A linear image edge detection method for gravure coating

Abstract

The invention provides a linear image edge patrol method for gravure coating, which relates to the field of image edge patrol, and comprises: obtaining an equipment image of an equipment to be subjected to gravure coating processing, and performing a first edge patrol according to a preset edge patrol algorithm to obtain a first edge patrol image; performing a second edge patrol based on a preset edge patrol planning scheme in combination with a second edge patrol algorithm to obtain a second edge patrol image; analyzing a first standard equipment image of the gravure coating equipment to obtain a standard equipment image; performing a first correction on an image grayscale value in the standard equipment image based on an image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image; performing micro-correction on a special-shaped area of ​​the first corrected edge patrol image based on the second edge patrol image to obtain a comprehensive edge patrol image; performing different edge patrols on a target gravure coating equipment by using different edge patrol algorithms, and adjusting according to different edge patrol images, so that the edge patrol of the gravure coating equipment is more accurate, and the working efficiency of the gravure coating equipment is improved.

Description

Technical Field

[0001] The invention relates to the field of image edge detection, and in particular to a linear image edge detection method for gravure coating. Background Art

[0002] At present, with the progress of society, the printing industry has developed rapidly. Low cost, timeliness, and accuracy have become the primary demands of customers. When detecting the edge of electrode coating in the lithium battery industry, edge patrol algorithms are often used to assist coating. This requires a detection algorithm that can find the location information of the edge image by scanning the electrode coating image.

[0003] However, existing image edge detection methods have problems such as a single edge detection algorithm and prone to errors in edge detection results.

[0004] Therefore, the present invention provides a linear image edge detection method for gravure coating. Summary of the invention

[0005] The present invention provides a linear image edge patrol method for gravure coating, which is used to perform different edge patrols on a target gravure coating device by using different edge patrol algorithms, and to adjust the edge patrol according to different edge patrol images, thereby making the edge patrol result of the target gravure coating device more accurate and improving the working efficiency of the gravure coating device.

[0006] The present invention provides a linear image edge detection method for gravure coating, comprising:

[0007] Step 1: acquiring a device image of a coating device that needs to be subjected to gravure coating processing based on a scanning device, and performing a first edge patrol on the device image according to a preset edge patrol algorithm to obtain a first edge patrol image;

[0008] Step 2: Perform a second patrol on the device image based on the preset patrol planning scheme combined with the second patrol algorithm to obtain a second patrol image;

[0009] Step 3: Obtaining a standard device image based on processing and analyzing the first standard device image of the target gravure coating device;

[0010] Step 4: performing a first correction on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image;

[0011] Step 5: Based on the second edge inspection image, the irregular-shaped area of ​​the first corrected edge inspection image is slightly corrected to obtain a comprehensive edge inspection image, thereby obtaining an edge inspection result.

[0012] In a possible implementation, a device image of a coating device that needs to be subjected to gravure coating processing is acquired based on a scanning device, and a first edge patrol is performed on the device image according to a preset edge patrol algorithm to obtain a first edge patrol image, including:

[0013] Step 11: Acquire several original images of coating equipment that needs to be subjected to gravure coating processing based on a scanning device;

[0014] Step 12: performing image clarity comparison based on the acquired original images of several devices, and obtaining the optimal original image of the device as the device image of the current coating device based on the comparison result;

[0015] Step 13: Based on the equipment parameters of the current coating equipment, the inspection algorithm in the inspection algorithm database with the highest degree of consistency with the current coating equipment is selected as the first inspection algorithm to perform a first inspection on the equipment image to obtain a first inspection image.

[0016] In a possible implementation, performing a second patrol on the device image based on a preset patrol planning scheme in combination with a second patrol algorithm to obtain a second patrol image includes:

[0017] Step 21: Based on the preset patrol planning scheme, select the patrol algorithm with the highest degree of consistency with the current planning scheme from the patrol algorithm database as the second initial patrol algorithm of the current coating device;

[0018] Step 22: Compare the second initial edge patrol algorithm with the first edge patrol algorithm, and adjust the algorithm based on the comparison result to obtain a second edge patrol algorithm;

[0019] Step 23: Perform a second edge patrol on the device image based on the preset edge patrol planning scheme and the corresponding second edge patrol algorithm to obtain a second edge patrol image.

