Wafer defect detection method, device, equipment, medium and product
By performing differential processing on the wafer image and separating potential defects based on pixel values, and determining target defects with preset thresholds, the problem of low accuracy in traditional detection methods in complex backgrounds is solved, and high-precision wafer defect detection is achieved.
Patent Information
- Application Number
- CN202510218988.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-26
- Publication Date
- 2025-06-13
AI Technical Summary
Traditional wafer defect detection methods have low accuracy when detecting wafer surface pattern structure and defects, especially when complex background interference is large.
By acquiring the first wafer image containing the defect and the second wafer image containing the defect, differential processing is performed on the two to generate the differential image. Based on the pixel values in the differential image, the potential defect is separated from the image background and the target defect is determined by a preset threshold.
The accurate distinction between the wafer surface graphic structure and target defects is achieved, the accuracy and accuracy of wafer defect detection is improved, and the error detection problems caused by background interference is reduced.
Smart Images
Figure CN120147260A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of semiconductor manufacturing technology, and particularly to a wafer defect detection method, apparatus, device, medium and product. Background Art
[0002] In the process of semiconductor manufacturing, the detection of wafer surface defects is an important link to ensure product quality. Traditional wafer defect detection methods include optical microscopes and scanning electron microscopes, etc. Although these methods can provide high-resolution images, they have problems such as complex operation, slow detection speed, and large interference from the complex background of the wafer graphic structure. Especially for wafers with graphic structures (such as lithography patterns, etching patterns, etc.), traditional detection methods are difficult to effectively distinguish defects from graphic structures, thus affecting the accuracy of defect identification. Summary of the Invention
[0003] In view of this, the present disclosure provides a wafer defect detection method, apparatus, device, medium and product to solve the problem of low accuracy in wafer defect detection.
[0004] In a first aspect, the present disclosure provides a wafer defect detection method, which includes:
[0005] Obtain a first wafer image containing defects and a second wafer image without defects to be detected;
[0006] Perform differential processing on the first wafer image and the second wafer image to generate a differential image;
[0007] Based on the pixel value of the first pixel in the differential image, separate potential defects in the differential image from the image background to obtain a potential defect image;
[0008] Based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, determine the target defect to obtain a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can adjust and change.
[0009] In the embodiments of the present disclosure, by obtaining a first wafer image including defects to be detected and a second wafer image without defects; performing differential processing on the first wafer image and the second wafer image to generate a differential image; based on the pixel value of the first pixel in the differential image, separating potential defects in the differential image from the image background to obtain a potential defect image; based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, determining target defects to obtain a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can be adjusted and changed. Since the embodiments of the present disclosure perform differential processing on wafer images with and without defects, separate potential defects from the image background based on pixel values, and then determine target defects based on pixel values and a preset threshold, it is possible to distinguish the graphic structure on the wafer surface from target defects, achieve high-precision wafer defect detection, and improve the accuracy of wafer defect detection.
[0010] In an alternative embodiment, performing differential processing on the first wafer image and the second wafer image to generate a differential image includes:
[0011] Obtaining the difference between the pixel values of corresponding pixels of the first wafer image and the second wafer image;
[0012] Generating a differential image according to the difference between the pixel values of corresponding pixels.
[0013] In the embodiments of the present disclosure, by generating a differential image according to the difference between the pixel values of corresponding pixels of the first wafer image and the second wafer image, it is possible to initially detect defects, facilitate more accurate identification of potential defects in the subsequent process, reduce the problem of false detection caused by background interference, and improve the efficiency and accuracy of wafer defect detection.
[0014] In an alternative embodiment, obtaining a first wafer image including defects to be detected and a second wafer image without defects includes:
[0015] Performing image simulation processing on the wafer object to be detected using an image simulation tool to obtain the first wafer image and the second wafer image;
[0016] Or,
[0017] Performing image acquisition on the wafer object to be detected using a target system to obtain the first wafer image and the second wafer image.
[0018] In the embodiments of the present disclosure, by performing image simulation processing on the wafer object to be detected using an image simulation tool, it is possible to obtain simulated first and second wafer images. By performing image acquisition on the wafer object to be detected using a target system, it is possible to obtain real first and second wafer images.
