the pixel gray value H （x，y） If it is greater than or equal to the pixel grayscale threshold HY, the pixel is marked as 1;

[0020] If the pixel gray value H （x，y） If the grayscale value is less than the pixel grayscale threshold HY, the pixel is marked as 0.

[0021] As a further solution of the present invention: in the step three, the colloid connected area determines whether the pixels are connected in a four-connectivity manner, and the directions of the four-connectivity are four directions, namely, up, down, left, and right.

[0022] As a further solution of the present invention: judging whether the pixel area LS of the connected region is within the effective glue connected area value range [LSmin, LSmax]:

[0023] If the pixel area LS of the connected region is within the effective glue connected area range [LSmin, LSmax], a feature determination signal is generated;

[0024] If the pixel area LS of the connected region is not within the effective glue connected area range [LSmin, LSmax], an invalid colloid signal is generated.

[0025] As a further solution of the present invention: the characteristic shape performance value XB is calculated as follows:

[0026] S41: Obtaining the side length data of the connected area, including: the maximum horizontal span value Wk and the maximum vertical span value Wh of the connected area;

[0027] pass Calculate the aspect ratio KH of the connected area;

[0028] S42: Based on the side length data of the connected region and the pixel area value LS of the connected region;

[0029] pass Calculate the compactness value JC of the connected area;

[0030] S43: Obtain the perimeter value Cz of the connected region based on the pixel area value LS of the connected region;

[0031] pass Calculate and obtain the heterogeneous value YX of the connected area;

[0032] S44: Based on the aspect ratio KH, the compact value JC and the profile value YX, The characteristic shape performance value XB is calculated and obtained.

[0033] As a further solution of the present invention: comparing the characteristic shape representation value XB with the characteristic shape representation threshold value Xby:

[0034] If the characteristic shape representation value XB is greater than the characteristic shape representation threshold value Xby, an invalid colloid signal is generated;

[0035] If the characteristic shape representation value XB is less than or equal to the characteristic shape representation threshold value Xby, a valid colloid signal is generated.

[0036] As a further solution of the present invention: the laser scanning data in step five includes a scanning laser emission time point FD and a scanning laser reception time point SD.

[0037] As a further solution of the present invention: the calculation method of the invalid colloid thickness value QC is: , where υ is the speed of light.

[0038] Beneficial effects of the present invention:

[0039] In the present invention, the image of the acquired flexographic printing surface is analyzed, and the pixel coordinates of the residual glue are output based on the calculated area and shape of the residual glue, the position of the residual invalid colloid is accurately calculated and obtained, and then the invalid colloid thickness on each pixel is obtained based on the laser traversal scanning, and then the power pulse width and frequency data of the laser are controlled according to the relationship between the colloid thickness and the laser energy density, and the residual colloid or excess colloid is accurately removed, so as to ensure the effectiveness of the colloid on the surface of the flexographic printing substrate and the integrity of the substrate, and avoid the problem of damaging the flexographic substrate due to inaccurate pixel colloid removal; solve the problem that the pattern area is prone to residual adhesive during the flexographic printing production process, detect the distribution of the glue layer on the flexographic plate through image recognition technology, realize automatic positioning and degumming, ensure the cleanliness of the pattern area, and protect the non-target area at the same time; effectively solve the problem that manual inspection cannot accurately locate, and the flexographic plate is easily damaged due to incomplete or excessive degumming, and the invalid colloid is quickly identified, the accuracy of identification is improved, and the quality of flexographic degumming is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention will be further described below in conjunction with the accompanying drawings.

[0041] Figure 1 It is a schematic diagram of the process of automatic positioning and degumming process of flexographic printing based on image recognition technology of the present invention;

[0042] Figure 2 The present invention is a system block diagram of an automatic positioning and degumming system for flexographic printing based on image recognition technology. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0044] See also Figure 1 As shown, the present invention is a flexographic printing automatic positioning and degumming process based on image recognition technology, comprising the following steps:

[0045] Step 1: Based on the camera position data and the light source position data, the incident angle value θ of the light source is calculated and adjusted, and the image of the printing plate surface is collected. Then, the coordinates of the pixels in the image are marked, and the three-channel pixel value of each pixel in the image is obtained, and the grayscale value of the pixel is calculated and obtained;