[0020] In a possible implementation, the second initial edge patrol algorithm is compared with the first edge patrol algorithm, and the algorithm is adjusted based on the comparison result to obtain the second edge patrol algorithm, including:

[0021] If it is determined according to the comparison result that there is an algorithm difference between the second initial edge patrol algorithm and the first edge patrol algorithm, the second initial edge patrol algorithm is used as the second edge patrol algorithm;

[0022] Otherwise, the patrol algorithm with the second highest degree of consistency with the current planning scheme is extracted from the patrol algorithm database as the second patrol algorithm.

[0023] In a possible implementation, based on processing and analyzing a first standard device image of a target gravure coating device, a standard device image is obtained, including:

[0024] Step 31: obtaining standard equipment parameters of the current gravure coating equipment, and performing gravure simulation under standard conditions in a virtual machine based on the standard equipment parameters to obtain a simulated equipment image, and using the simulated equipment image as a first standard image of the target gravure coating equipment;

[0025] Step 32: Obtain basic image parameters of the first edge patrol image, and perform image processing on the first standard image based on the basic image parameters to obtain a standard device image.

[0026] In a possible implementation, performing a first correction on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image includes:

[0027] Step 41: extracting all image grayscale values ​​in the first edge patrol image as first grayscale values, and extracting all image grayscale values ​​in the standard device image as second grayscale values;

[0028] Step 42: Fill the first edge patrol image and the standard device image into the same coordinate system, and overlap the images in the same coordinate system;

[0029] Step 43: based on the image overlap result, pixels of the portion where there is no grayscale difference between the first edge patrol image and the standard device image are removed;

[0030] Step 44: marking the first grayscale value and the second grayscale value of each remaining pixel after the removal, and constructing a first grayscale sub-image and a second grayscale sub-image;

[0031] Step 45: performing grayscale range compression processing on the first grayscale sub-image and the second grayscale sub-image respectively;

[0032] Step 46: extract the first grayscale value of each pixel position in the compressed first grayscale sub-image and the second grayscale value of each pixel position in the compressed second grayscale sub-image to obtain a first grayscale value table, and determine the grayscale difference value between each compressed first grayscale value and the corresponding compressed second grayscale value in the first grayscale value table;

[0033] When the grayscale difference value is less than the preset standard difference value, the compressed first grayscale value of the corresponding pixel position is adjusted by using the compressed second grayscale value;

[0034] Otherwise, the image with the second highest definition in the original image of the device is processed as the device image to obtain a new first edge patrol image, and the image overlap and grayscale difference value are obtained and adjusted again;

[0035] Step 47: performing a first correction on the grayscale value of the corresponding position of the corresponding first edge patrol image based on the adjusted first grayscale value, and obtaining a first corrected edge patrol image based on the first corrected first edge patrol image.

[0036] In a possible implementation, micro-correction is performed on the irregular-shaped area of ​​the first corrected edge patrol image based on the second edge patrol image to obtain a comprehensive edge patrol image, thereby obtaining an edge patrol result, including:

[0037] Step 51: Acquire all irregular parts in the first corrected edge patrol image, and perform irregular marking on the pixel interval corresponding to each pixel point of the irregular part, and mark the irregular part corresponding to the second edge patrol image with the irregular mark;

[0038] Step 52: performing a second comparison between the grayscale value of each pixel in the irregularly shaped mark area of ​​the first corrected edge patrol image and the grayscale value of each pixel in the corresponding irregularly shaped mark area in the second edge patrol image;

[0039] Step 53: performing micro-correction on the grayscale value of the irregularly shaped mark area of ​​the first corrected edge inspection image based on the second grayscale value comparison result;

[0040] Step 54: Corresponding the grayscale value after micro-correction to the first corrected edge inspection image to perform image micro-correction, and using the image micro-correction result as the comprehensive edge inspection image of the target gravure coating device to obtain the edge inspection result of the target gravure coating device.

[0041] In a possible implementation, after obtaining the border patrol result, the method further includes: determining the accuracy of the border patrol result, specifically including:

[0042] Step 01: Obtain the edge inspection result of the current gravure coating equipment, and obtain the standard edge inspection result based on the gravure coating equipment;

[0043] Step 02: Compare the standard edge inspection result with the edge inspection result of the current gravure coating equipment to obtain the consistency between the two edge inspection results;

[0044] Step 03: The consistency of the results is used as the edge patrol accuracy of the current gravure coating device, and compared with the preset edge patrol accuracy threshold range;

[0045] If the current edge patrol accuracy is within the preset accuracy threshold range, the accuracy of the current edge patrol result is judged to be qualified and is used as the final linear image edge patrol result of the current gravure coating device.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] By using different edge patrol algorithms to perform different edge patrols on the target gravure coating equipment, and performing edge patrol adjustments according to different edge patrol images, the edge patrol results of the target gravure coating equipment are made more accurate, and the working efficiency of the gravure coating equipment is improved.