[0019] In an alternative embodiment, based on the pixel value of the first pixel in the differential image, separating potential defects in the differential image from the image background to obtain a potential defect image, including:
[0020] When obtaining the first wafer image and the second wafer image through image simulation processing, extracting the edges of potential defects in the differential image based on the pixel value of the first pixel in the differential image;
[0021] Based on the edges of the potential defects, separating the potential defects in the differential image from the image background to obtain a potential defect image;
[0022] Or,
[0023] When obtaining the first wafer image and the second wafer image using the target system, dividing the first pixel based on the pixel value of the first pixel in the differential image to determine the category to which the first pixel belongs;
[0024] Based on the category to which the first pixel belongs, separating the potential defects in the differential image from the image background to obtain a potential defect image.
[0025] In the embodiments of the present disclosure, by extracting the edges of potential defects in the differential image when obtaining the first wafer image and the second wafer image through image simulation processing, or determining the category to which the first pixel in the differential image belongs when obtaining the first wafer image and the second wafer image using the target system, and then separating the potential defects from the image background, potential defects can be obtained, facilitating more accurate identification of target defects subsequently and improving the efficiency and accuracy of wafer defect detection.
[0026] In an alternative embodiment, based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, determining target defects to obtain a target defect image, including:
[0027] Based on the pixel value and pixel coordinates of the second pixel in the potential defect image, fitting the potential defect image to obtain a fitted image;
[0028] When the numerical change value of the fitted image is greater than the preset threshold, determining the target defects and target information, where the target information is information describing the target defects;
[0029] Generating a target defect image based on the target information.
[0030] In the embodiments of the present disclosure, by fitting the potential defect image and determining the target information of the target defects when the numerical change value of the fitted image is greater than the preset threshold, the target defects can be accurately detected, improving the efficiency and accuracy of wafer defect detection.
[0031] In an alternative embodiment, after determining a target defect based on the relationship between the pixel value of a second pixel in the potential defect image and a preset threshold to obtain a target defect image, the method further includes:
[0032] Labeling the first wafer image based on the target information to obtain a labeled image;
[0033] Analyzing the target defect based on the target information to obtain an analysis result;
[0034] Obtaining a defect analysis report based on the labeled image and the analysis result.
[0035] In the embodiments of the present disclosure, by labeling the first wafer image to obtain a labeled image, analyzing the target defect to obtain an analysis result, and obtaining a defect analysis report based on the labeled image and the analysis result, a systematic analysis and comprehensive record of wafer defects can be achieved.
[0036] In a second aspect, the present disclosure provides a wafer defect detection device, which includes:
[0037] An acquisition module, configured to acquire a first wafer image containing defects and a second wafer image without defects to be detected;
[0038] A generation module, configured to perform differential processing on the first wafer image and the second wafer image to generate a differential image;
[0039] A first obtaining module, configured to separate potential defects in the differential image from the image background based on the pixel value of a first pixel in the differential image to obtain a potential defect image;
[0040] A second obtaining module, configured to determine a target defect based on the relationship between the pixel value of a second pixel in the potential defect image and a preset threshold to obtain a target defect image, where the preset threshold is the maximum value of the adjustable change of the pixel value of the second pixel.
[0041] In a third aspect, the present disclosure provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the wafer defect detection method according to the first aspect or any corresponding embodiment thereof.
[0042] In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the wafer defect detection method according to the first aspect or any corresponding embodiment thereof.