[0046] The camera position data includes the camera horizontal distance value Lca, and the light source position data includes the light source height value Hg; then, through Calculate and obtain the incident angle value θ of the light source; Calculate and obtain the incident angle value of the light source, and then adjust the incident angle of the light source. At this time, the collected data and the calculation results are more accurate. It should be noted that when facing different flexographic printing materials, the incident angle of the light source can be manually adapted and optimized to improve the accuracy of the data;

[0047] Specifically, the grayscale value of a pixel in an image is obtained as follows:

[0048] S11: Mark the pixel point at the upper left corner of the image as the origin (0, 0), then record the horizontal column of pixels as the X-axis direction, and the vertical column as the Y-axis direction, and obtain the coordinates of each pixel point as (x, y);

[0049] S12: Extract the red, green, and blue channel pixel values ​​of each pixel in the image and mark them as the red channel pixel value R （x，y） , green channel pixel value G （x，y） and blue channel pixel value B （x，y） ;

[0050] S13: Pass Calculate the pixel gray value H （x，y）, where a is the preset ratio coefficient of the red channel, b is the preset ratio coefficient of the green channel, and c is the preset ratio coefficient of the blue channel, and a, b and c are all greater than 0, the value of a is 0.298, the value of b is 0.587, and the value of c is 0.114; the gray value is calculated and obtained based on the three-channel pixel value of each pixel point, because graying the image is equivalent to retaining only the brightness information, reducing the complexity of the calculation process, and at the same time, it can enhance the contrast between the colloid and the flexographic background;

[0051] Step 2: Binarize the grayscale values ​​of the pixels in the image, determine and obtain the colloid pixels, and mark the pixels with colloid on the surface;

[0052] The following steps are involved:

[0053] Traverse each pixel gray value and convert the pixel gray value H （x，y） Compare with the pixel grayscale threshold HY; the pixel grayscale threshold refers to the critical value between the grayscale value of the background pixel point on the normal flexographic plate surface and the grayscale value of the pixel point on the glue surface, which is used to distinguish and judge whether there is colloid on the pixel point;

[0054] If the pixel gray value H （x，y） If it is greater than or equal to the pixel grayscale threshold HY, the pixel is marked as 1; this means that the grayscale value of the pixel is too large, and there is colloid on the surface of the flexographic plate, which is a colloid pixel;

[0055] If the pixel gray value H （x，y） If the pixel gray value is less than the pixel gray threshold HY, the pixel is marked as 0, which means that the gray value of the pixel meets the standard and there is no colloid on the flexographic plate surface, that is, the pixel is blank.

[0056] Step 3: Based on the marked pixels containing colloids, traverse to obtain the pixel area value of each colloid connected area and record it as LS;

[0057] Among them, the colloid-connected area determines whether the pixels are connected in a four-connectivity manner, and the directions of the four-connectivity are the four directions of up, down, left, and right. The counting method of the pixels in the colloid-connected area is: the number of pixels whose values ​​are 1 and connected continuously, and the calculation method of the pixel area value is the number of pixels multiplied by the area of ​​a single pixel.

[0058] Determine whether the pixel area LS of the connected region is within the effective glue connected area range [LSmin, LSmax];

[0059] If the pixel area LS of the connected region is within the effective glue connected area value range [LSmin, LSmax], a feature judgment signal is generated; this means that the pixel area of ​​the connected region is within the effective colloid area range, and it is necessary to continue to judge the shape characteristics of the connected region to further determine whether the colloid on the pixel point in the connected region is an invalid colloid;

[0060] If the pixel area LS of the connected region is not within the effective glue connected area range [LSmin, LSmax], an invalid colloid signal is generated; at this time, it means that the continuous colloid area in the connected region is too large or too small, exceeding the effective colloid area range. At this time, the colloid on each pixel in the connected region needs to be removed;

[0061] Regarding the determination of the pixel area value of the colloid connected region, this application provides an exemplary description:

[0062] For example, let's take a 5X4 pixel coordinate point binary matrix as an example; suppose the pixel coordinate point is ;

[0063] At this time, the four-connectivity method is used to calculate the connected area:

[0064] Assume that the unit area of ​​the pixel is also 1, that is, there are two connected regions;

[0065] The first connected region has an area of ​​3 and contains three pixels: (0,0), (0,1) and (1,0);

[0066] The second connected region has an area of ​​7, including seven pixels: (3, 2), (4, 2), (4, 3), (4, 2), (3, 3), (2, 3), and (1, 3).

