Machine visual quality detection method for semiconductor equipment part production

Abstract

The invention discloses a machine visual quality detection method for semiconductor equipment part production, and relates to the technical field of visual quality detection, and the method comprises the following steps: carrying out the graying processing of a part image, and obtaining a part gray-scale image; obtaining a background threshold value based on the images of the first number of normal parts; obtaining a part threshold value based on the images of the first number of normal parts; obtaining a to-be-detected area based on the background threshold and the component grey-scale map; performing binarization processing on the to-be-detected area based on the part threshold value to obtain an area binarization image; judging whether an abnormal area appears or not based on the area binary image, if yes, obtaining an abnormal position, sending out a defect signal and displaying the abnormal position at the same time; if not, sending out a defect-free signal; the method is used for solving the problem that in the prior art, the efficiency of detecting the defects of the parts of the semiconductor equipment is low due to the fact that the method for detecting the defects of the parts is complex when various parts are applied.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of visual quality detection, and particularly relates to a machine visual quality detection method for semiconductor equipment parts production. BACKGROUND

[0002] The semiconductor industry, as the basis of modern information technology, highly depends on the precision and reliability of manufacturing equipment; the semiconductor equipment itself is composed of a large number of high-precision and complex-geometry parts, and the manufacturing quality of the parts directly determines the performance, yield, stability and service life of the semiconductor equipment, so it is necessary to detect the quality of the parts of the semiconductor equipment. Quality detection includes defect detection, but the structure of the semiconductor equipment parts is complex, and the parts usually contain holes, which are easily misjudged as defects when detected through the acquired images, so it is necessary to scan and compare each type of semiconductor equipment part, which is large in calculation amount and complex, such as the patent application with the publication number CN115272302A, which discloses an image part detection method, part detection equipment and system, the scheme compares with the same part, and needs to acquire the image of each normal part when dealing with parts of multiple structures, so it is relatively cumbersome, that is, the existing technology is relatively cumbersome when dealing with multiple parts, resulting in low efficiency of defect detection of the parts of the semiconductor equipment. SUMMARY

[0003] The application aims to at least solve one of the technical problems in the prior art, and the part image is subjected to gray scale processing to obtain a part gray scale image; a background threshold value is obtained based on the images of the first number of normal parts; a part threshold value is obtained based on the images of the first number of normal parts; a detection area is obtained based on the background threshold value and the part gray scale image; the detection area is subjected to binary processing based on the part threshold value to obtain a region binary image; whether an abnormal region appears is judged based on the region binary image, if yes, an abnormal position is obtained, a defect signal is sent and the abnormal position is displayed; if not, a defect-free signal is sent, so as to solve the problem that the existing technology is relatively cumbersome when dealing with multiple parts, resulting in low efficiency of defect detection of the parts of the semiconductor equipment.

[0004] To achieve the above-mentioned purpose, the application provides a machine visual quality detection method for semiconductor equipment part production, which comprises the following steps: An image of a semiconductor equipment part is acquired and marked as a part image; The part image is subjected to gray scale processing to obtain a part gray scale image; A background threshold value is obtained based on the images of the first number of normal parts; acquiring the part threshold value based on the first quantity of normal part images; acquiring the to-be-detected region based on the background threshold value and the part gray image; performing binarization processing on the to-be-detected region based on the part threshold value to obtain a region binarization image; judging whether an abnormal region appears based on the region binarization image, if yes, acquiring an abnormal position, issuing a defect signal and displaying the abnormal position, and if no, issuing a no-defect signal.

[0005] Further, the gray processing of the part image to obtain the part gray image includes the following sub-steps: acquiring R, G and B channel values of each pixel point in the part image, calculating the mean value of the R, G and B channel values of each pixel point, and marking the mean value as a part gray value; and replacing the R, G and B channel values of each pixel point in the part image with the corresponding part gray value to obtain the part gray image.

[0006] Further, the background threshold value is acquired based on the first quantity of normal part images, including the following sub-steps: performing gray processing on the normal part image to obtain a normal gray image, acquiring the gray value of a pixel point that is not a part in the normal gray image, and marking the gray value as a background gray value; acquiring the range of the background gray value, and equally dividing the range of the background gray value into N ranges with the same interval, and marking the ranges as background division ranges; respectively calculating the frequency of the background gray value in each background division range, and marking the frequency as a background gray frequency; taking the background gray value as the X-axis data and the background gray frequency as the Y-axis data, establishing a plane rectangular coordinate system, and marking the coordinate system as a background coordinate system.