[0048] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0049] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0051] Figure 1 It is a flow chart of a linear image edge detection method for gravure coating in an embodiment of the present invention;

[0052] Figure 2 This is a flow chart of obtaining a first edge patrol image in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0054] Embodiment 1:

[0055] The embodiment of the present invention provides a linear image edge detection method for gravure coating, such as Figure 1 As shown, including:

[0056] Step 1: acquiring a device image of a coating device that needs to be subjected to gravure coating processing based on a scanning device, and performing a first edge patrol on the device image according to a preset edge patrol algorithm to obtain a first edge patrol image;

[0057] Step 2: Perform a second patrol on the device image based on the preset patrol planning scheme combined with the second patrol algorithm to obtain a second patrol image;

[0058] Step 3: obtaining a standard device image based on processing and analyzing the first standard device image of the target gravure coating device;

[0059] Step 4: performing a first correction on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image;

[0060] Step 5: Based on the second edge inspection image, the irregular-shaped area of ​​the first corrected edge inspection image is slightly corrected to obtain a comprehensive edge inspection image, thereby obtaining an edge inspection result.

[0061] In this embodiment, the device image refers to an image obtained by scanning and processing the gravure coating device that needs to be subjected to gravure coating processing using a scanning device.

[0062] In this embodiment, the first edge patrol image refers to an edge patrol result obtained after performing edge patrol on the device image according to the first edge patrol algorithm.

[0063] In this embodiment, the preset edge patrol algorithm and the second edge patrol algorithm refer to the edge patrol algorithm that is determined based on the equipment parameters of the gravure coating equipment and the preset edge patrol planning scheme and has the highest degree of consistency with the current gravure coating equipment.

[0064] In this embodiment, the second edge patrol image refers to an edge patrol result obtained after performing edge patrol on the device image according to the second edge patrol algorithm.

[0065] In this embodiment, the first standard device image refers to a simulated image obtained after the target gravure coating device performs gravure coating simulation under a standard state.

[0066] In this embodiment, the standard device image refers to an image obtained by performing image processing on the first standard image according to the basic image parameters of the first edge patrol image. For example, the image processing includes adjusting the resolution of the image, adjusting the size of the image, and the like.

[0067] In this embodiment, the image grayscale value refers to the color depth of pixels contained in a black-and-white image, wherein the grayscale value range of the image grayscale value is generally [0, 255].

[0068] In this embodiment, the first corrected edge patrol image refers to an image obtained by correcting the first edge patrol image according to the standard device image.

[0069] In this embodiment, the micro-correction refers to adjusting the irregular-shaped portion of the first corrected edge patrol image according to the second edge patrol image.

[0070] In this embodiment, the comprehensive edge patrol image refers to an edge patrol image obtained by performing micro-correction on the first corrected edge patrol image.

[0071] The beneficial effect of the above technical solution is: by using different edge patrol algorithms to perform different edge patrols on the target gravure coating equipment, and adjusting the edge patrol according to different edge patrol images, the edge patrol result of the target gravure coating equipment is more accurate, and the working efficiency of the gravure coating equipment is improved.

[0072] Embodiment 2:

[0073] Based on Example 1, a device image of a coating device that needs to be subjected to gravure coating processing is obtained based on a scanning device, and a first edge patrol is performed on the device image according to a preset edge patrol algorithm to obtain a first edge patrol image, such as Figure 2 As shown, including:

[0074] Step 11: Acquire several original images of coating equipment that needs to be subjected to gravure coating processing based on a scanning device;

[0075] Step 12: performing image clarity comparison based on the acquired original images of several devices, and obtaining the optimal original image of the device as the device image of the current coating device based on the comparison result;

[0076] Step 13: Based on the equipment parameters of the current coating equipment, the inspection algorithm in the inspection algorithm database with the highest degree of consistency with the current coating equipment is selected as the first inspection algorithm to perform a first inspection on the equipment image to obtain a first inspection image.

[0077] In this embodiment, the original image of the device refers to an image obtained by scanning the gravure coating device that needs to be subjected to gravure coating processing using a scanning device.

[0078] In this embodiment, the image definition refers to the image quality of the scanned image determined according to different scanning devices, wherein the higher the image quality, the higher the image definition.

[0079] In this embodiment, the optimal device original image refers to a device original image with the highest image clarity obtained by comparing the image clarity of several device original images.

