A calibration method, device, medium and equipment

Abstract

This specification discloses a calibration method, device, medium and equipment. Obtain a mark image of the same mark captured by a line scan camera on each machine. For each mark image, determine the average grayscale value of each color in the mark image and the pixel coordinates of each feature point. Select a mark image from each mark image as the standard image, and use the other mark images as the images to be corrected. According to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected, respectively determine the correction parameters of the machine corresponding to each image to be corrected, and the correction parameters are used to correct the image captured by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image. Each machine only needs to shoot once to make the subsequently captured images have the same grayscale value and size consistency, and there is no need to calibrate the machine separately, which reduces the time consumption of calibration.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a calibration method, device, medium and equipment. Background Art

[0002] In the semiconductor industry, due to problems such as the installation accuracy of line scan cameras and light sources, light source types, and lighting conditions, the images taken by line scan cameras on the machine often suffer from pixel distortion and image distortion, which directly affects the accuracy and quality of the manufactured semiconductor products. Therefore, calibrating the line scan cameras on the machine is a very important part of the semiconductor product production process.

[0003] In the prior art, the line scan camera calibration work is usually performed separately for each machine. However, this method of requiring separate calibration for each machine not only increases the calibration time, but also may cause differences between machines.

[0004] To this end, this specification provides a calibration method, device, medium and equipment. Summary of the invention

[0005] This specification provides a calibration method, device, medium and equipment to partially solve the above problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a calibration method, including:

[0008] Obtain a sign image of the same sign taken by a line scan camera on each machine;

[0009] For each logo image, determine the average grayscale value of each color in the logo image and the pixel coordinates of each feature point;

[0010] Select one sign image from each sign image as the standard image, and use the other sign images as images to be corrected;

[0011] According to the average grayscale value of each color in the standard image and the average grayscale value of each color in the images to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in the images to be corrected, the correction parameters of the machine corresponding to each image to be corrected are respectively determined, and the correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0012] Optionally, the logo image is a multi-color image, including a periodically arranged color block pattern formed by combining two or more colors.

[0013] Optionally, the step of determining the average grayscale value of each color in each logo image specifically includes:

[0014] For each logo image, determine the average grayscale value of each color in the logo image.

[0015] Optionally, the step of determining the correction parameters of the machine corresponding to each image to be corrected according to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected specifically includes:

[0016] For each color, determine the average gray value of the color in the standard image and the average gray value of the color in each image to be corrected;

[0017] For each image to be corrected, the grayscale value correction parameter of the machine corresponding to the image to be corrected is determined according to the average grayscale value of the color in the standard image and the average grayscale value of the color in the image to be corrected.

[0018] Optionally, the logo image is a two-color grid image;

[0019] The step of determining the correction parameters of the machine corresponding to the image to be corrected according to the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected comprises:

[0020] For each image to be corrected, determine the horizontal correction parameter of the image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image;

[0021] The row correction parameter of the image to be corrected is determined according to the row average distance of the standard image and the row average distance of the image to be corrected.

[0022] Optionally, the step of determining the horizontal correction parameters of the image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image specifically includes:

[0023] Determine a row of grid points from the image to be corrected as a calibration row, and determine the column average distance between adjacent grid points in the calibration row and an array of horizontal pixel coordinates of the grid points;

[0024] Determine a row of grid points from the standard graph as a standard row, and determine the column average distance between adjacent grid points in the standard row;

[0025] Determine reference grid points from the calibration rows of the image to be corrected, use the average column distance of the standard image as the spacing between adjacent grid points, and use the horizontal pixel coordinates of the reference grid points as a reference to determine the standard horizontal pixel coordinate array of the image to be corrected;

[0026] A polynomial fitting is performed through the standard horizontal pixel coordinate array and the grid point horizontal pixel coordinate array to determine the horizontal correction polynomial of the image to be corrected.

[0027] Optionally, the step of determining reference grid points from the calibration rows of the image to be corrected specifically includes:

[0028] The middle grid point is determined from the calibration row of the image to be corrected as the reference grid point.

[0029] Optionally, the step of determining the row correction parameter of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected specifically includes:

[0030] Determine a column of grid points from the image to be corrected as a calibration column, and determine the row average distance between adjacent grid points in the calibration column; determine a column of grid points from the standard image as a standard column, and determine the row average distance between adjacent grid points in the standard column;

[0031] The ratio of the row average distance of the image to be corrected to the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

[0032] Optionally, the step of determining the row correction parameter of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected specifically includes:

[0033] The column average distance of the standard graph is used as the row average distance;

[0034] Determine a column of grid points from the image to be corrected as a calibration column, and determine a row average distance between adjacent grid points in the calibration column;

[0035] The ratio of the row average distance of the image to be corrected to the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

[0036] Optionally, the sign image is a grid image;

[0037] Before selecting a logo image from each logo image as a standard image, the method further includes:

[0038] Determine a column from the logo as a speed measurement column, and determine the spacing between adjacent grid points in the speed measurement column;

[0039] Determine an average value of each spacing in the speed measurement column, and judge whether the difference between each spacing in the speed measurement column and the average value is within a preset range;

[0040] If yes, proceed to the next steps according to the sign diagram;

[0041] If not, the shooting timing is adjusted, and a new sign image is shot again by the line scan camera that shoots the sign image, until the difference between each spacing in the speed measurement column and the average value is within the preset range.