[0067] Step 4: Based on the characteristic judgment signal, calculate and obtain the characteristic shape performance value XB of the connected area, and compare the characteristic shape performance value XB with the characteristic shape performance threshold Xby, and obtain a valid colloid signal or an invalid colloid signal;

[0068] Among them, the calculation method of the characteristic shape performance value XB is:

[0069] S41: Obtaining the side length data of the connected area, including: the maximum horizontal span value Wk and the maximum vertical span value Wh of the connected area;

[0070] pass Calculate the aspect ratio KH of the connected area;

[0071] Similarly, based on the above 5X4 matrix, the aspect ratios of the two connected regions are calculated respectively;

[0072] The aspect ratio of the first connected region ;

[0073] The aspect ratio of the second connected region ;

[0074] It should be noted that the closer the aspect ratio is to 1, the more the shape of the connected region is similar to a square, and the more it conforms to a qualified colloid;

[0075] S42: Based on the side length data of the connected region and the pixel area value LS of the connected region;

[0076] pass Calculate the compactness value JC of the connected area;

[0077] Similarly, based on the above 5X4 matrix, calculate the compactness values ​​of the two connected regions respectively;

[0078] The compactness value of the first connected region ;

[0079] The compactness value of the second connected region ;

[0080] It is also explained that the larger the compactness value is, the higher the colloid filling coverage on the pixel points in the outer contour area of ​​the connected area is, which means that the colloid in the connected area is closer to the qualified colloid compactness;

[0081] S43: Obtain the perimeter value Cz of the connected region based on the pixel area value LS of the connected region;

[0082] pass Calculate and obtain the heterogeneous value YX of the connected area;

[0083] Similarly, based on the above 5X4 matrix, calculate the heterogeneity values ​​of the two connected regions respectively;

[0084] The first connected region's odd value ;

[0085] The second connected region's odd value ;

[0086] The larger the value of the heteromorphism is, the more irregular the shape of the colloid on the pixel point in the connected area is, and the less it conforms to the shape representation of the standard colloid;

[0087] S44: Based on the aspect ratio KH, the compact value JC and the profile value YX, Calculate and obtain the characteristic shape performance value XB;

[0088] Similarly, based on the above 5X4 matrix, the characteristic shape performance values ​​of the two connected regions are calculated respectively;

[0089] The characteristic shape performance value of the first connected area ;

[0090] The characteristic shape performance value of the second connected area ;

[0091] Compare the characteristic shape representation value XB with the characteristic shape representation threshold Xby:

[0092] If the characteristic shape representation value XB is greater than the characteristic shape representation threshold value Xby, an invalid colloid signal is generated;

[0093] If the characteristic shape performance value XB is less than or equal to the characteristic shape performance threshold value Xby, a valid colloid signal is generated;

[0094] It should be noted that when the characteristic shape performance value is too large, it means that the shape and coverage performance of the colloid in the connected area are abnormal. At this time, the colloid on the pixel point needs to be removed to ensure that the colloid on the surface of the flexographic plate meets the qualified use conditions;

[0095] Step 5: Based on the invalid colloid signal, obtain the pixel coordinate set of the invalid colloid connected area, traverse and scan the invalid colloid on each pixel in the pixel coordinate set through the laser sensor, obtain the laser scanning data of each pixel coordinate, and calculate the invalid colloid thickness value QC on each pixel coordinate; then based on the invalid colloid thickness value on each pixel coordinate, select the corresponding laser energy density through the laser energy density relationship table to remove the invalid colloid;

[0096] The laser scanning data includes the scanning laser emission time point FD and the scanning laser reception time point SD;

[0097] In addition, the calculation method of the invalid colloid thickness value QC is: , where υ is the speed of light;