[0080] In this embodiment, the first edge patrol algorithm refers to an image edge patrol algorithm that is selected from an edge patrol algorithm database according to equipment parameters of the coating equipment and has the highest degree of consistency with the gravure coating equipment that currently needs to perform gravure coating processing.

[0081] In this embodiment, the first edge patrol image refers to an edge patrol result obtained after performing image edge patrol on the optimal device original image according to the first edge patrol algorithm.

[0082] The beneficial effect of the above technical solution is that the first edge patrol image is obtained by analyzing the equipment parameters, and multiple image corrections are performed on the first edge patrol image, so that the edge patrol of the gravure coating equipment can be made more accurate.

[0083] Embodiment 3:

[0084] Based on Example 2, a second patrol is performed on the device image based on a preset patrol planning scheme combined with a second patrol algorithm to obtain a second patrol image, including:

[0085] Step 21: Based on the preset patrol planning scheme, select the patrol algorithm with the highest degree of consistency with the current planning scheme from the patrol algorithm database as the second initial patrol algorithm of the current coating device;

[0086] Step 22: Compare the second initial edge patrol algorithm with the first edge patrol algorithm, and adjust the algorithm based on the comparison result to obtain a second edge patrol algorithm;

[0087] Step 23: Perform a second edge patrol on the device image based on the preset edge patrol planning scheme and the corresponding second edge patrol algorithm to obtain a second edge patrol image.

[0088] In this embodiment, the patrol planning scheme refers to a patrol planning scheme for the gravure coating device that is predetermined according to the device form of the target gravure coating device. For example, the patrol planning scheme includes the angle of the device to patrol, the distance from the device, etc.

[0089] In this embodiment, the second initial edge patrol algorithm refers to an edge patrol algorithm obtained by screening from an edge patrol algorithm database according to an edge patrol planning scheme.

[0090] In this embodiment, the second edge patrol algorithm refers to comparing the second initial edge patrol algorithm with the first edge patrol algorithm. If the second initial edge patrol algorithm is inconsistent with the first edge patrol algorithm, the second initial edge patrol algorithm is used as the second edge patrol algorithm. Otherwise, the algorithm is re-extracted from the edge patrol algorithm database to obtain the second edge patrol algorithm.

[0091] In this embodiment, the second edge patrol image refers to an edge patrol image obtained after performing equipment edge patrol on the target gravure coating equipment according to the second edge patrol algorithm.

[0092] The beneficial effect of the above technical solution is that by analyzing the edge patrol planning scheme to obtain the second edge patrol image, the first edge patrol image can be corrected, thereby making the edge patrol of the gravure coating equipment more accurate.

[0093] Embodiment 4:

[0094] Based on Example 3, the second initial edge patrol algorithm is compared with the first edge patrol algorithm, and the algorithm is adjusted based on the comparison result to obtain a second edge patrol algorithm, including:

[0095] If it is determined according to the comparison result that there is an algorithm difference between the second initial edge patrol algorithm and the first edge patrol algorithm, the second initial edge patrol algorithm is used as the second edge patrol algorithm;

[0096] Otherwise, the patrol algorithm with the second highest degree of consistency with the current planning scheme is extracted from the patrol algorithm database as the second patrol algorithm.

[0097] The beneficial effect of the above technical solution is: by analyzing the patrol planning scheme, a more consistent second patrol algorithm is obtained, thereby obtaining a second patrol image, and the first patrol image can be corrected, thereby making the patrol of the gravure coating equipment more accurate.

[0098] Embodiment 5:

[0099] Based on Example 4, based on the processing and analysis of the first standard device image of the target gravure coating device, a standard device image is obtained, including:

[0100] Step 31: obtaining standard equipment parameters of the current gravure coating equipment, and performing gravure simulation under standard conditions in a virtual machine based on the standard equipment parameters to obtain a simulated equipment image, and using the simulated equipment image as a first standard image of the target gravure coating equipment;

[0101] Step 32: Obtain basic image parameters of the first edge patrol image, and perform image processing on the first standard image based on the basic image parameters to obtain a standard device image.

[0102] In this embodiment, the standard equipment parameters refer to the parameters of the equipment that needs to perform the gravure coating process, including the equipment moving speed, the equipment moving direction, basic equipment parameters, etc.

[0103] In this embodiment, the simulated device image refers to a simulated image obtained after inputting standard device parameters into a virtual machine to perform gravure simulation.

[0104] In this embodiment, the basic image parameters refer to parameters such as resolution, size, color, and clarity of the first standard image.

