Defect detection method, device, equipment and computer-readable storage medium

Abstract

The present application discloses a defect detection method, apparatus, device and computer-readable storage medium, wherein the defect detection device obtains a detection image of a part to be tested; determines a region to be tested in the detection image; performs binarization processing on the region to be tested to obtain a binary image; determines an edge region in the binary image, wherein the edge region includes a plurality of white pixels in the region to be tested; detects the pixels to be tested in the edge region along a first direction or along a second direction; determines the characteristic points of each column or each row on the edge region, and when the number of characteristic points is greater than or equal to a preset number, determines that the characteristic points are defects of the part to be tested. By determining the edge region of the region to be tested on a wafer, determining the characteristic points on the edge region, and then determining the defect of the part to be tested based on the characteristic points, the defect type on the part to be tested can be accurately determined by the position of the characteristic points, thereby improving the detection accuracy of the part to be tested, avoiding re-inspection due to low detection accuracy, and improving the detection efficiency of the part to be tested.

Description

Technical Field

[0001] The present application relates to the field of detection technology, and in particular to defect detection methods, devices, equipment, and computer-readable storage media. Background Art

[0002] During the wafer manufacturing process, different types of defects often appear in different functional areas of the wafer, especially for patterned wafers. The surface of patterned wafers often has multiple functional areas, and different circuits are connected through the functional areas. However, due to the influence of the manufacturing process or other factors, functional areas on patterned wafers often have defects such as pits or bumps, which affect the use of the functional areas.

[0003] In the prior art, when performing defect detection on a wafer, a template image is usually required to be used, and the inspection image of the wafer is compared with the template image. When the inspection image matches the template image to a high degree of match, it is determined that the wafer meets the usage requirements. When the inspection image matches the template image to a low degree of match, it is determined that there is a defect on the wafer. However, when judging defects by matching with the template image, defects similar to pits or protrusions on the wafer cannot be accurately detected, thereby reducing the detection accuracy, and re-inspection will reduce the detection efficiency of wafer detection. Therefore, how to accurately judge pits or protrusions on the wafer is an urgent problem to be solved. Summary of the Invention

[0004] Embodiments of the present application provide a defect detection method, apparatus, device, and computer-readable storage medium.

[0005] In a first aspect, an embodiment of the present application provides a defect detection method, the defect detection method comprising:

[0006] Acquire a test image of the test piece;

[0007] Determining a region to be detected in the detection image;

[0008] Performing binarization processing on the area to be measured to obtain a binary image;

[0009] Determining an edge area of ​​the area to be measured in the binary image;

[0010] Taking the pixel point of the edge area as the center and the preset detection length as the radius, the pixel point to be detected in the edge area is detected along the first direction or along the second direction;

[0011] Determine the characteristic points of each column or each row on the edge area, and when the number of the characteristic points is greater than or equal to a preset number, determine that the characteristic points are defects of the test piece.

[0012] Optionally, performing binarization processing on the area to be measured to obtain a binary image includes:

[0013] Determining a grayscale histogram of the area to be measured;

[0014] Determining a binary grayscale value according to the grayscale histogram;

[0015] The area to be measured is binarized according to the binarized grayscale value to obtain a binary image.

[0016] Optionally, determining a binarized grayscale value according to the grayscale histogram includes:

[0017] Determine the grayscale value distribution in the grayscale histogram whose grayscale values ​​are less than a preset grayscale value;

[0018] The grayscale value corresponding to the largest number of pixel points having grayscale values ​​less than the preset grayscale value is determined as the binarized grayscale value.

[0019] Optionally, the binarization process is performed on the area to be measured to obtain a binary image, and then the process further includes:

[0020] Performing connected region analysis on the binary image;

[0021] When the area of ​​a connected region formed by any pixel point and adjacent pixel points is smaller than a preset area, the connected region is removed.

[0022] Optionally, the determining of the edge region in the binary image further includes:

[0023] A detection area of ​​the binary image is determined according to the edge area and the preset length.

[0024] Optionally, detecting the pixel points to be detected in the edge area along the first direction or along the second direction includes:

[0025] Determining a detection direction of the pixel to be detected on the edge area;

[0026] Obtaining the detection length;

[0027] Determine the detection range of the pixel to be measured with the pixel to be measured as the center and the detection length as the radius;

[0028] The edge area is detected according to the detection range.