[0098] By analyzing the image of the flexographic printing surface, the pixel coordinates of the residual glue are output based on the calculated area and shape of the residual glue, and the position of the residual invalid colloid is accurately calculated and obtained. Then, the thickness of the invalid colloid on each pixel is obtained based on the laser traversal scanning. Then, according to the relationship between the colloid thickness and the laser energy density, the power pulse width and frequency data of the laser are controlled to accurately remove the residual colloid or excess colloid, so as to ensure the effectiveness of the colloid on the surface of the flexographic printing substrate and the integrity of the substrate, and avoid the problem of damaging the flexographic substrate due to inaccurate pixel colloid removal;

[0099] To solve the problem of adhesive residue in the pattern area during flexographic printing, the image recognition technology is used to detect the distribution of the adhesive layer on the flexographic plate, and automatic positioning and adhesive removal are achieved to ensure the cleanliness of the pattern area while protecting non-target areas.

[0100] In addition, image recognition technology is used to accurately identify the shape, position and distribution of excess colloid on the printing surface, and then remove it with laser, which effectively solves the problem that manual inspection cannot accurately locate the surface, and is prone to incomplete or excessive glue removal leading to damage to the flexographic plate. In addition, the invalid colloid can be identified quickly, which improves the accuracy of identification and the quality of flexographic plate glue removal.

[0101] Based on binarization, connected region analysis and other algorithms, the areas that need to be debonded can be quickly screened. Example 2

[0102] Based on the above embodiments, this embodiment provides a flexographic printing automatic positioning and degumming system based on image recognition technology, comprising:

[0103] Data acquisition module: Based on the camera position data and the light source position data, the incident angle value θ of the light source is calculated and adjusted, and the image of the printing plate surface is collected. Then, the coordinates of the pixels in the image are marked, and the three-channel pixel value of each pixel in the image is obtained, and the grayscale value of the pixel is calculated and obtained;

[0104] Data processing module: used to perform binarization processing on the grayscale values ​​of pixels in the image, determine and obtain colloid pixels, and mark the pixels with colloids on the surface;

[0105] Area determination module: Based on the marked pixels containing colloids, the pixel area value of each colloid connected area is traversed and recorded as LS; it is determined whether the pixel area LS of the connected area is within the valid colloid connected area value range [LSmin, LSmax], and a feature determination signal or an invalid colloid signal is obtained;

[0106] Feature determination module: based on the feature determination signal, calculate and obtain the feature shape performance value XB of the connected area, compare the feature shape performance value XB with the feature shape performance threshold Xby, and obtain a valid colloid signal or an invalid colloid signal;

[0107] Glue removal module: Based on the invalid colloid signal, the pixel coordinate set of the invalid colloid connected area is obtained, and the laser sensor is used to traverse and scan the invalid colloid on each pixel in the pixel coordinate set to obtain the laser scanning data of each pixel coordinate, and the invalid colloid thickness value QC on each pixel coordinate is calculated; then based on the invalid colloid thickness value on each pixel coordinate, the corresponding laser energy density is selected through the laser energy density relationship table to remove the invalid colloid.

[0108] Based on the camera position data and the light source position data, the system obtains the three-channel pixel value of each pixel in the image, calculates and obtains the pixel grayscale value; binarizes the pixel grayscale value in the image; traverses to obtain the pixel area value of each colloid connected region to determine whether it is within the effective glue connected area value range; then calculates and obtains the characteristic shape expression value of the connected region, and compares it with the characteristic shape expression threshold, and calculates the invalid colloid thickness value at each pixel coordinate based on the invalid colloid signal; removes the invalid colloid through laser, which can solve the problem of adhesive residue in the pattern area during flexographic printing production. The distribution of the glue layer on the flexographic plate is detected through image recognition technology to achieve automatic positioning and glue removal, which can ensure the cleanliness of the pattern area while protecting non-target areas.