[0042] Optionally, the sign image is a grid image;

[0043] The step of determining the correction parameters of the machine corresponding to each image to be corrected according to the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected comprises:

[0044] Determine a row of grid points from the standard image as a standard row, and determine the spacing between adjacent grid points in the standard row; for each image to be corrected, determine a row of grid points from the image to be corrected as a calibration row, and determine the spacing between adjacent grid points in the calibration row;

[0045] The spacings between adjacent grid points determined in sequence from the first grid point to the last grid point in the calibration row form a calibration spacing array; the spacings between adjacent grid points determined in sequence from the first grid point to the last grid point in the standard row form a standard spacing array;

[0046] According to the spacings of corresponding positions in the calibrated spacing array and the standard spacing array, correction parameters of the spacings corresponding to each position of the image to be corrected are determined.

[0047] Optionally, the method further includes:

[0048] Determine the machine corresponding to the image to be corrected, and obtain an image acquired by the machine corresponding to the image to be corrected as the image to be corrected;

[0049] According to the correction parameters of the machine corresponding to the image to be corrected, grayscale value correction and pixel coordinate correction are performed on the image to be corrected, so that the grayscale value and pixel coordinate position of the image to be corrected are consistent with those of the image collected by the machine corresponding to the standard image.

[0050] This specification provides a calibration device, including:

[0051] An acquisition module is used to acquire a mark image of the same mark object taken by a line scan camera on each machine;

[0052] A determination module, for determining, for each logo image, an average grayscale value of each color and a pixel coordinate of each feature point in the logo image;

[0053] A selection module, used for selecting one sign image from each sign image as a standard image and taking the other sign images as images to be corrected;

[0054] The calibration module is used to determine the correction parameters of the machine corresponding to each image to be corrected according to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected, respectively. The correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0055] This specification provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above calibration method is implemented.

[0056] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a calibration method when executing the program.

[0057] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0058] The calibration method provided in this specification obtains the mark images of the same mark taken by the line scan cameras on each machine. For each mark image, determine the average grayscale value of each color in the mark image and the pixel coordinates of each feature point. Select one mark image from each mark image as the standard image, and use the other mark images as the images to be corrected. According to the average grayscale value of each color in the standard image and the average grayscale value of each color in the images to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in the images to be corrected, respectively determine the correction parameters of the machine corresponding to each image to be corrected, and the correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0059] The line scan cameras on each machine are used to take photos of the same marker to obtain a sign map. One sign map is selected from each sign map as the standard map, and the remaining sign maps are used as the standard map to determine the correction parameters. This ensures that the images subsequently taken by the line scan cameras on each machine have the same grayscale value and pixel coordinate position as the images collected by the machine corresponding to the standard map. Each machine only needs to shoot once to make the subsequent images have the same grayscale value and size consistency. It is no longer necessary to calibrate the machine separately, which reduces the calibration time. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0061] Figure 1A flowchart of a calibration method provided in an embodiment of this specification;

[0062] Figure 2 A schematic diagram of a correction provided for this specification;

[0063] Figure 3 A schematic diagram of grayscale value correction of a two-color image provided in this specification;

[0064] Figure 4 A schematic diagram of grayscale value correction of a multi-color image provided in this specification;

[0065] Figure 5 A schematic diagram of horizontal and vertical correction of a grid diagram provided in this specification;

[0066] Figure 6 A schematic diagram of a logo correction provided in this manual;

[0067] Figure 7 A schematic diagram of the correction of a sign diagram that does not have a periodic or regular arrangement provided in this specification;

[0068] Figure 8 A schematic diagram of a calibration device provided in this specification;

[0069] Fig. 9 A method corresponding to the Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0071] The calibration method provided in this specification is mainly used in the field of wafer defect detection, and calibration is a preliminary work of defect detection.

[0072] Automated Optical Inspection (AOI) plays a vital role in the semiconductor industry by using high-resolution camera systems and advanced image processing technology to detect defects on the surface of wafers. These defects may include but are not limited to pattern defects, surface irregularities, foreign matter, cracks, etc., which have a direct impact on the performance and reliability of semiconductor devices.

[0073] The key components of the AOI system include the lighting system, the inspection camera system, the inspection workbench, the image processing and recognition system, and the data recording and processing system. The pre-stored template is an important criterion for whether the AOI system can match the production line, while the lighting system and the inspection camera system jointly ensure the accuracy of image acquisition. The image processing and recognition system is responsible for analyzing the collected images and comparing them with the standard images to identify any anomalies. The data recording and processing system is used to store the inspection results for subsequent analysis and process improvement.

[0074] Among them, the correction of optomechanical differences in the inspection camera system is crucial to ensure manufacturing accuracy and quality. Camera differences may be caused by multiple factors, including lens design, manufacturing process, assembly accuracy, and working environment. These differences may cause image distortion, pixel distortion, inaccurate focus, and other problems, which will affect the accuracy of detection. Differences in lighting environments may come from different light source types, lighting conditions, assembly accuracy, and working environment. These differences may cause images to show different brightness and uniformity, and thus cause differences between machines. Taking all the above factors into consideration, the wafer images taken by different machines may not be consistent, and a unified standard cannot be used as a measure to judge abnormalities.