[0007] Further, the background threshold value is acquired based on the first quantity of normal part images, including the following sub-steps: acquiring the median value of the background division range, and marking the median value as a background median value; taking the background median value and the corresponding background gray frequency as the horizontal and vertical coordinates of the coordinate point, and marking the coordinate point as a background coordinate point; drawing all the background coordinate points into the background coordinate system to obtain a scatter plot, and marking the scatter plot as a background scatter plot; performing fitting on the background scatter plot to obtain a function, and marking the function as a background fitting function; acquiring the intersection point of the background fitting function and the X-axis of the background coordinate system, and marking the intersection point as a background intersection point; acquiring the maximum value of the horizontal coordinate of the background intersection point, and marking the maximum value as a background threshold value.

[0008] Further, the obtaining the part threshold value based on the first quantity of normal part images comprises the following sub-steps: Obtaining the gray value of the pixel point of the part in the normal gray image, and marking as part gray value; Obtaining the range of the part gray value, and equally dividing the range of the part gray value into M same intervals, and marking as part division range; Respectively obtaining the frequency of the part gray value in each part division range, and marking as part gray frequency; Taking the part gray value as the X-axis data and the part gray frequency as the Y-axis data, establishing a plane rectangular coordinate system, and marking as part coordinate system.

[0009] Further, the obtaining the part threshold value based on the first quantity of normal part images comprises the following sub-steps: Obtaining the median value of the part division range, and marking as part median value; Taking the part median value and the corresponding part gray frequency as the horizontal and vertical coordinates of the coordinate point, and marking as part coordinate point; Drawing all part coordinate points into the part coordinate system to obtain a scatter plot, and marking as part scatter plot; Fitting the part scatter plot to obtain a function, and marking as part fitting function; Obtaining the intersection of the part fitting function and the X-axis of the part coordinate system, and marking as part intersection point; Obtaining the minimum value of the horizontal coordinate of the part intersection point, and marking as part threshold value.

[0010] Further, the obtaining the to-be-detected region based on the background threshold value and the part gray image comprises the following sub-steps: Setting the gray value less than or equal to the background threshold value in the part gray image to 255, and setting the gray value greater than the background threshold value in the part gray image to 0 to obtain a part binary image; Establishing a plane rectangular coordinate system, marking as position coordinate system, and placing the part binary image in the position coordinate system; obtaining the largest area region composed of pixel points with a gray value of 0 in the part binary image, and marking as initial region; obtaining the position of the initial region in the position coordinate system, and marking as initial region position; Placing the part gray image in the position coordinate system at the same position as the part binary image, and obtaining the region of the initial region position in the part gray image, and marking as to-be-detected region.

[0011] Further, the obtaining the region binary image by performing binary processing on the to-be-detected region based on the part threshold value comprises the following sub-steps: Setting the gray value of the pixel point in the region to be detected which is greater than or equal to the component threshold value to 255 and setting the gray value of the pixel point in the region to be detected which is less than the component threshold value to 0 to obtain a region binary image.

[0012] Further, judging whether an abnormal region appears based on the region binary image, if yes, obtaining an abnormal position, issuing a defect signal and displaying the abnormal position; if no, issuing a defect non-appearing signal including the following sub-steps: Marking the independent region composed of the pixel point with a gray value of 0 in the region binary image in the region to be detected as an initial defect region; Obtaining the minimum value of the area of the defect-allowing part of the semiconductor and marking it as an area minimum value; Obtaining the pixel point corresponding to the area minimum value in the component image and marking it as a pixel point number threshold value; Obtaining the pixel point number of the initial defect region, if the pixel point number of the initial defect region is greater than the pixel point number threshold value, marking the initial defect region as an abnormal region; If the pixel point number of the initial defect region is less than or equal to the pixel point number threshold value, it indicates that no abnormal region appears.