[0029] Optionally, obtaining the feature points of each column or each row on the edge area includes:

[0030] Determining a transition point of each column or each row on the edge area;

[0031] When the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be the feature point.

[0032] In a second aspect, an embodiment of the present application provides a defect detection device, comprising:

[0033] An acquisition unit, used for acquiring a detection image of the object to be tested;

[0034] A determination unit, configured to determine a region to be detected in the detection image;

[0035] An image processing unit, configured to perform binarization processing on the area to be measured to obtain a binary image;

[0036] The determining unit is further configured to determine an edge region of the region to be detected in the binary image;

[0037] a detection unit, configured to detect the pixel points to be detected in the edge area along a first direction or a second direction with the pixel points in the edge area as the center and a preset detection length as the radius;

[0038] The determining unit is further configured to determine feature points in each column or row on the edge area, and when the number of the feature points is greater than or equal to a preset number, determine that the feature points are defects of the test piece.

[0039] In a third aspect, an embodiment of the present application provides a defect detection device, comprising a processor, a memory, a transceiver, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the method described in any of the above embodiments.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute a method as described in any of the above embodiments.

[0041] It can be seen that in an embodiment of the present application, the defect detection method includes: obtaining a detection image of the part to be tested; determining the area to be tested of the detection image; binarizing the area to be tested to obtain a binary image; determining the edge area in the binary image, wherein the edge area includes a plurality of white pixel points of the area to be tested; taking the pixel points of the edge area as the center and the preset detection length as the radius, detecting the pixel points to be tested in the edge area along the first direction or along the second direction; determining the feature points of each column or each row on the edge area, and when the number of the feature points is greater than or equal to the preset number, determining the feature points as defects of the part to be tested. By determining the edge area of ​​the area to be tested on the wafer, determining the feature points on the edge area, and then determining the defect of the part to be tested based on the feature points, the defect type on the part to be tested can be accurately determined by the position of the feature points, thereby improving the detection accuracy of the part to be tested, avoiding re-inspection due to low detection accuracy, and improving the detection efficiency of the part to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 This is a flow chart of a defect detection method provided in an embodiment of the present application;

[0044] Figure 2 is a schematic diagram of a binary image provided in an embodiment of the present application;

[0045] Figure 3 is a schematic diagram of the detection area provided in an embodiment of the present application;

[0046] Figure 4 This is a schematic structural diagram of a defect detection device provided in an embodiment of the present application;

[0047] Figure 5 It is a structural schematic diagram of a defect detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0049] The following are detailed descriptions of each.

[0050] The terms "first," "second," "third," and "fourth," etc., in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0051] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] See Figure 1 , Figure 1 This is a flow chart of a defect detection method provided by an embodiment of the present application, such as Figure 1 As shown, the defect detection method includes:

[0053] Step 10: Acquire a test image of the test piece;

[0054] The device to be tested is a wafer. It is understandable that the device to be tested may also be a glass substrate or other products requiring surface testing.

[0055] It is understandable that the defect detection method described in this application can omit step 10 and directly execute the step of determining the area to be tested in the detection image in step 20 when the detection equipment has already collected the detection image of the test piece by other means.

[0056] Step 20, determining the area to be tested in the detection image;

[0057] The template image may be a template image preset by a user, or may be a test image of a standard part or other product. Specifically, the template image includes a test area for determining the part to be tested.

[0058] Among them, the area to be tested in the detection image corresponds to the area of ​​the device to be tested that needs to be tested. In a specific embodiment, the device to be tested is a wafer, and multiple conductive circuits are arranged on the wafer. In order to facilitate the simultaneous connection of multiple conductive circuits, a conductive protruding area is provided on the wafer, and the conductive protruding area is connected to multiple conductive circuits. When an external element needs to be connected to multiple conductive circuits at the same time, the external element can be directly connected to the conductive protruding area, thereby facilitating the connection of all conductive circuits connected to the conductive protruding area.

[0059] Step 30, performing binarization processing on the area to be measured to obtain a binary image;

[0060] In order to conveniently determine the position of the test area of ​​the test piece, it is first necessary to perform a binarization process on the test area to obtain a binary image, and then determine the test area based on the binary image.

[0061] In an optional embodiment, the binarization processing is performed on the area to be measured to obtain a binary image, including:

[0062] Determining a grayscale histogram of the area to be measured;

[0063] Determining a binary grayscale value according to the grayscale histogram;

[0064] The area to be measured is binarized according to the binarized grayscale value to obtain a binary image.