[0105] In this embodiment, the standard device image refers to an image obtained by performing image processing on the first standard image according to the basic image parameters of the first edge patrol image. For example, the image processing includes adjusting the resolution of the image, adjusting the size of the image, and the like.

[0106] The beneficial effect of the above technical solution is: by acquiring the standard equipment image of the target gravure coating equipment, the first edge patrol image is corrected, and the second edge patrol image is combined for further correction, so that the edge patrol of the linear image of gravure coating can be made more accurate.

[0107] Embodiment 6:

[0108] Based on Example 5, a first correction is performed on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image, including:

[0109] Step 41: extracting all image grayscale values ​​in the first edge patrol image as first grayscale values, and extracting all image grayscale values ​​in the standard device image as second grayscale values;

[0110] Step 42: Fill the first edge patrol image and the standard device image into the same coordinate system, and overlap the images in the same coordinate system;

[0111] Step 43: based on the image overlap result, pixels of the portion where there is no grayscale difference between the first edge patrol image and the standard device image are removed;

[0112] Step 44: marking the first grayscale value and the second grayscale value of each remaining pixel after the removal, and constructing a first grayscale sub-image and a second grayscale sub-image;

[0113] Step 45: performing grayscale range compression processing on the first grayscale sub-image and the second grayscale sub-image respectively;

[0114] Step 46: extract the first grayscale value of each pixel position in the compressed first grayscale sub-image and the second grayscale value of each pixel position in the compressed second grayscale sub-image to obtain a first grayscale value table, and determine the grayscale difference value between each compressed first grayscale value and the corresponding compressed second grayscale value in the first grayscale value table;

[0115] When the grayscale difference value is less than the preset standard difference value, the compressed first grayscale value of the corresponding pixel position is adjusted by using the compressed second grayscale value;

[0116] Otherwise, the image with the second highest definition in the original image of the device is processed as the device image to obtain a new first edge patrol image, and the image overlap and grayscale difference value are obtained and adjusted again;

[0117] Step 47: performing a first correction on the grayscale value of the corresponding position of the corresponding first edge patrol image based on the adjusted first grayscale value, and obtaining a first corrected edge patrol image based on the first corrected first edge patrol image.

[0118] In this embodiment, the first grayscale value refers to the color depth of all pixels included in the first edge patrol image.

[0119] In this embodiment, the second grayscale value refers to the color depth of all pixels included in the standard device image.

[0120] In this embodiment, image overlapping refers to overlapping the first edge patrol image and the standard device image so that the two images are in the same coordinate system.

[0121] In this embodiment, the first grayscale sub-image is constructed by the existence of remaining pixels and the corresponding first grayscale values, and the second grayscale sub-image is constructed by the existence of remaining pixels and the corresponding second grayscale values.

[0122] In this embodiment, compression processing refers to a data processing method of reducing redundant information in image data so as to store and transmit data in a more efficient format.

[0123] In this embodiment, the first grayscale value table refers to a data table obtained by extracting the first grayscale value and the second grayscale value of the compressed first grayscale image.

[0124] In this embodiment, the grayscale difference value refers to the difference between the first grayscale value and the corresponding second grayscale value. For example, if the first grayscale value of a pixel is 203 and the second grayscale value is 205, then the grayscale difference value of the two grayscale values ​​is 2, wherein the grayscale difference values ​​are all positive numbers or 0.

[0125] In this embodiment, the first corrected edge patrol image refers to an edge patrol image obtained by adjusting the first grayscale value according to the grayscale difference value and adjusting the grayscale values ​​of corresponding pixels of the first edge patrol image based on the grayscale value adjustment result.

[0126] In this embodiment, adjusting the compressed first grayscale value of the corresponding pixel position by using the compressed second grayscale value includes:

[0127] capturing a first compressed log for the first grayscale sub-image and capturing a second compressed log for the second grayscale sub-image from a log database;

[0128] Extracting compression noise information from the first compression log and inputting it into an information analysis model to construct a noise vector;

[0129] Determine a noise generation path and a noise transfer function of each generation path according to the second noise log, and calculate a noise contribution coefficient for the second grayscale sub-image;

[0130] ;in, Indicates the i1th generated path The noise transfer function of Indicates the i1th generated path The historical noise occurrence probability; Indicates the i1th generated path The degree of historical noise impact; represents the noise contribution coefficient; Indicates the maximum historical noise occurrence probability The corresponding noise contribution coefficient;

[0131] According to the noise contribution coefficient, the noise vector is decomposed to determine a high noise element and a low noise element;

[0132] Determine a compression error region in the first grayscale sub-image according to the first compression index of the high noise element;

[0133] Determine a normal compression region in the first grayscale sub-image according to the second compression index of the low noise element, and adjust the compression error region according to the compression frequency of the normal compression region to obtain an adjusted compression region;

[0134] A new compressed sub-image is constructed based on the adjusted compressed area and the normal compressed area, and the pixel values ​​of the pixels at the same position in the new compressed sub-image are adjusted in combination with the compressed second grayscale sub-image.