[0013] Further, obtaining the abnormal position includes the following sub-steps: Obtaining the maximum and minimum values of the horizontal coordinate of the abnormal region and marking them as a region horizontal maximum value and a region horizontal minimum value respectively; Obtaining the maximum and minimum values of the vertical coordinate of the abnormal region and marking them as a region vertical maximum value and a region vertical minimum value respectively; Calculating the difference between the region horizontal maximum value and the region horizontal minimum value and marking it as a region horizontal difference value; calculating the difference between the region vertical maximum value and the region vertical minimum value and marking it as a region vertical difference value; Calculating the product of the region vertical difference value and the region horizontal difference value and marking it as a difference product; Rotating the abnormal region by 360° with any point in the abnormal region as the rotation center, when the difference product is the smallest, taking the region horizontal minimum value and the region vertical minimum value as the horizontal coordinate and the vertical coordinate of a coordinate point respectively and marking it as a first coordinate point, taking the region horizontal maximum value and the region vertical minimum value as the horizontal coordinate and the vertical coordinate of a coordinate point respectively and marking it as a second coordinate point, taking the region horizontal maximum value and the region vertical maximum value as the horizontal coordinate and the vertical coordinate of a coordinate point respectively and marking it as a third coordinate point, taking the region horizontal minimum value and the region vertical maximum value as the horizontal coordinate and the vertical coordinate of a coordinate point respectively and marking it as a fourth coordinate point, and taking the rectangle formed by connecting the first coordinate point, the second coordinate point, the third coordinate point and the fourth coordinate point in order and the head and tail as an abnormal position.

[0014] The beneficial effects of the present application are as follows: the present application obtains a part gray image by performing gray processing on a part image; a background threshold is obtained based on a first number of normal part images; a part threshold is obtained based on the first number of normal part images; a detection area is obtained based on the background threshold and the part gray image; a region binary image is obtained by performing binary processing on the detection area based on the part threshold; it is determined whether an abnormal area appears based on the region binary image, if an abnormal area appears, an abnormal position is obtained, a defect signal is sent out and the abnormal position is displayed; if no abnormal area appears, a defect-free signal is sent out, the advantage is that the method can cope with defect detection of various parts, and the efficiency of part defect detection of semiconductor equipment is improved. The present application obtains a detection area based on a background threshold and a part gray image, the advantage is that not only can the part in the image be screened, but also the interference of holes on part threshold defect recognition can be excluded, the accuracy of part defect detection of semiconductor equipment is improved, and the efficiency of part defect detection of semiconductor equipment is improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A step flow chart of the method of the present application; Figure 2 A schematic diagram of the background fitting function of the present application; Figure 3 A schematic diagram of the part fitting function of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application, obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0017] Embodiment 1, please refer to Figure 1 The present application provides a machine vision quality detection method for semiconductor equipment part production, comprising the following steps: Step S1, obtaining an image of a semiconductor equipment part, marked as a part image; when obtaining the part image, a specific scene needs to be obtained, i.e. the scene is a black background, which is convenient for subsequent image analysis.

[0018] Step S2, performing gray processing on the part image to obtain a part gray image; step S2 comprises the following substeps: Step S201, obtaining R, G and B three channel values of a pixel point in the part image, calculating the mean value of R, G and B three channel values of each pixel point, and marking the mean value as a part gray value; replacing R, G and B three channel values of each pixel point in the part image with the corresponding part gray value to obtain a part gray image; since the image only contains black background and part color, the mean value method is the most convenient; In practical application, for example, R, G and B three channel values of a pixel point in the part image are 23, 22 and 24 respectively, and the part gray value of the pixel point is 23.

[0019] Step S3, obtaining a background threshold based on the images of the first number of normal parts; the first number is used to summarize the distribution of the gray value in the image, so multiple images are needed to make the obtained data more accurate, for example, the first number is 10, and step S3 includes the following substeps: Step S301, performing gray processing on the images of the normal parts to obtain a normal gray image, obtaining the gray value of the pixel point that is not a part in the normal gray image, and marking the gray value as a background gray value; here, the gray processing method is the same as step 201; Step S302, obtaining the range of the background gray value, and equally dividing the range of the background gray value into N ranges with the same interval, and marking the ranges as background division ranges; in order to facilitate calculation and observation of the distribution of the background gray value, N should not be too large or too small, for example, N is set to 7; Step S303, respectively calculating the frequency of the background gray value in each background division range, and marking the frequency as a background gray frequency; Step S304, establishing a plane rectangular coordinate system with the background gray value as the X-axis data and the background gray frequency as the Y-axis data, and marking the coordinate system as a background coordinate system; Step S305, obtaining the median value of the background division range, and marking the median value as a background median value; Step S306, taking the background median value and the corresponding background gray frequency as the horizontal coordinate and the vertical coordinate of the coordinate point, and marking the coordinate point as a background coordinate point; Step S307, drawing all the background coordinate points into the background coordinate system to obtain a scatter plot, and marking the scatter plot as a background scatter plot; Step S308, fitting the background scatter plot to obtain a function, and marking the function as a background fitting function; through the function fitting method, the influence of the abnormal background gray value that is too large or too small can be reduced, and the data obtained based on the background fitting function is more accurate; Step S309, obtaining the intersection of the background fitting function and the X-axis of the background coordinate system, and marking the intersection as a background intersection point; Step S310, the maximum value of the horizontal coordinate in the background intersection point is obtained, which is marked as the background threshold; the background threshold is obtained by using this method, so that the obtained background gray scale range is more accurate; here, the maximum value is obtained, because the background is black, the range of the background gray scale value is close to 0, so the value less than the maximum value can separate the image part of the background; in actual application, please refer to Figure 2 As shown in the figure, the maximum value of the horizontal coordinate in the background intersection point is 40, so the background threshold is 40.