[0065] A grayscale histogram is used to analyze the grayscale distribution of an image or a region within it. Specifically, a grayscale histogram calculates the frequency of occurrence of all pixels in a digital image, based on their grayscale values. A grayscale histogram is a function of grayscale levels, representing the number of pixels with a certain grayscale level in an image and reflecting the frequency of occurrence of a specific grayscale level within the image.

[0066] Wherein, after determining the grayscale histogram, it is necessary to determine a binary grayscale value according to the grayscale histogram. Specifically, the binary grayscale value is used to perform a binarization process on the area to be tested, thereby obtaining a binary image. Specifically, when the grayscale value of a pixel point of the detection image is greater than or equal to the binary grayscale value, the grayscale value of the pixel point is adjusted to 255 through the binarization process. When the grayscale value of a pixel point of the detection image is less than the binary grayscale value, the grayscale value of the pixel point is adjusted to 0 through the binarization process. The binary grayscale value is used as the boundary of the binarization process, thereby dividing all the pixels on the detection image into white pixels with a grayscale value of 255 and black pixels with a grayscale value of 0, and converting the detection image into a binary image consisting of only white pixels and black pixels.

[0067] By determining the grayscale histogram and determining the binarized grayscale value, and obtaining a binary image after binarization processing according to the binarized grayscale value, the detection image can be converted into a binary image with only white pixels and black pixels, thereby facilitating the determination of the edge area of ​​the detection image, facilitating subsequent defect detection of the detection image, and improving the detection accuracy of the test piece.

[0068] In an optional implementation, determining the binarized grayscale value according to the grayscale histogram includes:

[0069] Determine the grayscale value distribution in the grayscale histogram whose grayscale values ​​are less than a preset grayscale value;

[0070] The grayscale value corresponding to the largest number of pixel points having grayscale values ​​less than the preset grayscale value is determined as the binarized grayscale value.

[0071] Among them, in order to facilitate the determination of the binary grayscale value, it is first necessary to determine the grayscale value in the grayscale histogram that is less than the preset grayscale value. In a specific embodiment, the detection image includes multiple pixels, each pixel has a grayscale value corresponding to it, and the bucket

[0072] By first determining the grayscale value distribution, determining the binarization grayscale value according to the grayscale value distribution, and then binarizing the detection image according to the binarization grayscale value, the impact on the details of the detection image during the binarization process is reduced, the loss of details is reduced, the noise generated during the image processing process is reduced, and the detection efficiency is improved.

[0073] In an optional embodiment, the binarization process is performed on the area to be measured to obtain a binary image, and then the method further includes:

[0074] Performing connected region analysis on the binary image;

[0075] When the area of ​​a connected region formed by any pixel point and adjacent pixel points is smaller than a preset area, the connected region is removed.

[0076] Among them, after the detection image is binarized and the binary image is obtained, there may be a plurality of noise points consisting of white pixels remaining on the binary image. The noise points will cause great interference to the subsequent defect detection of the test piece, thereby reducing the detection accuracy of the test piece.

[0077] In order to process the noise, a connected region analysis may be performed on the binary image, and each connected region with an area smaller than a preset area may be set as a noise region.

[0078] Specifically, a connected region generally refers to an image region consisting of adjacent foreground pixels with the same pixel value. Connected region analysis involves identifying and marking each connected region in an image. Connected region analysis primarily includes four-connected region analysis and eight-connected region analysis. Four-connected refers to connectivity between the same pixel in four directions: up, down, left, and right. Eight-connected refers to connectivity between the same pixel in eight directions: up, down, left, right, upper left corner, lower left corner, lower right corner, and upper right corner.

[0079] In an optional embodiment, the determining the edge area in the binary image further includes:

[0080] A detection area of ​​the binary image is determined according to the edge area and the preset length.

[0081] To facilitate detection of the binary image and prevent the conductive protrusion from shifting and thus preventing accurate detection, after determining the edge region corresponding to the large area to be detected in the binary image, it is necessary to further determine the detection region of the binary image based on the edge region and a preset length. In one specific embodiment, the preset length is 100 pixels, and the detection region is determined by extending the edge region by 100 pixels in the direction opposite to the white pixels, thereby determining the detection region corresponding to the edge region.