[0043] Fifth aspect, the present disclosure provides a computer program product, including computer instructions for causing a computer to execute the wafer defect detection method according to the first aspect or any corresponding embodiment thereof as described above. Description of the Drawings
[0044] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0045] Figure 1 is a flowchart of the wafer defect detection method according to an embodiment of the present disclosure;
[0046] Figure 2 is a first wafer image including defects obtained by using an image simulation tool according to an embodiment of the present disclosure;
[0047] Figure 3 is a first wafer image including defects obtained by using a target system according to an embodiment of the present disclosure;
[0048] Figure 4 is another first wafer image including defects obtained by using a target system according to an embodiment of the present disclosure;
[0049] Figure 5 is yet another first wafer image including defects obtained by using a target system according to an embodiment of the present disclosure;
[0050] Figure 6 is a second wafer image without defects obtained by using an image simulation tool according to an embodiment of the present disclosure;
[0051] Figure 7 is a differential image according to an embodiment of the present disclosure;
[0052] Figure 8 is a target defect image according to an embodiment of the present disclosure;
[0053] Figure 9 is a fitting image according to an embodiment of the present disclosure;
[0054] Figure 10 is another fitting image according to an embodiment of the present disclosure;
[0055] Figure 11 is yet another fitting image according to an embodiment of the present disclosure;
[0056] Figure 12It is a structural block diagram of a wafer defect detection device according to an embodiment of the present disclosure;
[0057] Figure 13 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. Specific embodiments
[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.
[0059] In the semiconductor manufacturing process, the detection of wafer surface defects is an important link to ensure product quality. Traditional wafer defect detection methods include optical microscopes and scanning electron microscopes, etc. Although these methods can provide high-resolution images, they have problems such as complex operation, slow detection speed, and large interference from the complex background of the wafer graphic structure. Especially for wafers with graphic structures (such as lithography patterns, etching patterns, etc.), traditional detection methods are difficult to effectively distinguish defects from graphic structures, thus affecting the accuracy of defect identification.
[0060] To solve the above problems, according to an embodiment of the present disclosure, an embodiment of a wafer defect detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.
[0061] In this embodiment, a wafer defect detection method is provided, as Figure 1 shown, Figure 1 It is a flowchart of the wafer defect detection method according to an embodiment of the present disclosure. This process can be applied to a server and includes the following steps:
[0062] Step S101, obtain a first wafer image containing defects and a second wafer image without defects to be detected.
[0063] Optionally, in the embodiment of the present disclosure, the wafer to be detected includes a first wafer containing defects and a second wafer without defects. As Figure 2 , Figure 3 , Figure 4 and Figure 5 shown, the first wafer image refers to the image corresponding to the first wafer containing defects, where Figure 2is the first wafer image obtained by using an image simulation tool, Figure 3 , Figure 4 and Figure 5 are respectively the first wafer images of three different forms of defects obtained by using the target system. As Figure 6 shown, the second wafer image refers to the image corresponding to the second wafer without defects.
[0064] Specifically, the server can use an image simulation tool or the target system to obtain the first wafer image of the first wafer with defects and the second wafer image of the second wafer without defects respectively.
[0065] In addition, after obtaining the images, the server can also perform image preprocessing on these images to remove noise and background interference. For example: the server can use filtering algorithms (such as Gaussian filtering, median filtering, etc.) to reduce image noise, or use methods such as contrast stretching and histogram equalization to improve the contrast of the images, making the defect features more prominent.
[0066] For the images obtained by using the target system, due to deviations in factors such as shooting angle, position, and illumination, the server can also register these images to align them so that they are consistent in terms of spatial position, scale, and direction.
[0067] Step S102, perform a difference operation on the first wafer image and the second wafer image to generate a difference image.
[0068] Optionally, in the embodiments of the present disclosure, the sizes and pixel positions of the first wafer image and the second wafer image correspond one by one. As Figure 7 shown, the difference image refers to the image containing the defective area.
[0069] Specifically, the server generates a difference image by processing the pixels at the corresponding positions of the first wafer image and the second wafer image. In the difference image, the pixel values of the pixels in the normal area approach 0, and the pixel values of the pixels in the defective area deviate from 0. Moreover, the greater the deviation degree, the more significant the difference between this area and the normal area, and the more likely it is the defective position.
[0070] Step S103, based on the pixel value of the first pixel in the difference image, separate the potential defects in the difference image from the image background to obtain a potential defect image.
[0071] Optionally, in the embodiments of the present disclosure, the first pixel refers to the pixel in the difference image. The potential defect refers to the area that is initially identified in the intermediate link of wafer defect detection and may belong to a defect. The potential defect image refers to the image containing potential defects and removing the background.