[0020] Step S4, the part threshold is obtained based on the images of the first number of normal parts; step S4 includes the following sub-steps: Step S401, the gray scale value of the pixel point of the part part in the normal gray scale image is obtained, which is marked as the part gray scale value; Step S402, the range of the part gray scale value is obtained, and the range of the part gray scale value is evenly divided into M same intervals, which is marked as the part division range; in order to facilitate calculation and observation of the distribution of the part gray scale value, M should not be too large or too small, for example, M is set to 7; Step S403, the frequency of the part gray scale value in each part division range is obtained, which is marked as the part gray scale frequency; Step S404, a plane rectangular coordinate system is established with the part gray scale value as the X-axis data and the part gray scale frequency as the Y-axis data, which is marked as the part coordinate system; Step S405, the median of the part division range is obtained, which is marked as the part median; Step S406, the part median and the corresponding part gray scale frequency are taken as the horizontal coordinate and the vertical coordinate of the coordinate point, which is marked as the part coordinate point; Step S407, all part coordinate points are drawn into the part coordinate system to obtain a scatter plot, which is marked as the part scatter plot; Step S408, the part scatter plot is fitted to obtain a function, which is marked as the part fitting function; the function fitting method not only reduces the influence of abnormal part gray scale values that are too large or too small, but also makes the data obtained based on the part fitting function more accurate; Step S409, the intersection of the part fitting function and the X-axis of the part coordinate system is obtained, which is marked as the part intersection; Step S410, the minimum value of the horizontal coordinate in the part intersection is obtained, which is marked as the part threshold; the part threshold is obtained by using this method, so that the obtained part gray scale range is more accurate; here, the minimum value is obtained, because the part is silver white and the distribution of the gray scale value is different from that of the background, so the minimum value can distinguish the part from the background; in actual application, please refer to Figure 2 As shown in the figure, the maximum value of the horizontal coordinate in the background intersection point is 40, so the background threshold is 40.

[0021] Step S5, obtaining the region to be detected based on the background threshold and the part gray image; Step S5 includes the following sub-steps: Step S501, setting the gray value less than or equal to the background threshold in the part gray image as 255, and setting the gray value greater than the background threshold in the part gray image as 0, to obtain a part binary image; In practical application, the gray value less than or equal to 40 in the part gray image is set as 255, and the gray value greater than 40 in the part gray image is set as 0, to obtain a part binary image; Step S502, establishing a plane rectangular coordinate system, marked as a position coordinate system, and placing the part binary image in the position coordinate system; obtaining a maximum area region composed of pixel points with a gray value of 0 in the part binary image, marked as an initial region; obtaining the position of the initial region in the position coordinate system, marked as an initial region position; Step S503, placing the part gray image in the position coordinate system at the same position as the part binary image, and obtaining the region at the initial region position in the part gray image, marked as a region to be detected; this method obtains the region to be detected in the part gray image based on the part binary image; the region to be detected is the region of the part that needs to be judged for defects.

[0022] Step S6, performing binary processing on the region to be detected based on the part threshold to obtain a region binary image; Step S6 includes the following sub-steps: Step S601, setting the gray value greater than or equal to the part threshold of the pixel points in the region to be detected as 255, and setting the gray value less than the part threshold of the pixel points in the region to be detected as 0, to obtain a region binary image; if a defect exists, the gray value of the defect part will be lower than that of the part under the action of light, and this method obtains the defect part. In practical application, the gray value greater than or equal to 80 of the pixel points in the region to be detected is set as 255, and the gray value less than 40 of the pixel points in the region to be detected is set as 0, to obtain a region binary image.