[0075] Therefore, before conducting AOI inspection, it is necessary to calibrate each machine and correct the machine error of the wafer images taken by each machine so that the grayscale value and pixel coordinate position of the wafer images taken by each machine are consistent.

[0076] Generally speaking, the process of calibrating multiple machines is usually to calibrate each machine according to the ideal values ​​of the image parameters taken by the machine in theory. Each machine is calibrated with the ideal value as the target, so that the images taken by the line scan camera on each machine can be used for defect detection.

[0077] This specification provides a calibration method, which takes the image taken by any machine in the same batch of machines as the target image, takes the image parameters of the target image as the correction target, obtains the initial optical information and initial interval size information of each machine, and then performs difference compensation calculation on each machine according to the correction target to complete the correction of each machine. It can achieve optical and dimensional consistency of different machines through only one shooting, without the need for separate compensation, and reduces the time consumption of calibration. Among them, the machine includes a high-resolution CCD camera (i.e., a line scan camera), an optical lens, and a multi-angle color light source, that is, the machine has different lighting modes such as bright field and dark field, as well as adjustable wavelength and brightness. At the same time, a high-precision, high-speed motion platform cooperates with the camera to synchronously scan and obtain the image to be shot, such as a wafer image.

[0078] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0079] Figure 1 A flow chart of a calibration method provided in an embodiment of this specification includes the following steps:

[0080] S100: Obtain a landmark image of the same landmark taken by a line scan camera on each machine.

[0081] The calibration process performed in this specification involves processing of the image. In the embodiments of this specification, the calibration process can be performed by a server. Of course, this specification does not limit which device is used to perform the calibration process. For example, a personal computer, a mobile terminal, and a terminal on a machine can also be used to calibrate and correct the image. For the convenience of description, the following description is based on the server as the execution subject.

[0082] In one or more embodiments of the present specification, the server obtains a landmark image of the same landmark taken by a line scan camera on each machine.

[0083] In one or more embodiments of the present specification, in order to calibrate each machine based on the same standard, the line scan camera on each machine photographs the same marker to obtain a marker image photographed by each machine.

[0084] When the line scan cameras on each machine take photos of the same marker, the motion mechanism on the machine that can at least achieve unidirectional uniform motion makes the line scan camera and the photographed marker move relative to each other. The motion mechanism can move the line scan camera in a unidirectional uniform motion to photograph a fixed marker. The motion mechanism can also move the photographed marker in a unidirectional uniform motion to photograph it with a fixed line scan camera.

[0085] It is worth noting that when the line scan cameras on various machines shoot the same marker, the hardware parameters such as light source brightness and movement speed set on each machine remain consistent.

[0086] S102: For each logo image, determine the average grayscale value of each color and the pixel coordinates of each feature point in the logo image.

[0087] In one or more embodiments of the present specification, the server determines, for each logo image, an average grayscale value of each color in the logo image and the pixel coordinates of each feature point in the logo image, wherein the average grayscale value of each color in the logo image is initial optical information.

[0088] Specifically, the server determines the average grayscale value of each color in the logo image by simply adding up the grayscale values ​​of each color in the logo image and then calculating the average value.

[0089] For the pixel coordinates of each feature point in the logo image, the pixel coordinates of the feature point can be determined by finding corner points. For example, if there is a grid in the logo image, the grid lines in the logo image can be highlighted by an edge detection algorithm, and then the corner points of each feature point can be identified and determined by a corner point detection algorithm. Then, the pixel coordinates of the feature point can be determined by the corner point position information of each feature point. Of course, the method for determining the pixel coordinates of the feature point is not limited in this specification, and the pixel coordinates of the feature point can be selected and determined according to the actual situation.

[0090] It is worth mentioning that for the logo images photographed by the line scan cameras on each machine, it is necessary to meet the requirement that each color area in the photographed logo image is neither overexposed nor underexposed, which can be judged by means such as the grayscale histogram of the logo image.

[0091] In one or more embodiments of the present specification, the logo image captured by the line scan camera on each machine may be a multi-color image, including an image having a periodically arranged color block pattern formed by combining two or more colors.

[0092] S104: Select one of the landmark images as the standard image, and use the other landmark images as images to be corrected.

[0093] In one or more embodiments of the present specification, in order to make the images captured by multiple machines in the calibration process all converge to the images captured by one of the machines, the server selects a logo image from each logo image as the standard image, and uses the other logo images as images to be corrected. Through subsequent steps, the correction parameters of each image to be corrected are determined by correcting the image to be corrected toward the standard image.

[0094] It is worth noting that the server selects a logo image from each logo image as the standard image, which can be a random selection of a logo image from each logo image as the standard image. It can also be selected according to a preset rule, for example, the logo image taken by the machine with the most forward sequence number among the machines is used as the standard image. In this specification, there is no restriction on the method of selecting a logo image as the standard image, which can be set according to the actual situation.

[0095] S106: According to the average grayscale value of each color in the standard image and the average grayscale value of each color in the image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in the image to be corrected, respectively determine the correction parameters of the machine corresponding to each image to be corrected, and the correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0096] In one or more embodiments of the present specification, the server determines the correction parameters of the machine corresponding to each image to be corrected based on the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected. The correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected, that is, to perform difference compensation calculation to keep it consistent with the standard image.