[0072] Specifically, since the defects have different pixel values from the image background, the server first obtains the pixel value of the first pixel in the difference image, and then, based on the difference in pixel values, uses image segmentation techniques (such as edge detection, clustering segmentation, etc.) to separate the potential defects in the difference image from the image background, obtaining a potential defect image.
[0073] Step S104: Based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, determine the target defect, obtaining a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can adjust and change.
[0074] Optionally, in the embodiments of the present disclosure, the second pixel refers to the pixel in the potential defect image. The target defect refers to the actual defect on the surface of the wafer finally detected after multiple rounds of identification. As Figure 8 shown, the target defect image refers to an image containing the target defect.
[0075] Specifically, the server first obtains the pixel value of the second pixel in the potential defect image, then analyzes the pixel value to obtain the change value of the pixel value (the absolute value of the difference between the pixel values of adjacent pixels or the gradient of the pixel values in a certain area), and determines the target defect based on the relationship between the change value of the pixel value and the preset threshold, obtaining a target defect image.
[0076] In the embodiments of the present disclosure, by obtaining a first wafer image containing defects to be detected and a second wafer image without defects; performing differential processing on the first wafer image and the second wafer image to generate a difference image; based on the pixel value of the first pixel in the difference image, separating the potential defects in the difference image from the image background, obtaining a potential defect image; based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, determining the target defect, obtaining a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can adjust and change. Since the embodiments of the present disclosure perform differential processing on the wafer images with and without defects, separate potential defects from the image background based on pixel values, and then determine the target defect based on pixel values and a preset threshold, it is possible to distinguish the graphic structure on the wafer surface from the target defect, achieve high-precision wafer defect detection, and improve the accuracy of wafer defect detection.
[0077] In some alternative embodiments, performing differential processing on the first wafer image and the second wafer image to generate a difference image includes:
[0078] Obtaining the difference between the pixel values of the corresponding pixels of the first wafer image and the second wafer image;
[0079] Generating a difference image according to the difference between the pixel values of the corresponding pixels.
[0080] Optionally, in the embodiments of the present disclosure, the server first obtains the pixel values of the pixels in the first wafer image and the second wafer image, then calculates the differences between the pixel values of the corresponding pixels in the first wafer image and the second wafer image in sequence to obtain a series of new pixel values, and then combines these new pixel values according to the pixel arrangement order of the first wafer image to generate a differential image.
[0081] In the embodiments of the present disclosure, by generating a differential image based on the differences between the pixel values of the corresponding pixels in the first wafer image and the second wafer image, defects can be preliminarily detected, which is convenient for more accurately identifying potential defects in the subsequent process, reducing the problem of false detection caused by background interference, and improving the efficiency and accuracy of wafer defect detection.
[0082] In some alternative embodiments, obtaining the first wafer image containing defects to be detected and the second wafer image not containing defects includes:
[0083] Performing image simulation processing on the wafer object to be detected by using an image simulation tool to obtain the first wafer image and the second wafer image;
[0084] Or,
[0085] Performing image acquisition on the wafer object to be detected by using a target system to obtain the first wafer image and the second wafer image.
[0086] Optionally, in the embodiments of the present disclosure, the image simulation tool may be software such as Python or Matlab, and the target system may be a high-resolution bright-field imaging system.
[0087] Specifically, the server may use the image simulation tool to perform simulation processing on the second wafer without defects to obtain the second wafer image, and then use the image simulation tool to add defects with the same pixel values or different pixel values to the second wafer image to obtain the first wafer image. The server may also use the target system to photograph the surface of the first wafer containing defects to obtain the first wafer image, and photograph the surface of the second wafer without defects to obtain the second wafer image.
[0088] It should be noted that Figure 2 the first wafer image containing defects with the same pixel values, since the wafer defect detection method for wafers containing defects with different pixel values is the same as that for wafers containing defects with the same pixel values, will not be elaborated here.
[0089] In the embodiments of the present disclosure, by performing image simulation processing on the wafer object to be detected by using an image simulation tool, simulated first and second wafer images can be obtained. By performing image acquisition on the wafer object to be detected by using a target system, real first and second wafer images can be obtained.