[0023] Step S7, judging whether an abnormal region exists based on the region binary image; if an abnormal region exists, obtaining an abnormal position, issuing a defect signal and displaying the abnormal position; if no abnormal region exists, issuing a defect non-existence signal; Step S7 includes the following sub-steps: Step S701, obtaining an independent region composed of pixel points with a gray value of 0 in the region to be detected in the region binary image, marked as an initial defect region; Step S702, obtaining the minimum value of the area of the defect part allowed by the semiconductor, marked as an area minimum value; Step S703, the minimum value of the area corresponding to the pixel points in the part image is obtained, and is marked as a pixel point number threshold; here, the precision of the semiconductor production parts is high, so that no defects can be contained, but in order to prevent independent pixel points from interfering, the pixel point number threshold is set to be greater than or equal to 2; Step S704, the pixel point number of the initial defect area is obtained, and if the pixel point number of the initial defect area is greater than the pixel point number threshold, the initial defect area is marked as an abnormal area; Step S705, if the pixel point number of the initial defect area is less than or equal to the pixel point number threshold, it indicates that no abnormal area appears; In actual application, if the minimum value of the area of the semiconductor allowable defect part is obtained, and is marked as the area minimum value is 0, and the pixel point number threshold is set to be greater than or equal to 2, then the pixel point number threshold is 2, if there is an initial defect area, and the pixel point number of the initial defect area is 122, if the pixel point number of the initial defect area is 122, which is greater than the pixel point number threshold 3, then the initial defect area is marked as an abnormal area.

[0024] Step S706, the maximum and minimum values of the abnormal area horizontal coordinates are obtained, and are marked as the area horizontal maximum value and the area horizontal minimum value respectively; Step S707, the maximum and minimum values of the abnormal area vertical coordinates are obtained, and are marked as the area vertical maximum value and the area vertical minimum value respectively; Step S708, the difference between the area horizontal maximum value and the area horizontal minimum value is calculated, and is marked as the area horizontal difference value; the difference between the area vertical maximum value and the area vertical minimum value is calculated, and is marked as the area vertical difference value; Step S709, the product of the area vertical difference value and the area horizontal difference value is calculated, and is marked as the difference product; the minimum bounding rectangle is obtained according to the size of the difference product; Step S710, the abnormal area is rotated by 360° with any point in the abnormal area as the center, when the difference product is the smallest, the area horizontal minimum value and the area vertical minimum value are taken as the horizontal coordinate and the vertical coordinate of a coordinate point, and are marked as the first coordinate point, the area horizontal maximum value and the area vertical minimum value are taken as the horizontal coordinate and the vertical coordinate of a coordinate point, and are marked as the second coordinate point, the area horizontal maximum value and the area vertical maximum value are taken as the horizontal coordinate and the vertical coordinate of a coordinate point, and are marked as the third coordinate point, the area horizontal minimum value and the area vertical maximum value are taken as the horizontal coordinate and the vertical coordinate of a coordinate point, and are marked as the fourth coordinate point, the first coordinate point, the second coordinate point, the third coordinate point and the fourth coordinate point are connected in order to form a rectangle, and are marked as the abnormal position; the obtained abnormal position is a kind of minimum bounding rectangle method, and the abnormal position is displayed, which is convenient for personnel to observe and further judge the defect part of the part.

[0025] In some embodiments, the electronic device can include a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory can communicate with each other through the communication bus. The memory can store computer-readable instructions. The processor can invoke the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in the semiconductor device component production machine vision quality detection method can be performed to achieve the following functions: obtaining an image of a semiconductor device component, which is marked as a component image; performing grayscale processing on the component image to obtain a component grayscale image; obtaining a background threshold value based on a first number of normal component images; obtaining a component threshold value based on the first number of normal component images; obtaining a to-be-detected region based on the background threshold value and the component grayscale image; performing binaryzation processing on the to-be-detected region based on the component threshold value to obtain a region binaryzation image; determining whether an abnormal region exists based on the region binaryzation image, and if an abnormal region exists, obtaining an abnormal position, issuing a defect signal, and displaying the abnormal position; and if no abnormal region exists, issuing a no-defect signal.