[0135] In this embodiment, the log database includes compression information of different sub-images and includes the grayscale compression status of each pixel at each position, and thus the compression log can be captured from the database.

[0136] In this embodiment, the compression noise information refers to the noise generated during the compression process. Because the compression is performed in a certain preset manner during the compression process, it is inevitable that the compression result may not be exactly the same as the setting due to unstable device signals, and thus there will be certain differences.

[0137] In this embodiment, the information analysis model is obtained by training a neural network model based on the noise generated by the instability of signals of different devices and the noise results obtained by experts evaluating the noise as samples, thereby obtaining a noise vector.

[0138] In this embodiment, the element values ​​in the noise vector that are greater than or equal to the noise contribution coefficient are regarded as high noise elements, and the remaining element values ​​are regarded as low noise elements.

[0139] In this embodiment, the matching compression index and the corresponding area are determined from the element-position-indicator-area mapping table by matching the high-noise elements and the element positions. For example, element 1 and element 3 correspond to position 1 and position 3 respectively, and the indexes 01 and 02 are determined. These two indexes generally affect area 001. Therefore, area 001 is finally used as the compression error area. The principles of the first compression index and the second compression index are similar and will not be repeated here.

[0140] In this embodiment, the compression error area is adjusted according to the compression frequency of the normal area, mainly to alleviate the situation where noise reaches pixel error, restore the error pixel points as much as possible, and obtain the adjusted compression area.

[0141] In this embodiment, the compressed first grayscale sub-image of the new compressed sub-image value is an image after adjustment.

[0142] In this embodiment, the adjustment of the pixel value is: the adjusted pixel value obtained by averaging the value of the same pixel point in the new compressed sub-image and the value of the same pixel point in the second grayscale sub-image.

[0143] In this embodiment, the compressed first grayscale sub-image is adjusted starting from the noise direction to ensure the rationality of sub-image acquisition and provide a reliability basis for subsequent acquisition of pixel values.

[0144] The beneficial effect of the above technical solution is that by comparing the grayscale value of the edge patrol image with the grayscale value of the standard equipment image, the grayscale value is adjusted, so that the edge patrol result of the edge patrol image can be more accurate.

[0145] Embodiment 7:

[0146] Based on Example 6, the irregular-shaped area of ​​the first corrected edge patrol image is slightly corrected based on the second edge patrol image to obtain a comprehensive edge patrol image, thereby obtaining an edge patrol result, including:

[0147] Step 51: Acquire all irregular parts in the first corrected edge patrol image, and perform irregular marking on the pixel interval corresponding to each pixel point of the irregular part, and mark the irregular part corresponding to the second edge patrol image with the irregular mark;

[0148] Step 52: performing a second comparison between the grayscale value of each pixel in the irregularly shaped mark area of ​​the first corrected edge patrol image and the grayscale value of each pixel in the corresponding irregularly shaped mark area in the second edge patrol image;

[0149] Step 53: performing micro-correction on the grayscale value of the irregularly shaped mark area of ​​the first corrected edge inspection image based on the second grayscale value comparison result;

[0150] Step 54: Corresponding the grayscale value after micro-correction to the first corrected edge inspection image to perform image micro-correction, and using the image micro-correction result as the comprehensive edge inspection image of the target gravure coating device to obtain the edge inspection result of the target gravure coating device.

[0151] In this embodiment, the first corrected edge patrol image refers to a new edge patrol image obtained by adjusting the image grayscale value at the corresponding position of the first edge patrol image according to the first grayscale value.

[0152] In this embodiment, the irregular-shaped portion refers to the turning corners and other portions of the gravure coating device during the device edge patrol process.

[0153] In this embodiment, the irregular shape marking refers to marking the pixel points of the irregular shape part.

[0154] In this embodiment, the second edge patrol image refers to an edge patrol image obtained after performing edge patrol on the gravure coating device according to the second edge patrol algorithm.