[0082] like Figure 3 Described area A is the area to be tested of the described part to be tested, a1a2, a2a3, a3a4 and a4a1 are the four side boundaries of the described area to be tested, and area B is the extended area of ​​the described area to be tested. When the preset length is 100 pixels, the distance between one side boundary of area B and the adjacent boundary on the same side of area A is 100 pixels, then the entire range of area A and area B is the detection area of ​​the binary image.

[0083] Step 40: determining the edge region of the area to be measured in the binary image, wherein the edge region includes a plurality of white pixels of the area to be measured;

[0084] In order to perform defect detection on the edge of the area to be detected, after the detection image is binarized, the edge area of ​​the area to be detected in the binary image needs to be binarized.

[0085] Wherein, determining the edge area of ​​the area to be measured in the binary image includes:

[0086] Determine the number of first pixels in each row of the binary image corresponding to the area to be measured along a first direction and the number of second pixels in each column along a second direction, where the first direction is perpendicular to the second direction;

[0087] The edge area of ​​the area to be measured in the binary image is determined according to the first number of pixels and the second number of pixels.

[0088] Among them, after the detection image is binarized and the binary image is obtained, in order to facilitate the determination of the edge area of ​​the area to be tested, it is also necessary to determine the number of first pixel points in each row of the binary image corresponding to the area to be tested along the first direction and the number of second pixel points in each column along the second direction. In a specific embodiment, the area to be tested is a rectangle, the first direction is parallel to one side edge of the area to be tested, the second direction is parallel to the other side edge of the area to be tested, and the first direction is perpendicular to the second direction.

[0089] The size of the area to be measured includes a first size along a first direction and a second size along a second direction, and determining the edge area of ​​the area to be measured in the binary image according to the first number of pixels and the second number of pixels further includes:

[0090] Determine a first preset number of preset areas to be tested in the template image along the first direction and a second preset number along the second direction;

[0091] The edge area of ​​the feature area in the detection image along the first direction is determined according to the first preset number and the first number of pixels, and the edge area of ​​the feature area in the detection image along the second direction is determined according to the second preset number and the second number of pixels.

[0092] In order to conveniently determine the edge area of ​​the area to be detected in the detection image, it is first necessary to determine the size of the preset area to be detected of the template image, and then determine the edge in the detection image according to the preset area to be detected.

[0093] The step of determining a first preset number of preset test areas in the template image along the first direction and a second preset number of preset test areas along the second direction includes:

[0094] Scanning the preset area to be tested row by row along a first direction to determine the number of pixels in each row along the first direction, and scanning the preset area to be tested column by column along a second direction to determine the number of pixels in each column along the second direction;

[0095] The first preset number is determined according to the number of pixels along the first direction, and the second preset number is determined according to the number of pixels along the first direction.

[0096] Among them, when the preset area to be tested is a rectangle, the number of pixels in each row of the preset area to be tested along the first direction is equal, then the number of pixels in any row along the first direction is the first preset number of the preset area to be tested, and the number of pixels in each column of the preset area to be tested along the second direction is equal, then the number of pixels in any column along the second direction is the first preset number of the preset area to be tested.

[0097] When the corners of the preset area to be tested are in the shape of a broken line or a circle, and the number of pixel points in each row of the preset area to be tested along the first direction is not equal, then the number of pixel points in the row with the largest number of pixel points along the first direction is determined to be the first preset number; if the number of pixel points in each column of the preset area to be tested along the second direction is not equal, then the number of pixel points in the column with the largest number of pixel points along the second direction is determined to be the second preset number;

[0098] The step of determining the edge area of ​​the area to be measured along the first direction according to the first preset number and the first number of pixels, and determining the edge area of ​​the area to be measured along the second direction according to the second preset number and the second number of pixels, includes:

[0099] When the ratio of the number of first pixels in any row of the area to be tested along the first direction to the first preset number reaches the first preset ratio, and the ratio of the number of first pixels in the first direction of the adjacent previous row to the first preset number does not reach the first preset ratio, the number of first pixels in the first direction of the row is determined to be an edge area on one side of the area to be tested along the first direction; when the ratio of the number of first pixels in any row of the area to be tested along the first direction to the first preset number reaches the first preset ratio, and the ratio of the number of first pixels in the first direction of the adjacent next row to the first preset number does not reach the first preset ratio, the number of first pixels in the first direction of the row is determined to be an edge area on the other side of the area to be tested along the first direction;

[0100] When the ratio of the number of first pixels in any column of the area to be tested along the second direction to the first preset number reaches the first preset ratio, and the ratio of the number of first pixels in the second direction of the adjacent previous column to the first preset number does not reach the first preset ratio, the number of first pixels in the second direction of the column is determined to be an edge area on one side of the area to be tested along the second direction. When the ratio of the number of first pixels in any column of the area to be tested along the second direction to the first preset number reaches the first preset ratio, and the ratio of the number of first pixels in the second direction of the adjacent next column to the first preset number does not reach the first preset ratio, the number of first pixels in the second direction of the column is determined to be an edge area on the other side of the area to be tested along the second direction.