[0090] In some alternative embodiments, based on the pixel value of the first pixel in the difference image, separating potential defects in the difference image from the image background to obtain a potential defect image, including:
[0091] When obtaining the first wafer image and the second wafer image through image simulation processing, based on the pixel value of the first pixel in the difference image, extracting the edge of the potential defect in the difference image;
[0092] Based on the edge of the potential defect, separating the potential defect in the difference image from the image background to obtain a potential defect image;
[0093] Or,
[0094] When obtaining the first wafer image and the second wafer image using the target system, based on the pixel value of the first pixel in the difference image, dividing the first pixel to determine the category to which the first pixel belongs;
[0095] Based on the category to which the first pixel belongs, separating the potential defect in the difference image from the image background to obtain a potential defect image.
[0096] Optionally, in the embodiments of the present disclosure, when obtaining the first wafer image and the second wafer image through image simulation processing, since the image background is relatively simple, an edge detection algorithm (such as the Candy operator edge detection algorithm) can be used to separate potential defects from the image background to obtain a potential defect image; when obtaining the first wafer image and the second wafer image using the target system, since the image background is relatively complex, a clustering algorithm (such as the K-means clustering algorithm) can be used to separate potential defects from the image background to obtain a potential defect image.
[0097] Taking the difference image obtained through image simulation processing and difference processing as an example of the Candy operator edge detection algorithm: First, the server can perform Gaussian filtering on the difference image, perform weighted averaging on the first pixel in the difference image through a Gaussian filter, and reduce the interference of high-frequency noise. Then, the server calculates the gradient magnitude and direction of the first pixel in the difference image to obtain a gradient magnitude image.
[0098] Next, the server performs non-maximum suppression on each pixel in the gradient magnitude image, traverses each pixel in the gradient magnitude image, and determines whether the gradient magnitude of the pixel is the local maximum in its gradient direction: If not, set the gradient magnitude of the pixel to 0; if so, retain the gradient magnitude of the pixel.
[0099] After that, the server performs hysteresis thresholding on the gradient magnitude image, setting two different thresholds, including a high threshold and a low threshold. Pixels with a gradient magnitude greater than the high threshold are determined as edge points, and pixels with a gradient magnitude less than the low threshold are excluded as non-edge points. For pixels with a gradient magnitude between the high threshold and the low threshold, if the pixel is connected to the already determined edge points, it is also determined as an edge point; otherwise, it is excluded.
[0100] After extracting the edges of potential defects, these edges form a series of closed contours. The server can mark the area inside the contour as the potential defect area, extract the pixels within the potential defect area from the difference image, and remove or set the remaining pixels (i.e., the image background part) to a specific value (such as 0, representing black), obtaining a potential defect image that contains potential defects and removes the background.
[0101] For the difference image obtained by using the target system and differential processing, taking the K-means clustering algorithm as an example: First, the server randomly selects or selects K pixel points as the initial clustering centers according to experience. Then, the server calculates the distances between the first pixel in the difference image and the K clustering centers, and assigns each pixel to the category of the clustering center with the closest distance. Next, the server calculates the pixel mean of all pixels in each cluster and updates the position of each clustering center with the pixel mean.
[0102] The server repeats the above steps until the preset maximum number of iterations is reached, or the positions of the clustering centers no longer change significantly, that is, the moving distance of the clustering centers after two adjacent iterations is less than the preset distance threshold, then the update of the clustering centers stops, and the clustering category to which the first pixel in the difference image belongs is obtained.
[0103] After obtaining the clustering category to which each pixel in the difference image belongs, the server marks the pixels of different categories differently. Pixels belonging to the potential defect category are marked as the foreground, for example, setting the pixel values of these pixels to a specific value (such as 255, representing white), and pixels belonging to the image background category are marked as the background, for example, setting the pixel values of these pixels to another specific value (such as 0, representing black). Then, the pixels belonging to the potential defect category are extracted from the difference image, and the pixels belonging to the image background category (i.e., the image background part) are removed or set to a specific value (such as 0, representing black), obtaining a potential defect image that contains potential defects and removes the background.
