CN113935927A - Detection method, device and storage medium - Google Patents
Detection method, device and storage medium Download PDFInfo
- Publication number
- CN113935927A CN113935927A CN202111168471.XA CN202111168471A CN113935927A CN 113935927 A CN113935927 A CN 113935927A CN 202111168471 A CN202111168471 A CN 202111168471A CN 113935927 A CN113935927 A CN 113935927A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- threshold value
- defect
- defect area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 230000007547 defect Effects 0.000 claims abstract description 136
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a detection method, a detection device and a storage medium, wherein an image to be detected and at least two comparison images adjacent to the image to be detected are obtained; obtaining a difference image of an image to be detected and a comparison image; according to the gray level histogram of the difference image, carrying out binarization processing on the difference image to obtain a binarization image of the difference image; performing phase and processing on at least two binary images to obtain a binary image of an image to be detected; and determining the defect of which the area is greater than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result. Therefore, two differential images are formed through the two comparison images, the binary image of the image to be detected is obtained through the phase combination of the binary images of the two differential images, the complex calculation of the binary processing of the image to be detected is reduced, and the defect detection is realized on the premise of no template image.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to a detection method, a detection device and a storage medium.
Background
In the field of chip (or wafer or integrated circuit) manufacture, a chip needs to be detected, and an electronic microscope and other equipment are generally adopted to acquire an image of a microstructure on the chip, and the image is detected and analyzed to judge whether the chip is good or not.
The existing detection method adopts a template image mode to carry out matching detection on an image of a chip so as to detect the position and the size of the defect of the image of the chip.
The conventional mode of adopting the template image needs a large amount of time to manufacture the template image, and the defect detection cannot be carried out on the chip on the premise of no template image.
Disclosure of Invention
The invention mainly solves the technical problem that the existing detection method can not detect the defects on the premise of no template image.
According to a first aspect, there is provided in an embodiment a detection method comprising:
acquiring an image to be detected and at least two comparison images adjacent to the image to be detected;
obtaining a difference image of an image to be detected and a comparison image;
determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image;
performing phase and processing on at least two binary images to obtain a binary image of an image to be detected;
and determining the defect of which the area is greater than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result.
According to a second aspect, there is provided in an embodiment a detection apparatus comprising:
the image acquisition module is used for acquiring an image to be detected and at least two comparison images adjacent to the image to be detected;
the processing module is used for acquiring a difference image of the image to be detected and the contrast image; determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image; performing phase and processing on at least two binary images to obtain a binary image of an image to be detected; and determining the defect of which the area is greater than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result.
According to a third aspect, an embodiment provides a computer-readable storage medium having a program stored thereon, the program being executable by a processor to implement the detection method according to the first aspect.
According to the detection method, the detection device and the storage medium of the embodiment, the image to be detected and at least two comparison images adjacent to the image to be detected are obtained; obtaining a difference image of an image to be detected and a comparison image; determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image; performing phase and processing on at least two binary images to obtain a binary image of an image to be detected; and determining the defect of which the area is greater than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result. Therefore, two differential images are formed through the two comparison images, the binary image of the image to be detected is obtained through the phase combination of the binary images of the two differential images, the complex calculation of the binary processing of the image to be detected is reduced, and the defect detection is realized on the premise of no template image.
Drawings
FIG. 1 is a schematic structural diagram of a detection apparatus according to an embodiment;
FIG. 2 is a schematic flow chart of a detection method provided by an embodiment;
FIG. 3 is a schematic diagram of an image to be detected and a comparative image according to an embodiment;
FIG. 4 is a schematic diagram of a defect region provided in one embodiment;
FIG. 5 is a schematic diagram of a difference image in the detection method according to an embodiment;
FIG. 6 is another schematic diagram of a difference image in the detection method according to an embodiment;
FIG. 7 is a diagram illustrating a binarized image of a difference image in a detection method according to an embodiment;
FIG. 8 is a schematic diagram of a gray histogram of a difference image in a detection method according to an embodiment;
FIG. 9 is a schematic diagram of a binarized image of an image to be detected in the detection method according to an embodiment;
fig. 10 is a schematic diagram illustrating a defect detection result in the detection method according to an embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
Wafer defect inspection generally employs an electron microscope (e.g., a scanning electron microscope) to scan (photograph) and image a wafer, and finds defects on the wafer by finding and analyzing abnormal patterns on the image. In the existing image detection and analysis methods, an image to be detected and a template image (or called reference image or standard image) are mostly used for comparison, so that the template image is an indispensable ring of the existing image detection and analysis methods.
In the embodiment of the invention, at least two comparison images adjacent to the image to be detected are adopted, the phase comparison processing is carried out after the difference image is formed, the binarization processing is carried out to obtain the part only corresponding to the defect in the image to be detected, and then the defect detection and analysis are carried out, and the comparison and detection of the defect do not need to be carried out on the template image.