[0101] The first preset ratio is 70%, 80% or other values.

[0102] The second preset ratio is 70%, 80% or other values.

[0103] Wherein, when the corners of the test area of ​​the test area are arc-shaped or broken line-shaped, the edge of the test area may not be detected, thereby improving the detection efficiency of the test area. In a specific embodiment, the first preset number of the template image along the first direction is 100 pixels, the second preset number along the second direction is 200 pixels, the first preset ratio is 80%, and the second preset ratio is 90%. When the feature area of ​​the detection image is detected row by row, when the ratio of the number of first pixels in any row to the first preset number reaches 80%, and the ratio of the number of first pixels in the previous row to the first preset number does not reach 80%, it is determined that the row position where the first pixel number is currently located is the edge of one side of the test area along the first direction. When the ratio of the number of first pixels in any row to the first preset number reaches 80%, and the ratio of the number of first pixels in the next row to the first preset number does not reach 80%, it is determined that the row position where the first pixel number is currently located is the edge of the other side of the test area along the first direction.

[0104] By analogy, when the ratio of the second number of pixels in any column to the first preset number reaches 90%, and the ratio of the second number of pixels in the previous column to the first preset number does not reach 90%, it is determined that the column position where the second number of pixels is currently located is the side edge of the area to be measured along the first direction; when the ratio of the second number of pixels in any column to the first preset number reaches 90%, and the ratio of the second number of pixels in the subsequent column to the first preset number does not reach 90%, it is determined that the column position where the second number of pixels is currently located is the other side edge of the area to be measured along the first direction.

[0105] By setting the first preset ratio and the second preset ratio, it is possible to avoid misjudgment of the characteristic area of ​​the detection image due to noise. In a specific embodiment, the first preset number is 100, and the first preset ratio is 80%, which are A1 to A100 respectively. First, the detection device performs detection row by row from left to right. When it is detected that the number of white pixels in row A19 is 79 and the number of white pixels in row A20 is 80, the number of pixels in row A19 is less than the product of the first preset number and the first preset ratio, and the number of pixels in row A20 is greater than or equal to the product of the first preset number and the first preset ratio. Therefore, the upper edge of the characteristic area of ​​row A20 is determined.

[0106] Similarly, when it is detected that the number of white pixels in row A80 is 80 and the number of white pixels in row A81 is 78, the number of pixels in row A80 is greater than or equal to the product of the first preset number and the first preset ratio, and the number of pixels in row A81 is less than the product of the first preset number and the first preset ratio, then row A80 is the lower edge of the feature area.

[0107] Step 50: Detect the pixel points to be detected in the edge area along the first direction or the second direction with the pixel points in the edge area as the center and the preset detection length as the radius;

[0108] In an optional embodiment, the detecting the pixel points to be detected in the edge area along the first direction or along the second direction includes:

[0109] Determining a detection direction of the pixel to be detected on the edge area;

[0110] Obtaining the detection length;

[0111] Determine the detection range of the pixel to be measured with the pixel to be measured as the center and the detection length as the radius;

[0112] The edge area is detected according to the detection range.

[0113] To facilitate detection of the pixel points to be tested in the edge region, it is first necessary to determine the detection direction of the pixel points to be tested in the edge region. Specifically, the edge region is a collection of white pixels at the edge of the pixel points to be tested, and each white pixel at the edge is a pixel point to be tested. When determining the detection direction, it is first determined whether there are white pixels in the up, down, left, and right directions of the pixel points to be tested. Specifically, the direction in which there are no white pixels along the circumference of the pixel points to be tested is determined as the detection direction.

[0114] like Figure 3As shown, the pixel to be tested is any pixel on a1a2, then there are white pixels to the left, bottom and right of the pixel to be tested, and there is no white pixel above the pixel to be tested, so the detection direction of the pixel to be tested is determined to be the up and down direction.