[0155] In this embodiment, the second comparison refers to comparing the grayscale values ​​of the pixels in the irregularly marked area of ​​the irregularly shaped part in the first corrected edge patrol image and the corresponding area in the second edge patrol image.

[0156] In this embodiment, micro-correction refers to adjusting the grayscale value of the irregular-shaped part in the first corrected edge patrol image according to the second comparison result to achieve image correction.

[0157] In this embodiment, the comprehensive edge patrol image refers to an image obtained by performing micro-correction on the first corrected edge patrol image based on the second edge patrol image.

[0158] The beneficial effect of the above technical solution is that by comparing and adjusting the irregular parts of the edge inspection image, the edge inspection of the linear image can be made more accurate.

[0159] Embodiment 8:

[0160] Based on the first embodiment, after obtaining the border patrol result, the method further includes: determining the accuracy of the border patrol result, specifically including:

[0161] Step 01: Obtain the edge inspection result of the current gravure coating equipment, and obtain the standard edge inspection result based on the gravure coating equipment;

[0162] Step 02: Compare the standard edge inspection result with the edge inspection result of the current gravure coating equipment to obtain the consistency between the two edge inspection results;

[0163] Step 03: The consistency of the results is used as the edge patrol accuracy of the current gravure coating device, and compared with the preset edge patrol accuracy threshold range;

[0164] If the current edge patrol accuracy is within the preset accuracy threshold range, the accuracy of the current edge patrol result is judged to be qualified and is used as the final linear image edge patrol result of the current gravure coating device.

[0165] In this embodiment, the standard edge patrol result refers to the standard edge patrol result of the gravure coating device that performs gravure coating processing as needed.

[0166] In this embodiment, the result consistency refers to the consistency between the standard edge scanning result of the same gravure coating device and the currently obtained edge scanning result when the two results are compared.

[0167] In this embodiment, the edge patrol accuracy refers to the equipment edge patrol accuracy of the current gravure coating equipment determined according to the degree of consistency of the results.

[0168] In this embodiment, the preset edge patrol accuracy threshold range refers to a threshold range of maximum and minimum thresholds of the edge patrol accuracy of the current gravure coating device determined according to the allowable error of the gravure coating process.

[0169] The beneficial effect of the above technical solution is that by checking the accuracy of the edge patrol results, the edge patrol of the gravure coating equipment can be made more accurate, and inaccurate edge patrol results can be adjusted in time, thereby improving the working efficiency of the equipment.

[0170] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A linear image edge inspection method for gravure coating, characterized in that: include: Step 1: acquiring a device image of a coating device that needs to be subjected to gravure coating processing based on a scanning device, and performing a first edge patrol on the device image according to a preset edge patrol algorithm to obtain a first edge patrol image; Step 2: Perform a second patrol on the device image based on the preset patrol planning scheme combined with the second patrol algorithm to obtain a second patrol image; Step 3: obtaining a standard device image based on processing and analyzing the first standard device image of the target gravure coating device; Step 4: performing a first correction on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image; Step 5: Based on the second edge inspection image, the irregular-shaped area of ​​the first corrected edge inspection image is slightly corrected to obtain a comprehensive edge inspection image, thereby obtaining an edge inspection result; Wherein, step 2 includes: Step 21: Based on the preset patrol planning scheme, select the patrol algorithm with the highest degree of consistency with the current planning scheme from the patrol algorithm database as the second initial patrol algorithm of the current coating device; Step 22: Compare the second initial edge patrol algorithm with the first edge patrol algorithm, and adjust the algorithm based on the comparison result to obtain a second edge patrol algorithm, including: If it is determined according to the comparison result that there is an algorithm difference between the second initial edge patrol algorithm and the first edge patrol algorithm, the second initial edge patrol algorithm is used as the second edge patrol algorithm; Otherwise, the patrol algorithm with the second highest consistency with the current planning scheme is extracted from the patrol algorithm database as the second patrol algorithm; Step 23: Perform a second edge patrol on the device image based on the preset edge patrol planning scheme and the corresponding second edge patrol algorithm to obtain a second edge patrol image.

2. A linear image edge detection method for gravure coating according to claim 1, characterized in that: The device image of the coating device that needs to be subjected to the gravure coating process is acquired based on the scanning device, and the device image is subjected to a first edge patrol according to a preset edge patrol algorithm to obtain a first edge patrol image, including: Step 11: Acquire several original images of coating equipment that needs to be subjected to gravure coating processing based on a scanning device; Step 12: performing image clarity comparison based on the acquired original images of several devices, and obtaining the optimal original image of the device as the device image of the current coating device based on the comparison result; Step 13: Based on the equipment parameters of the current coating equipment, the inspection algorithm in the inspection algorithm database with the highest degree of consistency with the current coating equipment is selected as the first inspection algorithm to perform a first inspection on the equipment image to obtain a first inspection image.