[0109] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

[0110] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A flexographic printing automatic positioning and degumming process based on image recognition technology, characterized in that: The following steps are involved: Step 1: Based on the camera position data and the light source position data, the incident angle value θ of the light source is calculated and adjusted, and the image of the printing plate surface is collected. Then, the coordinates of the pixels in the image are marked, and the three-channel pixel value of each pixel in the image is obtained, and the grayscale value of the pixel is calculated and obtained; Step 2: Binarize the grayscale values ​​of pixels in the image, determine and obtain the colloid pixels, and then mark them; Step 3: Based on the marked pixels containing colloids, traverse and obtain the pixel area value of each colloid connected region, and record it as LS; determine whether the pixel area LS of the connected region is within the effective glue connected area value range [LSmin, LSmax]; Obtaining characteristic determination signals or invalid colloid signals; Step 4: Based on the characteristic judgment signal, calculate and obtain the characteristic shape performance value XB of the connected area, and compare the characteristic shape performance value XB with the characteristic shape performance threshold Xby, and obtain a valid colloid signal or an invalid colloid signal; The characteristic shape performance value XB is calculated as follows: S41: Obtaining the side length data of the connected area, including: the maximum horizontal span value Wk and the maximum vertical span value Wh of the connected area; pass Calculate the aspect ratio KH of the connected area; S42: Based on the side length data of the connected region and the pixel area value LS of the connected region; pass Calculate the compactness value JC of the connected area; S43: Obtain the perimeter value Cz of the connected region based on the pixel area value LS of the connected region; pass Calculate and obtain the heterogeneous value YX of the connected area; S44: Based on the aspect ratio KH, the compact value JC and the profile value YX, Calculate and obtain the characteristic shape performance value XB; Step 5: Based on the invalid colloid signal, obtain the pixel coordinate set of the invalid colloid connected area, traverse the invalid colloid on each pixel in the pixel coordinate set through the laser sensor, obtain the laser scanning data of each pixel coordinate, and calculate the invalid colloid thickness value QC on each pixel coordinate; select the corresponding laser energy density through the laser energy density relationship table to remove the invalid colloid.

2. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: The camera position data includes the camera horizontal distance value Lca, and the light source position data includes the light source height value Hg; then, by Calculate and obtain the incident angle value θ of the light source.

3. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: The grayscale value of the pixel in the image is obtained as follows: Mark the pixel in the upper left corner of the image as the origin (0, 0), then record the horizontal column of pixels as the X-axis direction and the vertical column as the Y-axis direction, and obtain the coordinates of each pixel as (x, y); Extract the red, green, and blue channel pixel values ​​of each pixel in the image and mark them as the red channel pixel value R （x，y） , green channel pixel value G （x，y） and blue channel pixel value B （x，y） ; pass Calculate the pixel gray value H （x，y） , where a is the preset proportional coefficient of the red channel, b is the preset proportional coefficient of the green channel, c is the preset proportional coefficient of the blue channel, and a, b and c are all greater than 0.

4. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: In the step 2, the step of marking the pixel points where the colloid exists on the surface includes: traversing the gray value of each pixel point, and marking the gray value H of the pixel point （x，y） Compare with the pixel grayscale threshold HY; If the pixel gray value H （x，y） If it is greater than or equal to the pixel grayscale threshold HY, the pixel is marked as 1; If the pixel gray value H （x，y） If the grayscale value is less than the pixel grayscale threshold HY, the pixel is marked as 0.

5. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: In the step 3, the colloid connected area determines whether the pixels are connected in a four-connectivity manner, and the directions of the four-connectivity are the four directions of up, down, left, and right.

6. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 5, characterized in that: Determine whether the pixel area LS of the connected region is within the effective glue connected area range [LSmin, LSmax]: If the pixel area LS of the connected region is within the effective glue connected area range [LSmin, LSmax], a feature determination signal is generated; If the pixel area LS of the connected region is not within the effective glue connected area range [LSmin, LSmax], an invalid colloid signal is generated.

7. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: Compare the characteristic shape representation value XB with the characteristic shape representation threshold Xby: If the characteristic shape representation value XB is greater than the characteristic shape representation threshold value Xby, an invalid colloid signal is generated; If the characteristic shape representation value XB is less than or equal to the characteristic shape representation threshold value Xby, a valid colloid signal is generated.

8. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 1, characterized in that: The laser scanning data in step five includes the scanning laser emission time point FD and the scanning laser reception time point SD.

9. The automatic positioning and degumming process for flexographic printing based on image recognition technology according to claim 8, characterized in that: The calculation method of the invalid colloid thickness value QC is: , where υ is the speed of light.

Images