Referring to fig. 1, the present invention provides a detection apparatus, which includes an image acquisition module 10 and a processing module 20, and the detection apparatus provided by the present invention can be applied to a detection system, and the detection system can include the detection apparatus and a display module 30, or the detection apparatus provided by the present invention further includes the display module 30.
The image obtaining module 10 is configured to obtain a plurality of images to be detected of a wafer, where each image to be detected corresponds to a region to be detected on the wafer. The image capturing module 10 may be an electron microscope, such as a scanning electron microscope, or other image capturing modules 10 that may be used, such as an RGB camera. The specific equipment adopted by the device is determined according to the product object to be inspected.
The processing module 20 is configured to obtain an image to be detected and at least two images to be detected (defined as contrast images in this case) adjacent to the image to be detected. By adopting the detection method provided by the invention, the defects in the image to be detected are detected to obtain the corresponding detection result, and the detection result is sent to the display module 30. The display module 30 displays the detection result, and the display module 30 may be a display.
Specifically, the processing module 20 is configured to obtain a difference image between the image to be detected and the comparison image; determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image; performing phase and processing on at least two binary images to obtain a binary image of an image to be detected; and determining the defect of which the area is greater than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result. The processing module 20 may employ a device with operation processing capability, such as a processor, a single chip, a Programmable Logic Controller (PLC), a programmable logic array (FPGA), or the like.
The following describes a specific process of defect detection by a detection apparatus or system, and as shown in fig. 2, the detection method provided by the present invention includes the following steps:
step 1: as shown in fig. 3, the processing module 20 obtains the image to be detected and at least two contrast images adjacent to the image to be detected through the image obtaining module 10. The image to be detected is seen to have a pattern which is obviously distinguished in color and is black visually, for convenience of description, the area where the black pattern is located is defined as a defect area, and the area outside the defect area is defined as a background or a background area, wherein whether the two contrast images have the defect area is not limited. In reality, the color of the defect is not necessarily black, and the present embodiment describes the defect in fig. 3 as black for convenience of description only. As shown in fig. 4, it can be seen after the defect area is enlarged (for convenience of observation, the background color is uniformly defined as white, and the defect is defined as black), one defect area includes a plurality of discontinuous defects, and it is seen that the areas (the number of pixels) of the defects are different. Meanwhile, factors which are not defects exist, so that a black pattern with a small area appears, namely noise exists in an image to be detected.
Step 2: the processing module 20 obtains a difference image between the image to be detected and the contrast image.
As shown in fig. 5, for convenience of description, the image to be detected and the contrast image are defined as a single-channel image or a black-and-white image, and "0" and "255" in the figure represent pixel values or gray-scale values of pixel points. The following description will be made with the image to be detected and the contrast image being black and white images. In a conventional image, the pixel value of a pixel point of the image is 0-255. As can be seen, after the contrast image is subtracted from the image to be detected, the pixel value range of the difference image is-255.
As shown in fig. 6, if only the pixel points in the image to be detected or the contrast image are determined, it is difficult to determine the pixel points corresponding to the defect. And through the differential image, the pixel point with the largest difference between the image to be detected and the contrast image can be known. Two contrast images are adopted to obtain two corresponding difference images, and the difference images have the significance of increasing the pixel value difference degree between the defects and the background and facilitating screening of the defects during binarization. For example, as shown in the differential image shown in fig. 6, it can be seen that the absolute value of the pixel point at the lower left is the largest, which proves that the corresponding pixel point in the image to be detected can be regarded as a defect.
And step 3: the processing module 20 determines a binarization threshold according to the gray histogram of the difference image, and performs binarization processing on the difference image to obtain a binarized image of the difference image.
As shown in fig. 7, after the binarization processing is performed on the basis of the two difference images, the two difference images are waited for. It can be seen that the defect is set to be white from the original black, and the background is set to be black, because the background occupies most of the area of the image to be detected, and is set to be black, the pixel value is 0, and the calculation speed is high when the detection is performed. In fig. 3, both the two comparison images have defect regions, so that after the difference, the difference image 1 retains the defect regions of the comparison image 1 and the image to be detected, and the difference image 2 retains the defect regions of the comparison image 2 and the image to be detected. That is, the binary image of the difference image retains the different part of the image to be detected and the contrast image, correspondingly retains the information of the defect area, and subtracts the information of the background.
In a possible implementation manner, the determining the binarization threshold according to the gray level histogram of the difference image in step 3 may include the following steps:
step 301: and obtaining a preset defect area threshold according to the size of the image to be detected and a preset defect area ratio.
For example, if the size of the image to be detected is 100 pixels long and 1000 pixels wide, the area of the long and wide is 100000 pixels, and if the predetermined defect area ratio is 0.001, the predetermined defect area threshold is 100 pixels.