[0097] In one or more embodiments of the present specification, the server determines the average grayscale value of each color in each logo image, and then determines the average grayscale value of the color in the standard image and the average grayscale value of the color in each image to be corrected.

[0098] For each image to be corrected, the grayscale value correction parameter of the machine corresponding to the image to be corrected is determined according to the average grayscale value of the color in the standard image and the average grayscale value of the color in the image to be corrected.

[0099] In one or more embodiments of the present specification, when the marker image is a two-color grid image, the server determines the horizontal correction parameters of each image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image.

[0100] Specifically, a row of grid points is determined from the image to be corrected as the calibration row, and the column average distance of the spacing between adjacent grid points in the calibration row and the grid point horizontal pixel coordinate array are determined. That is, the spacing between two adjacent grid points in the calibration row is calculated as the initial spacing size information. According to the calculated spacing between two adjacent grid points, the average value of the spacing between adjacent grid points in the calibration row is determined as the column average distance. In addition, the pixel coordinates of each grid point in the calibration row are determined. Since the logo image is a two-color grid image, which is a two-dimensional image, the pixel coordinates are composed of coordinates in the horizontal and vertical directions. Here, it is only necessary to select the horizontal pixel coordinates of each grid point in the calibration row to form the grid point horizontal pixel coordinate array.

[0101] A row of grid points is determined from the standard graph as a standard row, and the column average distance between adjacent grid points in the standard row is determined.

[0102] The reference grid points are determined from the calibration rows of the image to be corrected, the average column distance of the standard image is used as the spacing between adjacent grid points, and the horizontal pixel coordinates of the reference grid points are used as the reference to determine the standard horizontal pixel coordinate array of the image to be corrected.

[0103] Polynomial fitting is performed through the standard horizontal pixel coordinate array and the grid point horizontal pixel coordinate array to determine the horizontal correction polynomial of the image to be corrected.

[0104] It is worth noting that, in this specification, the column average distances of the spacings between adjacent grid points in each row of the image to be corrected or the standard image may be added and then averaged, and the result obtained may be used as the column average distance.

[0105] The row correction parameters of the image to be corrected are determined according to the row average distance of the standard image and the row average distance of the image to be corrected. Specifically, a column of grid points is determined from the image to be corrected as a calibration column, and the row average distance of the spacing between adjacent grid points in the calibration column is determined, which is also the initial spacing size information of the image to be corrected. A column of grid points is determined from the standard image as a standard column, and the row average distance of the spacing between adjacent grid points in the standard column is determined. The ratio of the row average distance of the image to be corrected and the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

[0106] It is worth noting that, in this specification, the row average distances between adjacent grid points in each column of the image to be corrected or the standard image may be added and then averaged, and the result obtained may be used as the row average distance.

[0107] In one or more embodiments of the present specification, in theory, in a two-color grid map, the grid point spacing in the horizontal direction and the vertical direction is the same, that is, the grid point spacing in each row is consistent with the grid point spacing in each column. Therefore, the server can also use the column average distance of the standard map as the row average distance. Determine a column of grid points from the image to be corrected as a calibration column, and determine the row average distance of the spacing between adjacent grid points in the calibration column. The ratio of the row average distance of the image to be corrected and the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

[0108] Figure 1 The flowchart of the calibration method provided in this specification includes: Step S100: Obtain a mark image of the same mark object taken by the line scan camera on each machine. Step S102: For each mark image, determine the average grayscale value of each color and the pixel coordinates of each feature point in the mark image. Step S104: Select a mark image from each mark image as the standard image, and use the other mark images as the images to be corrected. Step S106: According to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected, respectively determine the correction parameters of the machine corresponding to each image to be corrected, and the correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0109] In one or more embodiments of the present specification, the logo image is not limited to a two-color image, but can also be a multi-color image composed of multiple colors. If it is a multi-color image, the gray value correction parameters can be determined by using similar technical means as the above two-color image.

[0110] By obtaining the marker images captured by the line scan cameras on each machine platform for the same marker, selecting one of the marker images as the standard image, and using the standard image as a reference for the remaining marker images, the correction parameters are determined. This enables the images subsequently captured by the line scan cameras on each machine platform to have the same grayscale values and pixel coordinate positions as the images captured by the machine platform corresponding to the standard image. By achieving this, each machine platform only needs to capture images once, and the subsequent captured images will have the same grayscale values and size consistency, eliminating the need for individual calibration of each machine platform and reducing the calibration time.

[0111] In addition, in one or more embodiments of this specification, the step of determining the reference grid points from the calibration rows of the image to be corrected may be to determine the intermediate grid points from the calibration rows of the image to be corrected as the reference grid points. Then, based on the horizontal pixel coordinates of the intermediate grid points, using the average column distance of the standard image as the spacing between adjacent grid points, a standard horizontal pixel coordinate array is formed.

[0112] Of course, in this specification, it may be to use the first grid point in the calibration row as the reference grid point. Or when the number of grid points in the calibration row is even and there is no substantial intermediate grid point, in this case, a grid point close to the middle can be used as the intermediate grid point. This specification does not limit how to determine the reference grid points from the calibration rows of the image to be corrected.