[0115] After determining the detection direction, the detection length must also be determined to facilitate detection. Specifically, the detection length can be a user-set value or a value calculated based on the length of the area to be detected along the detection direction or the area of ​​the area to be detected. In one embodiment, the detection length is the product of the size of the feature area along the detection direction and a preset coefficient. When the preset coefficient is 0.06 and the size of the area to be detected along the detection direction is 1000 pixels, the detection length is 1000 * 0.06 = 60 pixels.

[0116] When determining the detection direction and the detection length, the pixel to be detected is used as the center position of the detection range, and the radius of the detection range is half of the detection length to determine the detection range, and the edge area is detected according to the detection range.

[0117] In an optional embodiment, the corner areas of the conductive protruding area of ​​the piece to be tested are designed with rounded corners. When the conductive protruding area of ​​the piece to be tested is used, the rounded portion of the conductive protruding area is usually not used as the detection range of the piece to be tested. Therefore, in order to improve the detection efficiency of the piece to be tested, when determining the detection range of the edge area, it is necessary to first determine the radius of the rounded area, and redetermine the detection range based on the radius of the rounded area. Specifically, the length of the detection range in the left-right direction is the length of the edge area in the left-right direction minus twice the radius of the rounded area, and the length of the detection range in the up-down direction is the length of the edge area in the up-down direction minus twice the radius of the rounded area.

[0118] Step 60 : determining feature points in each column or row on the edge area, and determining that the feature points are defects of the test piece when the number of adjacent feature points along the same detection direction is greater than or equal to a preset number.

[0119] In an optional embodiment, obtaining the feature points of each column or each row on the edge area includes:

[0120] Determining a transition point of each column or each row on the edge area;

[0121] When the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be the feature point.

[0122] When any pixel in the binary image is a white pixel and there are black pixels in the up, down, left, and right directions of the pixel, the pixel is determined to be a transition point.

[0123] When determining a feature point based on a jump point, when the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be the feature point; when the distance between the jump point and the edge area is less than the preset length, the jump point is determined not to be the feature point.

[0124] Among them, when the test piece has pits or protrusion defects in the test area, the test area will have more feature points that are far away from the edge area. For example, when the feature point is located on the side of the edge area far away from the center of the test area, the area where the feature point is located has a protrusion defect; when the feature point is located on the side of the edge area close to the center of the test area, the area where the feature point is located has a pit defect.

[0125] Preferably, in order to improve the accuracy of defect detection, after determining all feature points, when the number of adjacent feature points along the same detection direction is greater than or equal to a preset number, it indicates that there are defects in the area of ​​the feature points; when the number of adjacent feature points along the same detection direction is less than the preset number, it indicates that there may be noise in the area of ​​the feature points or the existing defects do not affect the use requirements of the test piece, so the area where the feature points are located is not detected as a defect.

[0126] In an embodiment of the present application, the defect detection method includes: obtaining a detection image of the part to be tested; determining the area to be tested of the detection image; binarizing the area to be tested to obtain a binary image; determining the edge area in the binary image, wherein the edge area includes a plurality of white pixels of the area to be tested; taking the pixel points of the edge area as the center and a preset detection length as the radius, detecting the pixel points to be tested in the edge area along a first direction or along a second direction; determining the feature points of each column or each row on the edge area, and when the number of the feature points is greater than or equal to a preset number, determining the feature points as defects of the part to be tested. By determining the edge area of ​​the area to be tested on the wafer, determining the feature points on the edge area, and then determining the defect of the part to be tested based on the feature points, the defect type on the part to be tested can be accurately determined by the position of the feature points, thereby improving the detection accuracy of the part to be tested, avoiding re-inspection due to low detection accuracy, and improving the detection efficiency of the part to be tested.

[0127] See also Figure 4 , Figure 4This is a schematic diagram of the structure of a defect detection device provided by an embodiment of the present application. As shown in the figure, the service device includes a processor, a memory, a transceiver port, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. The programs include instructions for performing the following steps:

[0128] Acquire a test image of the test piece;

[0129] Determining a region to be detected in the detection image;

[0130] Performing binarization processing on the area to be measured to obtain a binary image;

[0131] Determining an edge area of ​​the area to be measured in the binary image;

[0132] Taking the pixel point of the edge area as the center and the preset detection length as the radius, the pixel point to be detected in the edge area is detected along the first direction or along the second direction;

[0133] Determine the characteristic points of each column or each row on the edge area, and when the number of the characteristic points is greater than or equal to a preset number, determine that the characteristic points are defects of the test piece.