[0104] In the embodiments of the present disclosure, when obtaining the first wafer image and the second wafer image through image simulation processing, the edges of potential defects in the differential image are extracted, or when obtaining the first wafer image and the second wafer image through the target system, the category to which the first pixel in the differential image belongs is determined, and then the potential defects are separated from the image background, so that potential defects can be obtained, which is convenient for more accurate identification of target defects in the subsequent process and improves the efficiency and accuracy of wafer defect detection.
[0105] In some alternative embodiments, based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, the target defect is determined to obtain a target defect image, including:
[0106] Fitting the potential defect image based on the pixel value and pixel coordinates of the second pixel in the potential defect image to obtain a fitted image;
[0107] When the numerical change value of the fitted image is greater than the preset threshold, the target defect and target information are determined, where the target information is information describing the target defect;
[0108] Generating a target defect image based on the target information.
[0109] Optionally, in the embodiments of the present disclosure, as Figure 9 , Figure 10 , Figure 11 shown, the fitted image refers to the image obtained by fitting the potential defect image, where Figure 9 is Figure 3 the fitted image of the potential defect of the corresponding first wafer, Figure 10 is Figure 4 the fitted image of the potential defect of the corresponding first wafer, Figure 11 is Figure 5 the fitted image of the potential defect of the corresponding first wafer. The target information includes the number of defects and the pixel coordinates, pixel values, areas, and shape features of each defect, etc.
[0110] Specifically, the server first extracts the pixel value and pixel coordinates of the second pixel in the potential defect image, and then uses a three-dimensional surface fitting algorithm to fit the potential defect image according to the pixel value and pixel coordinates to obtain a fitted image, where the value of the x-axis of the fitted image corresponds to the pixel coordinate of the second pixel in the x direction, the value of the y-axis corresponds to the pixel coordinate of the second pixel in the y direction, and the value of the z-axis corresponds to the pixel value of the second pixel.
[0111] After that, the server calculates the numerical change value of each region in the fitted image (the absolute value of the difference between the pixel values of adjacent pixels or the gradient of the pixel values within a certain region), and compares the numerical change value with a preset threshold. If the numerical change value of a certain region is greater than the preset threshold, that is, the numerical value within this region changes sharply, then this region is determined as the region where the target defect is located, and the target information of the target defect is obtained.
[0112] After obtaining the target information of the target defect, the server marks the target defect according to the target information. For example, the pixel values of the region where the target defect is located are set to a specific value (such as 255, representing white), and the pixel values of the region where the non-target defect is located are set to another specific value (such as 0, representing black), to obtain a target image containing the target defect.
[0113] In the embodiments of the present disclosure, by fitting the potential defect image and determining the target information of the target defect when the numerical change value of the fitted image is greater than the preset threshold, the target defect can be accurately detected, improving the efficiency and accuracy of wafer defect detection.
[0114] In some optional implementation manners, after determining the target defect based on the relationship between the pixel value of the second pixel in the potential defect image and the preset threshold and obtaining the target defect image, the method further includes:
[0115] Annotating the first wafer image based on the target information to obtain an annotated image;
[0116] Analyzing the target defect based on the target information to obtain an analysis result;
[0117] Obtaining a defect analysis report based on the annotated image and the analysis result.
[0118] Optionally, in the embodiments of the present disclosure, the annotated image refers to an image obtained by annotating the target defect on the first wafer image. The analysis result includes a possible impact assessment of the target defect, a possible root cause analysis of the target defect, etc. The defect analysis report includes the annotated image and the analysis result.
[0119] Specifically, after the server obtains the target information, it uses an annotation tool (such as an image editing software like Python) to annotate the target defect on the first wafer image to obtain an annotated image. Then, the server analyzes the target defect based on the target information, such as the possible impact of the target defect (such as increasing the chip failure probability, shortening the chip service life, increasing the chip power consumption, etc.), the possible root cause of the target defect (such as lithography process problems, etching process problems, etc.). Finally, the server integrates the annotated image and the analysis result to obtain a defect analysis report.
[0120] In the embodiments of the present disclosure, by annotating the first wafer image to obtain an annotated image, analyzing the target defect to obtain an analysis result, and obtaining a defect analysis report based on the annotated image and the analysis result, systematic analysis and comprehensive recording of wafer defects can be achieved.
[0121] In this embodiment, a wafer defect detection device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.