[0113] Determining the standard horizontal pixel coordinate array with the intermediate grid point as the reference, compared with determining the reference grid points from both ends of the calibration row and then determining the standard horizontal pixel coordinate array. Determining the standard horizontal pixel coordinate array in a way that diverges from the middle to both sides simultaneously is faster than determining it in a way that diverges from left to right or from right to left.

[0114] In one or more embodiments of this specification, taking the first grid point in the calibration row as the reference grid point and assuming there are n grid points in the calibration row, the grid point horizontal pixel coordinate array of the calibration row may be X1, X2, X3... X n . The horizontal pixel coordinate of the first grid point is X1. Starting from X1, using the average column distance of the standard image as the spacing between adjacent grid points, the standard horizontal pixel coordinate array X1 ’ , X2 ’ , X3 ’ ... X n ’ can be obtained. Then, by performing polynomial fitting on the grid point horizontal pixel coordinate array and the standard horizontal pixel coordinate array, the horizontal rearrangement polynomial can be obtained:

[0115]

[0116] where m < n, and usually m takes values in [3, 8].

[0117] In one or more embodiments of the present specification, when the logo image is a grid image, the server may determine a column from the logo image as a speed measurement column, and determine the spacing between adjacent grid points in the speed measurement column.

[0118] Determine the average value of each spacing in the speed measurement column, and judge whether the difference between each spacing in the speed measurement column and the average value is within the preset range. If so, proceed to the subsequent steps according to the sign image. If not, adjust the shooting time, and re-shoot a new sign image with the line scan camera that shoots the sign image, until the difference between each spacing in the speed measurement column and the average value is within the preset range.

[0119] In one or more embodiments of the present specification, when the sign image is a grid image. The image of the marker captured by the line scan camera on the machine is generally captured at a uniform speed, and the distance between each two rows of grid points in the vertical direction in the captured image should theoretically be consistent. However, in the process of the motion mechanism accelerating to a uniform speed and decelerating to a stop, it is not a uniform motion. Therefore, in order to capture the sign image at a uniform speed, the server can determine whether it is a uniform speed based on the specific value of the distance between each two rows of grid points in the vertical direction. If the acquisition is not performed in a completely uniform speed section, the start and end positions of the acquisition need to be modified.

[0120] The server may also determine a column from the logo as a speed measurement column, and determine the spacing between adjacent grid points in the speed measurement column. It is determined whether the number of spacings with the same distance between adjacent grid points reaches a preset value. If so, the subsequent steps are performed according to the logo. If not, the shooting timing is adjusted, and a new logo is shot again by the line scan camera that shoots the logo until the number of spacings reaches the preset value.

[0121] In one or more embodiments of the present specification, when the mark image is a grid image. The server can determine a row of grid points from the standard image as a standard row, and determine the spacing between adjacent grid points in the standard row. For each image to be corrected, a row of grid points is determined from the image to be corrected as a calibration row, and the spacing between adjacent grid points in the calibration row is determined. The spacing between adjacent grid points determined in sequence from the first grid point to the last grid point in the calibration row is formed into a calibration spacing array. The spacing between adjacent grid points determined in sequence from the first grid point to the last grid point in the standard row is formed into a standard spacing array. According to the spacing between the corresponding positions in the calibration spacing array and the standard spacing array, the correction parameters of the corresponding spacing of each position of the image to be corrected are determined.

[0122] Figure 2 This is a schematic diagram of a correction provided in this manual. Figure 2As shown, the black dotted box of the standard image is the standard row, and S1 to S6 are the distances from the first grid point to the last grid point of the standard row. The black dotted box of the image to be corrected is the calibration row, and S1' to S6' are the distances from the first grid point to the last grid point of the calibration row. According to S1' and the corresponding S1, the distance that needs to be corrected for the first grid point of the image to be corrected is determined, until S6' and the corresponding S6 determine the distance that needs to be corrected for the last grid point of the image to be corrected, and the correction parameters are determined to correct the image to be corrected. The distance from the first grid point to the last grid point of the image to be corrected after correction is S1 to S6.

[0123] In one or more embodiments of the present specification, when the logo image is a two-color image, the server can determine the average grayscale value of the first color and the average grayscale value of the second color in each two-color image. According to the average grayscale value of the first color and the average grayscale value of the second color in the standard image, and the average grayscale value of the first color and the average grayscale value of the second color in the two-color image, the grayscale value correction parameter of the machine corresponding to the two-color image is determined.

[0124] The average grayscale value of the first color of each two-color image can be Wn, and the average grayscale value of the second color can be Dn. The grayscale value of the first color in the standard image can be expressed as W, and the grayscale value of the second color in the standard image can be expressed as D. According to the function of y=kx+b, k and b are determined through (W, Wn) and (D, Dn) of each two-color image, and the grayscale value correction parameters of each two-color image are obtained.

[0125] Figure 3 This is a schematic diagram of grayscale correction of a two-color image provided in this specification. Figure 3 As shown in the figure, there is an obvious gray value difference between the image to be corrected on the left and the standard image on the right. The gray value of the image to be corrected on the left is corrected by the gray value correction parameter, so that the image to be corrected is aligned with the standard image. Among them, the feature points (grid points) in the image to be corrected are determined in the way of determining corner points. Figure 3 The black solid circle is taken as an example to illustrate the feature points.