[0134] In one implementation of the present application, in terms of performing binarization processing on the area to be measured to obtain a binary image, the program further includes instructions for executing the following steps:

[0135] Determining a grayscale histogram of the area to be measured;

[0136] Determining a binary grayscale value according to the grayscale histogram;

[0137] The area to be measured is binarized according to the binarized grayscale value to obtain a binary image.

[0138] In one implementation of the present application, in terms of determining the binarized grayscale value according to the grayscale histogram, the program further includes instructions for executing the following steps:

[0139] Determine the grayscale value distribution in the grayscale histogram whose grayscale values ​​are less than a preset grayscale value;

[0140] The grayscale value corresponding to the largest number of pixel points having grayscale values ​​less than the preset grayscale value is determined as the binarized grayscale value.

[0141] In one implementation of the present application, in terms of performing binarization processing on the area to be measured to obtain a binary image, the above program includes instructions for subsequently executing the following steps:

[0142] Performing connected region analysis on the binary image;

[0143] When the area of ​​a connected region formed by any pixel point and adjacent pixel points is smaller than a preset area, the connected region is removed.

[0144] In one implementation of the present application, in terms of determining the edge region in the binary image, the above program is further specifically configured to execute the following steps:

[0145] A detection area of ​​the binary image is determined according to the edge area and the preset length.

[0146] In one implementation of the present application, in terms of detecting the pixel points to be measured in the edge area along the first direction or along the second direction, the above program is further specifically used to execute instructions for the following steps:

[0147] Determining a detection direction of the pixel to be detected on the edge area;

[0148] Obtaining the detection length;

[0149] Determine the detection range of the pixel to be measured with the pixel to be measured as the center and the detection length as the radius;

[0150] The edge area is detected according to the detection range.

[0151] In one implementation of the present application, in terms of obtaining the feature points of each column or each row on the edge area, the program includes instructions for subsequently executing the following steps:

[0152] Determining a transition point of each column or each row on the edge area;

[0153] When the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be the feature point.

[0154] It should be noted that the specific implementation process of this embodiment can refer to the specific implementation process described in the above method embodiment, and will not be described again here.

[0155] See also Figure 5 , Figure 5 The present invention provides a defect detection device, which includes:

[0156] An acquisition unit 410 is used to acquire a detection image of the object to be tested;

[0157] A determination unit 420 is configured to determine a region to be detected in the detection image;

[0158] The image processing unit 430 is used to perform binarization processing on the area to be measured to obtain a binary image;

[0159] The determining unit 420 is further configured to determine an edge region of the region to be detected in the binary image;

[0160] A detection unit 440 is configured to detect the pixel points to be detected in the edge area along a first direction or a second direction with the pixel points in the edge area as the center and a preset detection length as the radius;

[0161] The determining unit 420 is further configured to determine feature points in each column or row on the edge region, and when the number of the feature points is greater than or equal to a preset number, determine that the feature points are defects of the test piece.

[0162] In one implementation of the present application, in performing binarization processing on the area to be measured to obtain a binary image, the determining unit 420 is specifically configured to:

[0163] Determining a grayscale histogram of the area to be measured;

[0164] Determining a binary grayscale value according to the grayscale histogram;

[0165] The region to be measured is binarized according to the binarized grayscale value to obtain a binary image. In one implementation of the present application, in determining the binarized grayscale value according to the grayscale histogram, the determining unit 420 is specifically configured to:

[0166] Determine the grayscale value distribution in the grayscale histogram having grayscale values ​​less than a preset grayscale value;

[0167] The grayscale value corresponding to the largest number of pixel points having grayscale values ​​less than the preset grayscale value is determined as the binarized grayscale value.

[0168] In one implementation of the present application, in performing binarization processing on the area to be measured to obtain a binary image, the determining unit 420 is specifically configured to:

[0169] Performing connected region analysis on the binary image;

[0170] When the area of ​​a connected region formed by any pixel point and adjacent pixel points is smaller than a preset area, the connected region is removed.