[0026] In addition, the logic instructions in the memory described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0027] Embodiment 3, the application also provides a computer program product, the computer program product includes a computer program stored on a computer readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute a semiconductor device parts production machine vision quality detection method provided by each method, the method includes: obtaining an image of a semiconductor device part, marked as a part image; the part image is grayed to obtain a part gray image; obtain a background threshold based on a first number of normal part images; obtain a part threshold based on a first number of normal part images; obtain a detection area based on the background threshold and the part gray image; obtain a region binary image by binarizing the detection area based on the part threshold; determine whether an abnormal area appears based on the region binary image, if it appears, obtain an abnormal position, issue a defect signal and display the abnormal position; if it does not appear, issue a no defect signal.

[0028] Embodiment 4, the application also provides a computer readable storage medium, the application provides a storage medium, which stores a computer program, when the computer program is executed by a processor, the steps of the above semiconductor device parts production machine vision quality detection method are run to realize the following functions: obtaining an image of a semiconductor device part, marked as a part image; the part image is grayed to obtain a part gray image; obtain a background threshold based on a first number of normal part images; obtain a part threshold based on a first number of normal part images; obtain a detection area based on the background threshold and the part gray image; obtain a region binary image by binarizing the detection area based on the part threshold; determine whether an abnormal area appears based on the region binary image, if it appears, obtain an abnormal position, issue a defect signal and display the abnormal position; if it does not appear, issue a no defect signal.

[0029] Through the description of the above embodiments, the embodiments of the application can be provided as a method, a system or a computer program product. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

[0030] In the embodiments of the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are only illustrative, for example, the division of modules or units is only a logical function division, and other division manners can be used in actual implementation, for example, a plurality of modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some communication interface, the indirect coupling or communication connection between the system, the module and the unit can be electrical, mechanical or other forms.

[0031] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A machine vision quality inspection method for semiconductor equipment component manufacturing, characterized in that, Includes the following steps: Acquire images of semiconductor equipment components and label them as component images; The component images are converted to grayscale to obtain grayscale images of the components; Obtain the background threshold based on the images of a first number of normal components; Obtain component thresholds based on images of a first number of normal components; The area to be detected is obtained based on the background threshold and the grayscale image of the component. Binarization of the area to be detected is performed based on the component threshold to obtain a region binarization map; Based on the region binarization map, determine whether an abnormal region has appeared. If it has appeared, obtain the abnormal location, issue a defect signal and display the abnormal location at the same time. If it does not occur, a defect signal will be issued.

2. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 1, characterized in that, The process of converting component images to grayscale to obtain component grayscale images includes the following sub-steps: Obtain the R, G, and B channel values ​​of pixels in the component image, calculate the average of the R, G, and B channel values ​​of each pixel, and mark it as the component grayscale value; replace the R, G, and B channel values ​​of each pixel in the component image with the corresponding component grayscale value to obtain the component grayscale image.

3. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 2, characterized in that, Obtaining the background threshold based on images of a first number of normal components includes the following sub-steps: The image of a normal component is processed into a grayscale image to obtain a normal grayscale image. The grayscale values ​​of pixels that are not part of the component in the normal grayscale image are then obtained and marked as background grayscale values. Obtain the range of background grayscale values, and divide the range of background grayscale values ​​into N equal intervals, marking them as the background division range; Calculate the frequency of the background grayscale value within each background segmentation range and mark it as the background grayscale frequency; Establish a Cartesian coordinate system with the background grayscale value as the X-axis and the background grayscale frequency as the Y-axis, and label it as the background coordinate system.

4. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 3, characterized in that, Obtaining the background threshold based on images of a first number of normal components also includes the following sub-steps: Obtain the median value of the background segment and mark it as the background median value; The background median and the corresponding background grayscale frequency are used as the x and y coordinates of the coordinate points and marked as the background coordinate points; Plot all background coordinate points into the background coordinate system to obtain a scatter plot, and label it as the background scatter plot; The function obtained by fitting the background scatter plot is marked as the background fitting function. Obtain the intersection points of the background fitting function and the X-axis of the background coordinate system, and mark them as background intersection points; Obtain the maximum value of the x-coordinate among the background intersection points and mark it as the background threshold.

5. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 4, characterized in that, Obtaining the component threshold based on images of a first number of normal components includes the following sub-steps: Obtain the grayscale values ​​of the pixels of the component parts in the normal grayscale image and mark them as component grayscale values; Obtain the range of grayscale values ​​of the component, and divide the range of grayscale values ​​of the component into M equal intervals, marking them as the component division range; Calculate the frequency of grayscale values ​​of each component within the defined range, and mark it as the grayscale frequency of the component; A Cartesian coordinate system is established using the grayscale values ​​of the components as the X-axis and the grayscale frequencies of the components as the Y-axis. This system is then labeled as the component coordinate system.

6. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 5, characterized in that, Obtaining the component threshold based on images of a first number of normal components also includes the following sub-steps: Obtain the median value of the component's segmentation range and mark it as the component's median value; The median value of the component and the corresponding gray frequency of the component are used as the x and y coordinates of the coordinate points, and these are marked as component coordinate points. Plot all component coordinate points into the component coordinate system to obtain a scatter plot, and label it as the component scatter plot; The function obtained by fitting the scatter plot of the parts is marked as the part fitting function; Obtain the intersection points of the component fitting function and the X-axis of the component coordinate system, and mark them as component intersection points; Find the minimum x-coordinate of the intersection points of the components and mark it as the component threshold.

7. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 6, characterized in that, The process of obtaining the region to be detected based on the background threshold and component grayscale image includes the following sub-steps: Set the grayscale values ​​in the grayscale image of the component that are less than or equal to the background threshold to 255, and set the grayscale values ​​in the grayscale image of the component that are greater than the background threshold to 0 to obtain the binarized image of the component. Establish a Cartesian coordinate system, labeled as the position coordinate system, and place the binary image of the component in the position coordinate system; Obtain the largest area region composed of pixels with a grayscale value of 0 in the binarized image of the component, and mark it as the initial region; Obtain the position of the initial region in the position coordinate system and mark it as the initial region position; Place the grayscale image of the component in the same coordinate system as the binary image of the component, obtain the region at the initial location in the grayscale image of the component, and mark it as the region to be detected.

8. The machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 7, characterized in that, Binarizing the region to be detected based on component thresholds to obtain a binarized map includes the following sub-steps: Set the grayscale value of pixels in the detection area that are greater than or equal to the component threshold to 255, and set the grayscale value of pixels in the detection area that are less than the component threshold to 0 to obtain a region binarized image.

9. A machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 8, characterized in that, Based on the region binarized map, determine whether an abnormal region exists. If it does, obtain the abnormal location, issue a defect signal, and simultaneously display the abnormal location. If it does not exist, issue a defect absence signal, including the following sub-steps: The independent regions formed by pixels with a gray value of 0 within the region to be detected in the region binarized image are marked as the initial defect regions. Obtain the minimum area of ​​the permissible defect portion of the semiconductor and mark it as the minimum area. Find the pixel in the component image that corresponds to the minimum area and mark it as the threshold for the number of pixels; Obtain the number of pixels in the initial defect region. If the number of pixels in the initial defect region is greater than the pixel count threshold, then mark the initial defect region as an abnormal region. If the number of pixels in the initial defect area is less than or equal to the pixel count threshold, it indicates that no abnormal area has appeared.

10. A machine vision quality inspection method for semiconductor equipment component manufacturing according to claim 9, characterized in that, Obtaining the location of the anomaly includes the following sub-steps: Obtain the maximum and minimum values ​​of the horizontal coordinate of the abnormal region, and mark them as the maximum horizontal value and the minimum horizontal value of the region, respectively; Obtain the maximum and minimum values ​​of the vertical coordinate of the abnormal region, and mark them as the maximum and minimum values ​​of the region, respectively. Calculate the difference between the largest and smallest values ​​in the region and label it as the region's horizontal difference value; Calculate the difference between the maximum and minimum vertical values ​​of the region and mark it as the regional vertical difference value; Calculate the product of the longitudinal difference and the transverse difference of the region, and label it as the difference product; Rotate the abnormal region 360° around any point within the abnormal region. When the product of the differences is minimized, mark the first coordinate point as the x-coordinate and y-coordinate of the region's smallest horizontal and vertical values ​​as a single coordinate point. Mark the second coordinate point as the x-coordinate and y-coordinate of the region's largest horizontal and vertical values ​​as a single coordinate point. Mark the third coordinate point as the x-coordinate and y-coordinate of the region's largest horizontal and vertical values ​​as a single coordinate point. Mark the fourth coordinate point as the x-coordinate and y-coordinate of the region's smallest horizontal and vertical values ​​as a single coordinate point. The rectangle formed by connecting the first, second, third, and fourth coordinate points in sequence is marked as the abnormal location.

Images