[0122] This embodiment provides a wafer defect detection device, as Figure 12 shown, including:
[0123] An acquisition module 1201, configured to acquire a first wafer image containing defects to be detected and a second wafer image not containing defects;
[0124] A generation module 1202, configured to perform differential processing on the first wafer image and the second wafer image to generate a differential image;
[0125] A first obtaining module 1203, configured to separate potential defects in the differential image from the image background based on the pixel value of the first pixel in the differential image to obtain a potential defect image;
[0126] A second obtaining module 1204, configured to determine a target defect based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, and obtain a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can be adjusted and changed.
[0127] In the embodiments of the present disclosure, by acquiring a first wafer image containing defects to be detected and a second wafer image not containing defects; performing differential processing on the first wafer image and the second wafer image to generate a differential image; separating potential defects in the differential image from the image background based on the pixel value of the first pixel in the differential image to obtain a potential defect image; and determining a target defect based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, and obtaining a target defect image, where the preset threshold is the maximum value that the pixel value of the second pixel can be adjusted and changed. Since the embodiments of the present disclosure perform differential processing on wafer images containing and not containing defects, separate potential defects from the image background based on pixel values, and then determine target defects based on pixel values and preset thresholds, the graphic structure on the wafer surface and target defects can be distinguished, high-precision wafer defect detection can be achieved, and the accuracy of wafer defect detection can be improved.
[0128] In some alternative embodiments, the generation module 1202 includes:
[0129] An acquisition sub-module, configured to acquire the difference between the pixel values of corresponding pixels of the first wafer image and the second wafer image;
[0130] A first generation sub-module, configured to generate a differential image based on the difference between the pixel values of corresponding pixels.
[0131] In some alternative embodiments, the acquisition module 1201 includes:
[0132] A first obtaining sub-module, configured to perform image simulation processing on the wafer object to be detected by using an image simulation tool, so as to obtain a first wafer image and a second wafer image;
[0133] A second obtaining sub-module, configured to perform image acquisition on the wafer object to be detected by using a target system, so as to obtain a first wafer image and a second wafer image.
[0134] In some alternative embodiments, the first obtaining module 1203 includes:
[0135] An extraction sub-module, configured to extract the edge of a potential defect in the differential image based on the pixel value of a first pixel in the differential image when the first wafer image and the second wafer image are obtained by using image simulation processing;
[0136] A third obtaining sub-module, configured to separate the potential defect in the differential image from the image background based on the edge of the potential defect, so as to obtain a potential defect image;
[0137] A first determination sub-module, configured to divide a first pixel based on the pixel value of the first pixel in the differential image and determine the category to which the first pixel belongs when the first wafer image and the second wafer image are obtained by using a target system;
[0138] A fourth obtaining sub-module, configured to separate the potential defect in the differential image from the image background based on the category to which the first pixel belongs, so as to obtain a potential defect image.
[0139] In some alternative embodiments, the second obtaining module 1204 includes:
[0140] A fifth obtaining sub-module, configured to perform fitting on the potential defect image based on the pixel value and pixel coordinates of a second pixel in the potential defect image, so as to obtain a fitting image;
[0141] A second determination sub-module, configured to determine a target defect and target information when the numerical change value of the fitting image is greater than a preset threshold, where the target information is information describing the target defect;
[0142] A second generation sub-module, configured to generate a target defect image based on target information.
[0143] In some alternative embodiments, the apparatus further includes:
[0144] An annotation module, configured to annotate a first wafer image based on target information to obtain an annotated image;
[0145] An analysis module, configured to analyze a target defect based on target information to obtain an analysis result;
[0146] A third obtaining module, configured to obtain a defect analysis report based on the annotated image and the analysis result.
[0147] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.
[0148] The wafer defect detection apparatus in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0149] This embodiment of the present disclosure further provides a computer device having the above-mentioned Figure 12 wafer defect detection apparatus.
[0150] Please refer to Figure 13 , Figure 13 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present disclosure. As shown in Figure 13 , the computer device includes: one or more processors 10, a memory 20, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphic information of a GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Figure 13 In
[0151] The processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.
[0152] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.
[0153] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may further include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.