[0171] In one implementation of the present application, in terms of detecting the pixel points to be measured in the edge area along the first direction or along the second direction, the determining unit 420 is specifically configured to:

[0172] Determining a detection direction of the pixel to be detected on the edge area;

[0173] Obtaining the detection length;

[0174] Determine the detection range of the pixel to be measured with the pixel to be measured as the center and the detection length as the radius;

[0175] The edge area is detected according to the detection range.

[0176] In one implementation of the present application, in terms of obtaining the feature points of each column or each row on the edge area, the determining unit 420 is specifically configured to:

[0177] Determining a transition point of each column or each row on the edge area;

[0178] When the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be the feature point.

[0179] It should be noted that the determination unit 420 , the image processing unit 430 , and the detection unit 440 may be implemented by a processor, and the acquisition unit 410 may be implemented by a transceiver.

[0180] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described by the service device in the above method embodiment.

[0181] The present application also provides a computer program product, including a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to execute some or all of the steps described for the service device in the above method. The computer program product may be a software installation package.

[0182] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs), or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in an access network device, a target network device, or a core network device. Of course, the processor and the storage medium can also exist as discrete components in an access network device, a target network device, or a core network device.

[0183] Those skilled in the art will appreciate that, in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0184] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only a specific implementation method of the embodiments of the present application and is not intended to limit the scope of protection of the embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of protection of the embodiments of the present application.

Claims

1. A defect detection method, characterized in that: The defect detection method comprises: Acquire a test image of the test piece; Determining a region to be detected in the detection image; Performing binarization processing on the area to be measured to obtain a binary image; Determining an edge area of ​​the area to be measured in the binary image; Taking the pixel point of the edge area as the center and the preset detection length as the radius, the pixel point to be detected in the edge area is detected along the first direction or along the second direction; Determining a transition point for each column or row in the edge area; wherein, when any pixel in the binary image is a white pixel and there are black pixels above, below, left, and right of the pixel, the pixel is determined to be the transition point; When the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be a feature point; when the number of the feature points is greater than or equal to a preset number, the feature points are determined to be defects of the test piece.

2. The defect detection method according to claim 1, characterized in that: The binarization process is performed on the area to be measured to obtain a binary image, including: Determining a grayscale histogram of the area to be measured; Determining a binary grayscale value according to the grayscale histogram; The area to be measured is binarized according to the binarized grayscale value to obtain a binary image.

3. The defect detection method according to claim 2, characterized in that: Determining the binarized grayscale value according to the grayscale histogram includes: Determine the grayscale value distribution in the grayscale histogram having grayscale values ​​less than a preset grayscale value; The grayscale value corresponding to the largest number of pixel points having grayscale values ​​less than the preset grayscale value is determined as the binarized grayscale value.

4. The defect detection method according to claim 1, characterized in that: The binarization process is performed on the area to be measured to obtain a binary image, and then the method further includes: Performing connected region analysis on the binary image; When the area of ​​a connected region formed by any pixel point and adjacent pixel points is smaller than a preset area, the connected region is removed.

5. The defect detection method according to claim 1, characterized in that: The step of determining the edge region in the binary image further includes: A detection area of ​​the binary image is determined according to the edge area and the preset length.

6. The defect detection method according to claim 1, characterized in that: The detecting the pixel points to be detected in the edge area along the first direction or along the second direction includes: Determining a detection direction of the pixel to be detected on the edge area; Obtaining the detection length; Determine the detection range of the pixel to be measured with the pixel to be measured as the center and the detection length as the radius; The edge area is detected according to the detection range.

7. A defect detection device, characterized in that: The defect detection device comprises: An acquisition unit, used for acquiring a detection image of the object to be tested; A determination unit, configured to determine a region to be detected in the detection image; An image processing unit, configured to perform binarization processing on the area to be measured to obtain a binary image; The determining unit is further configured to determine an edge region of the region to be detected in the binary image; a detection unit, configured to detect the pixel points to be detected in the edge area along a first direction or a second direction with the pixel points in the edge area as the center and a preset detection length as the radius; The determination unit is further used to determine the jump point of each column or each row on the edge area; wherein, when any pixel point in the binary image is a white pixel point, and there are black pixels in the upper, lower, left and right directions of the pixel point, the pixel point is determined to be the jump point; when the distance between the jump point and the edge area is greater than or equal to a preset length, the jump point is determined to be a feature point, and when the number of the feature points is greater than or equal to a preset number, the feature point is determined to be a defect of the part to be tested.

8. A defect detection device, characterized in that: The method comprises a processor, a memory, a transceiver, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 6.

Images