3. A linear image edge detection method for gravure coating according to claim 2, characterized in that: Based on the processing and analysis of the first standard device image of the target gravure coating device, a standard device image is obtained, including: Step 31: obtaining standard equipment parameters of the current gravure coating equipment, and performing gravure simulation under standard conditions in a virtual machine based on the standard equipment parameters to obtain a simulated equipment image, and using the simulated equipment image as a first standard equipment image of the target gravure coating equipment; Step 32: Obtain basic image parameters of the first edge patrol image, and perform image processing on the first standard device image based on the basic image parameters to obtain a standard device image.

4. A linear image edge detection method for gravure coating according to claim 3, characterized in that: Performing a first correction on the image grayscale value in the standard device image based on the image grayscale value of the first edge patrol image to obtain a first corrected edge patrol image includes: Step 41: extracting all image grayscale values ​​in the first edge patrol image as first grayscale values, and extracting all image grayscale values ​​in the standard device image as second grayscale values; Step 42: Fill the first edge patrol image and the standard device image into the same coordinate system, and overlap the images in the same coordinate system; Step 43: based on the image overlap result, pixels of the portion where there is no grayscale difference between the first edge patrol image and the standard device image are removed; Step 44: marking the first grayscale value and the second grayscale value of each remaining pixel after the removal, and constructing a first grayscale sub-image and a second grayscale sub-image; Step 45: performing grayscale range compression processing on the first grayscale sub-image and the second grayscale sub-image respectively; Step 46: extract the first grayscale value of each pixel position in the compressed first grayscale sub-image and the second grayscale value of each pixel position in the compressed second grayscale sub-image to obtain a first grayscale value table, and determine the grayscale difference value between each compressed first grayscale value and the corresponding compressed second grayscale value in the first grayscale value table; When the grayscale difference value is less than the preset standard difference value, the compressed first grayscale value of the corresponding pixel position is adjusted by using the compressed second grayscale value; Otherwise, the image with the second highest definition in the original image of the device is processed as the device image to obtain a new first edge patrol image, and the image overlap and grayscale difference value are obtained and adjusted again; Step 47: performing a first correction on the grayscale value of the corresponding position of the corresponding first edge patrol image based on the adjusted first grayscale value, and obtaining a first corrected edge patrol image based on the first corrected first edge patrol image.

5. A linear image edge detection method for gravure coating according to claim 4, characterized in that: Based on the second edge inspection image, the irregular-shaped area of ​​the first corrected edge inspection image is slightly corrected to obtain a comprehensive edge inspection image, thereby obtaining an edge inspection result, including: Step 51: Obtain all irregular parts in the first corrected edge patrol image, and perform irregular marking on the pixel interval corresponding to each pixel point of the irregular part, and mark the corresponding irregular part of the second edge patrol image with the irregular mark; Step 52: performing a second comparison between the grayscale value of each pixel in the irregularly shaped mark area of ​​the first corrected edge patrol image and the grayscale value of each pixel in the corresponding irregularly shaped mark area in the second edge patrol image; Step 53: performing micro-correction on the grayscale value of the irregularly shaped mark area of ​​the first corrected edge inspection image based on the second grayscale value comparison result; Step 54: Corresponding the grayscale value after micro-correction to the first corrected edge inspection image to perform image micro-correction, and using the image micro-correction result as the comprehensive edge inspection image of the target gravure coating device to obtain the edge inspection result of the target gravure coating device.

6. The linear image edge detection method for gravure coating according to claim 1, characterized in that: After obtaining the patrol results, the accuracy of the patrol results is also determined, including: Step 01: Obtain the edge inspection result of the current gravure coating equipment, and obtain the standard edge inspection result based on the gravure coating equipment; Step 02: Compare the standard edge inspection result with the edge inspection result of the current gravure coating equipment to obtain the consistency between the two edge inspection results; Step 03: The consistency of the results is used as the edge patrol accuracy of the current gravure coating device, and compared with the preset edge patrol accuracy threshold range; If the current edge patrol accuracy is within the preset accuracy threshold range, the accuracy of the current edge patrol result is judged to be qualified and is used as the final linear image edge patrol result of the current gravure coating device.

Images