[0126] In one or more embodiments of the present specification, the server determines the machine corresponding to the image to be corrected, and obtains the image captured by the machine corresponding to the image to be corrected as the image to be corrected. According to the correction parameters of the machine corresponding to the image to be corrected, the image to be corrected is corrected in grayscale value and pixel coordinates, so that the grayscale value and pixel coordinate position of the image to be corrected are consistent with those of the image captured by the machine corresponding to the standard image. Each machine only needs to shoot once, so that the images shot subsequently have the same optical and dimensional consistency, and it is no longer necessary to calibrate the machine separately, which reduces the time consumption of calibration.

[0127] Figure 4 This is a schematic diagram of grayscale correction of a multi-color image provided in this specification. Figure 4 As shown, the upper, middle and lower three rows of the standard image represent black, white and gray respectively, and the upper, middle and lower three rows of the image to be corrected correspond to the colors represented by the upper, middle and lower three rows of the standard image respectively. According to the grayscale value correction parameters of each row of color in the image to be corrected corresponding to the color in the standard image, the image to be corrected is corrected so that the image to be corrected is aligned with the standard image.

[0128] Figure 5 This is a schematic diagram of horizontal and vertical correction of a grid diagram provided in this manual. Figure 5 As shown in the figure, the calibration row surrounded by the black dotted line in the image to be corrected and the standard row surrounded by the standard image determine the horizontal correction parameters. The calibration column surrounded by the black dotted line in the image to be corrected and the standard column surrounded by the standard image determine the row correction parameters. The image to be corrected is corrected according to the horizontal correction parameters and the row correction parameters to keep consistent with the standard image.

[0129] In one or more embodiments of the present specification, the line scan camera on each machine platform may be a line scan camera that has undergone flat field correction.

[0130] In one or more embodiments of the present specification, the server may also sum the average grayscale values ​​of each color in each logo image for each color, calculate the average value, and use the average value as the average grayscale value of each color in the standard image.

[0131] Therefore, in this specification, to determine the grayscale standard, it is not necessarily necessary to select the average grayscale value of each color of a standard image from each logo image as the grayscale standard.

[0132] It is worth noting that, in this specification, the preset average grayscale values ​​of each standard color can also be used, and then the grayscale value correction parameters for each logo image can be calculated. Of course, similarly, the column average distance and the row average distance do not necessarily need to be determined by selecting a logo image from each logo image, and the preset column average distance and the row average distance can also be used.

[0133] In one or more embodiments of the present specification, when the landmark map is a landmark map in which the feature points in the map are arranged periodically or regularly, but it is not a grid map, the calibration can also be performed by referring to the contents of the above method, and the specific contents will not be repeated here.

[0134] Figure 6 This is a schematic diagram of a logo correction provided in this manual. Figure 6 As shown, after the image to be corrected on the left is corrected by the correction parameters, the corrected image on the right is obtained.

[0135] In one or more embodiments of the present specification, the logo image is a logo image of a color block pattern that does not have a periodic arrangement formed by combining two or more colors. When the feature points in the image are not arranged periodically or regularly, the server can also correct the corresponding positions of each feature point in each image to be corrected in turn according to the positions of each feature point in the standard image, so as to keep them consistent with the positions of each feature point in the standard image.

[0136] Specifically, key points are detected in the standard image and each image to be corrected through a feature detection algorithm. For each detected key point, a descriptor of the key point is determined, and then these key points are matched between the standard image and the image to be corrected based on the descriptor. When the number of matched key points is sufficient, the correction parameters between the standard image and the image to be corrected can be determined. Correction is performed based on the correction parameters.

[0137] Figure 7 This is a schematic diagram of a correction of a logo pattern that does not have a periodic or regular arrangement provided in this specification. Figure 7 As shown, the left side is the image to be corrected. The image to be corrected is corrected according to the correction parameters to obtain an image with the same grayscale value and pixel coordinate position as the image collected by the machine corresponding to the standard image. It is worth noting that when correcting the image to be corrected, the above Figure 2 The more feature points there are in the image to be corrected, the more evenly they are distributed, and the better the correction result. Of course, it does not mean that the correction result will be bad if the number of feature points is small. When the feature points are concentrated in the area where the grains are located in the wafer image, the correction speed can be faster and the correction result will be more ideal.

[0138] The above is a calibration method provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding calibration device, such as Figure 8 shown.

[0139] Figure 8 A schematic diagram of a calibration device provided in this specification specifically includes:

[0140] An acquisition module 800 is used to acquire a mark image of the same mark object photographed by a line scan camera on each machine;

[0141] A determination module 802 is used to determine, for each logo image, the average grayscale value of each color and the pixel coordinates of each feature point in the logo image;

[0142] A selection module 804 is used to select one of the sign images as a standard image and other sign images as images to be corrected;

[0143] The calibration module 806 is used to determine the correction parameters of the machine corresponding to each image to be corrected according to the average grayscale value of each color in the standard image and the average grayscale value of each color in the image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in the image to be corrected, respectively. The correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image.

[0144] Optionally, the logo image is a multi-color image, including a periodically arranged color block pattern formed by combining two or more colors.

[0145] Optionally, the determination module 802 is further configured to determine, for each logo image, an average grayscale value of each color in the logo image.