[0154] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.
[0155] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
[0156] The embodiments of the present disclosure also provide a computer-readable storage medium. The method according to the embodiments of the present disclosure may be implemented in hardware, firmware, or may be implemented as computer code recorded on a storage medium, or may be implemented as computer code originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium may be a magnetic disk, an optical disc, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium may further include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component capable of storing or receiving software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.
[0157] A part of the present disclosure can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, it can call or provide the methods and / or technical solutions according to the present disclosure. Those skilled in the art should understand that the forms in which computer program instructions exist in a computer-readable medium include but are not limited to source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.
[0158] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A wafer defect detection method, characterized in that: The method comprises: Acquire a first wafer image to be detected that contains defects and a second wafer image that does not contain defects; performing differential processing on the first wafer image and the second wafer image to generate a differential image; Based on the pixel value of the first pixel in the differential image, the potential defect in the differential image is separated from the image background to obtain a potential defect image; Based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, the target defect is determined to obtain a target defect image, wherein the preset threshold is the maximum value of the adjustable change of the pixel value of the second pixel.
2. The method according to claim 1, characterized in that The performing differential processing on the first wafer image and the second wafer image to generate a differential image includes: Obtaining a difference between pixel values of corresponding pixels of the first wafer image and the second wafer image; The differential image is generated according to the difference in pixel values of the corresponding pixels.
3. The method according to claim 1, characterized in that The step of acquiring a first wafer image to be detected that contains defects and a second wafer image that does not contain defects includes: Using an image simulation tool to perform image simulation processing on the wafer object to be inspected, to obtain the first wafer image and the second wafer image; or, The target system is used to acquire images of the wafer object to be inspected, so as to obtain the first wafer image and the second wafer image.
4. The method according to claim 3, characterized in that The step of separating the potential defect in the differential image from the image background based on the pixel value of the first pixel in the differential image to obtain the potential defect image comprises: In a case where the first wafer image and the second wafer image are obtained by using the image simulation process, extracting an edge of the potential defect in the differential image based on a pixel value of the first pixel in the differential image; Based on the edge of the potential defect, the potential defect in the differential image is separated from the image background to obtain the potential defect image; or, In a case where the first wafer image and the second wafer image are obtained by using the target system, based on the pixel value of the first pixel in the differential image, the first pixel is divided to determine the category to which the first pixel belongs; Based on the category to which the first pixel belongs, the potential defect in the differential image is separated from the image background to obtain the potential defect image.
5. The method according to claim 1, characterized in that The step of determining the target defect based on the relationship between the pixel value of the second pixel in the potential defect image and the preset threshold value to obtain the target defect image includes: Fitting the potential defect image based on the pixel value and pixel coordinates of the second pixel in the potential defect image to obtain a fitted image; When the numerical change value of the fitting image is greater than the preset threshold, determining the target defect and target information, wherein the target information is information describing the target defect; The target defect image is generated based on the target information.
6. The method according to claim 5, characterized in that After determining the target defect based on the relationship between the pixel value of the second pixel in the potential defect image and the preset threshold value and obtaining the target defect image, the method further includes: Annotate the first wafer image based on the target information to obtain an annotated image; Analyze the target defect based on the target information to obtain an analysis result; A defect analysis report is obtained based on the annotated image and the analysis result.
7. A wafer defect detection device, characterized in that: The device comprises: An acquisition module, used for acquiring a first wafer image containing defects and a second wafer image not containing defects to be detected; A generating module, configured to perform differential processing on the first wafer image and the second wafer image to generate a differential image; A first obtaining module, configured to separate the potential defect in the differential image from the image background based on the pixel value of the first pixel in the differential image, so as to obtain a potential defect image; The second obtaining module is used to determine the target defect and obtain the target defect image based on the relationship between the pixel value of the second pixel in the potential defect image and a preset threshold, wherein the preset threshold is the maximum value of the adjustable change of the pixel value of the second pixel.
8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the wafer defect detection method according to any one of claims 1 to 6 by executing the computer instructions.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the wafer defect detection method according to any one of claims 1 to 6.
10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the wafer defect detection method according to any one of claims 1 to 6.