[0146] Optionally, the determination module 802 is also used to determine, with respect to the average grayscale value of each color, the average grayscale value of the color in the standard image and the average grayscale value of the color in each image to be corrected; and for each image to be corrected, determine the grayscale value correction parameter of the machine corresponding to the image to be corrected based on the average grayscale value of the color in the standard image and the average grayscale value of the color in the image to be corrected.

[0147] Optionally, the logo image is a two-color grid image;

[0148] The calibration module 806 is further used to determine, for each image to be corrected, the horizontal correction parameters of the image to be corrected according to the grid horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image, and to determine the row correction parameters of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected.

[0149] Optionally, the calibration module 806 is further used to determine a row of grid points from the image to be corrected as a calibration row, and determine the column average distance of the spacing between adjacent grid points in the calibration row and the grid point horizontal pixel coordinate array, determine a row of grid points from the standard image as a standard row, and determine the column average distance of the spacing between adjacent grid points in the standard row, determine reference grid points from the calibration row of the image to be corrected, use the column average distance of the standard image as the spacing between adjacent grid points, and use the horizontal pixel coordinates of the reference grid points as a reference to determine the standard horizontal pixel coordinate array of the image to be corrected, perform polynomial fitting through the standard horizontal pixel coordinate array and the grid point horizontal pixel coordinate array, and determine the horizontal correction polynomial of the image to be corrected.

[0150] Optionally, the calibration module 806 is further configured to determine middle grid points from the calibration rows of the image to be corrected as reference grid points.

[0151] Optionally, the calibration module 806 is further used to determine a column of grid points from the image to be corrected as a calibration column, and determine the row average distance of the spacing between adjacent grid points in the calibration column; determine a column of grid points from the standard image as a standard column, and determine the row average distance of the spacing between adjacent grid points in the standard column, and use the ratio of the row average distance of the image to be corrected and the row average distance of the standard image as the row correction parameter of the image to be corrected.

[0152] Optionally, the calibration module 806 is further used to use the column average distance of the standard image as the row average distance, determine a column of grid points from the image to be corrected as a calibration column, and determine the row average distance of the spacing between adjacent grid points in the calibration column, and use the ratio of the row average distance of the image to be corrected and the row average distance of the standard image as the row correction parameter of the image to be corrected.

[0153] Optionally, the sign image is a grid image;

[0154] The determination module 802 is further used to determine a column from the sign image as a speed measurement column, determine the spacing between adjacent grid points in the speed measurement column, determine the average value of each spacing in the speed measurement column, and judge whether the difference between each spacing in the speed measurement column and the average value is within a preset range. If so, perform subsequent steps according to the sign image; if not, adjust the shooting timing, and re-shoot a new sign image with the line scan camera that shoots the sign image, until the difference between each spacing in the speed measurement column and the average value is within the preset range.

[0155] Optionally, the sign image is a grid image;

[0156] The calibration module 806 is further used to determine a row of grid points from the standard image as a standard row, and determine the spacing between adjacent grid points in the standard row; for each image to be corrected, determine a row of grid points from the image to be corrected as a calibration row, determine the spacing between adjacent grid points in the calibration row, and form a calibration spacing array with the spacing between adjacent grid points determined in sequence from the first grid point to the last grid point in the calibration row; form a standard spacing array with the spacing between adjacent grid points determined in sequence from the first grid point to the last grid point in the standard row, and determine the correction parameters of the spacing corresponding to each position of the image to be corrected according to the spacing between the corresponding positions in the calibration spacing array and the standard spacing array.

[0157] Optionally, the device further includes a correction module 808;

[0158] The correction module 808 is used to determine the machine corresponding to the image to be corrected, obtain the image captured by the machine corresponding to the image to be corrected as the image to be corrected, and perform grayscale value correction and pixel coordinate correction on the image to be corrected according to the correction parameters of the machine corresponding to the image to be corrected, so that the grayscale value and pixel coordinate position of the image to be corrected are consistent with those of the image captured by the machine corresponding to the standard image.

[0159] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A calibration method is provided.

[0160] This manual also provides Fig. 9 The schematic structure diagram of the electronic device shown in FIG. Fig. 9 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Fig. 9 The calibration method described.

[0161] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0162] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0163] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0164] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0165] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0166] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0167] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0168] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0169] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0170] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0171] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0172] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0173] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0174] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0176] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0177] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A calibration method, characterized in that: include: Obtain a sign image of the same sign taken by a line scan camera on each machine; For each logo image, determine the average grayscale value of each color in the logo image and the pixel coordinates of each feature point; Select one sign image from each sign image as the standard image, and use the other sign images as images to be corrected; According to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected, respectively determine the correction parameters of the machine corresponding to each image to be corrected, and the correction parameters are used to correct the image taken by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image, wherein the logo image is a multi-color image, including a periodically arranged color block pattern formed by combining two or more colors; When the mark image is a two-color grid image, the step of determining the correction parameters of the machine corresponding to the image to be corrected according to the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected includes: For each image to be corrected, determine the horizontal correction parameter of the image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image; The row correction parameter of the image to be corrected is determined according to the row average distance of the standard image and the row average distance of the image to be corrected.

2. The method according to claim 1, characterized in that The step of determining the average grayscale value of each color in each logo image specifically includes: For each logo image, determine the average grayscale value of each color in the logo image; The step of determining the correction parameters of the machine corresponding to each image to be corrected according to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected specifically includes: For each color, determine the average gray value of the color in the standard image and the average gray value of the color in each image to be corrected; For each image to be corrected, the grayscale value correction parameter of the machine corresponding to the image to be corrected is determined according to the average grayscale value of the color in the standard image and the average grayscale value of the color in the image to be corrected.

3. The method according to claim 1, characterized in that The step of determining the horizontal correction parameters of the image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image specifically includes: Determine a row of grid points from the image to be corrected as a calibration row, and determine the column average distance between adjacent grid points in the calibration row and an array of horizontal pixel coordinates of the grid points; Determine a row of grid points from the standard graph as a standard row, and determine the column average distance between adjacent grid points in the standard row; Determine reference grid points from the calibration rows of the image to be corrected, use the average column distance of the standard image as the spacing between adjacent grid points, and use the horizontal pixel coordinates of the reference grid points as a reference to determine the standard horizontal pixel coordinate array of the image to be corrected; A polynomial fitting is performed through the standard horizontal pixel coordinate array and the grid point horizontal pixel coordinate array to determine the horizontal correction polynomial of the image to be corrected.

4. The method according to claim 3, characterized in that The step of determining the reference grid points from the calibration lines of the image to be corrected specifically includes: The middle grid point is determined from the calibration row of the image to be corrected as the reference grid point.

5. The method according to claim 4, characterized in that The step of determining the row correction parameter of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected specifically includes: Determine a column of grid points from the image to be corrected as a calibration column, and determine the row average distance between adjacent grid points in the calibration column; determine a column of grid points from the standard image as a standard column, and determine the row average distance between adjacent grid points in the standard column; The ratio of the row average distance of the image to be corrected to the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

6. The method according to claim 3, characterized in that The step of determining the row correction parameter of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected specifically includes: The average distance of the columns of the standard graph is used as the average distance of the rows of the standard graph; Determine a column of grid points from the image to be corrected as a calibration column, and determine a row average distance between adjacent grid points in the calibration column; The ratio of the row average distance of the image to be corrected to the row average distance of the standard image is used as the row correction parameter of the image to be corrected.

7. The method according to claim 1, characterized in that The logo diagram is a grid diagram; Before selecting a logo image from each logo image as a standard image, the method further includes: Determine a column from the logo as a speed measurement column, and determine the spacing between adjacent grid points in the speed measurement column; Determine an average value of each spacing in the speed measurement column, and judge whether the difference between each spacing in the speed measurement column and the average value is within a preset range; If yes, proceed to the next steps according to the sign diagram; If not, the shooting timing is adjusted, and a new sign image is shot again by the line scan camera that shoots the sign image, until the difference between each spacing in the speed measurement column and the average value is within the preset range.

8. The method according to claim 1, characterized in that The logo diagram is a grid diagram; The step of determining the correction parameters of the machine corresponding to each image to be corrected according to the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected comprises: Determine a row of grid points from the standard image as a standard row, and determine the spacing between adjacent grid points in the standard row; for each image to be corrected, determine a row of grid points from the image to be corrected as a calibration row, and determine the spacing between adjacent grid points in the calibration row; The spacings between adjacent grid points determined in sequence from the first grid point to the last grid point in the calibration row form a calibration spacing array; the spacings between adjacent grid points determined in sequence from the first grid point to the last grid point in the standard row form a standard spacing array; According to the spacings of corresponding positions in the calibrated spacing array and the standard spacing array, correction parameters of the spacings corresponding to each position of the image to be corrected are determined.

9. The method according to claim 1, characterized in that The method further comprises: Determine the machine corresponding to the image to be corrected, and obtain an image acquired by the machine corresponding to the image to be corrected as the image to be corrected; According to the correction parameters of the machine corresponding to the image to be corrected, grayscale value correction and pixel coordinate correction are performed on the image to be corrected, so that the grayscale value and pixel coordinate position of the image to be corrected are consistent with those of the image collected by the machine corresponding to the standard image.

10. A calibration device, characterized in that: include: An acquisition module is used to acquire a mark image of the same mark object taken by a line scan camera on each machine; A determination module, for determining, for each logo image, an average grayscale value of each color and a pixel coordinate of each feature point in the logo image; A selection module, used for selecting one sign image from each sign image as a standard image and taking the other sign images as images to be corrected; The calibration module is used to determine the correction parameters of the machine corresponding to each image to be corrected according to the average grayscale value of each color in the standard image and the average grayscale value of each color in each image to be corrected, the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected, respectively. The correction parameters are used to correct the image captured by the line scan camera on the machine corresponding to the image to be corrected to be consistent with the standard image, wherein the logo image is a multi-color image, including a periodically arranged color block pattern formed by combining two or more colors; when the logo image is a two-color grid image, the step of determining the correction parameters of the machine corresponding to the image to be corrected according to the pixel coordinates of each feature point in the standard image and the pixel coordinates of each feature point in each image to be corrected includes: for each image to be corrected, determining the horizontal correction parameters of the image to be corrected according to the grid point horizontal pixel coordinate array of the image to be corrected and the column average distance of the standard image; determining the row correction parameters of the image to be corrected according to the row average distance of the standard image and the row average distance of the image to be corrected.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method described in any one of claims 1 to 9 is implemented.

Images