Step 302: and obtaining a binarization threshold value according to the gray level histogram, the threshold value deviation value and a preset defect area threshold value. And carrying out binarization according to different binarization threshold values, wherein the obtained images are different, and because the information corresponding to the defect is left after binarization, the information of the defect can be reserved only by the proper binarization threshold value, so that noise is reduced.
Specifically, the step 302 may include:
step 303: obtaining an accumulated sum of the number of pixel values in the gray histogram in a mode of accumulating one end part of the gray histogram to the middle part; another accumulated sum of the number of pixel values in the gradation histogram is obtained in such a manner that the other end portion of the gradation histogram is accumulated toward the middle.
For example, when adding from the left end to the middle, the number of pixel values of-255, -254, -253, -252, and-251 is 1, 2, 3, 1, and the sum of the sums corresponding to-255 to-251 is: 1+2+3+1+1 ═ 8. Similarly, accumulating from the right end to the middle also corresponds to an accumulated sum.
Step 304: and determining a first pixel value and a second pixel value corresponding to the two accumulated sums respectively equal to a preset defect area threshold. Wherein the first pixel value corresponds to an accumulated sum accumulated from the left end to the middle, and the second pixel value corresponds to an accumulated sum accumulated from the right end to the middle. Due to the fact that the specific numerical value of the binary threshold can be manually and directly divided, the mode lacks relevance with the image to be detected and defects. Therefore, the detection method provided by the invention can be applied to the actual application of the images to be detected with different sizes and the preset defect area ratio by associating the binary threshold (corresponding accumulated sum) with the preset defect area threshold (corresponding image size and preset defect area ratio).
As shown in fig. 8, the number of each pixel value is counted from two sides to the middle of the gray histogram, and the summation is performed respectively, and the counting is stopped when the preset defect area threshold is reached, so as to obtain the corresponding first pixel value and the second pixel value. For example, in FIG. 8, when the cumulative sum is 100, the corresponding pixel value is-60 on the left and 60 on the right (the left and right thresholds may not be equal), then the corresponding first pixel value is-60 and the second pixel value is 60.
Step 305: and respectively superposing the threshold deviation values on the first pixel value and the second pixel value to obtain a binary threshold, wherein the binary threshold comprises a first threshold P1 and a second threshold P2, P1 is the superposed value of the first pixel value and the threshold deviation value, and P2 is the superposed value of the second pixel value and the threshold deviation value. The concept of threshold deviation value is introduced, the adjustment is carried out corresponding to the edge of the defect, and the superposition of the threshold deviation value is carried out in the invention, not the direct superposition of A + B, but the superposition of A +/-B.
Specifically, for example, assuming that the threshold value is-60 on the left side and 60 on the right side when stopping, the threshold value corresponding to the stopping plus the threshold deviation value is the final binarization threshold value according to the threshold deviation value. The threshold deviation value is 15, the left side is addition and the right side is subtraction, the thresholds are-45 and 45. It is understood that the first threshold P1 and the second threshold P2 are close to each other at this time.
For another example, assuming that the threshold value at the left side is-60 and the threshold value at the right side is 60, the final binarization threshold value is obtained by adding the threshold deviation value to the corresponding threshold value at the time of stopping according to the threshold deviation value. The threshold offset value is 15, the left is subtracted and the right is added, the thresholds are-75 and 75. It is understood that the first threshold P1 and the second threshold P2 are expanded outward at this time.
In one possible implementation manner, as shown in fig. 7, the binarizing processing on the difference image in step 3 to obtain a binarized image of the difference image may include:
step 306: setting the pixel value of the pixel point with the pixel value P of P1 not less than P2 in the difference image as 0, and setting the pixel values of the pixel points with other pixel values in the difference image as a first preset pixel value, such as 253, 254 or 255, to obtain the binary image of the difference image.
As can be seen from the gray histogram shown in fig. 8, the pixel values of the pixels of the difference image are concentrated between the first threshold P1 and the second threshold P2, and the pixel value of the pixel corresponds to the background of the image to be detected, and the pixel value of the background region is set to 0, so that the obtained binary image becomes a sparse image, and the operation speed can be improved during detection and analysis. Therefore, noise generated in the acquired image to be detected is reduced, and the possibly generated non-defect area is removed in a mode of adjusting the pixel value to 0.
And 4, step 4: the processing module 20 performs a phase-and-inversion process on the at least two binarized images to obtain a binarized image of the image to be detected.
As shown in fig. 9, compared with the image to be detected in fig. 3, the binarized image of the image to be detected in fig. 9 only retains the defect region, and the background is set to be black. Therefore, the detection method can carry out high-quality binarization on the image to be detected, and noise is not generated on the background area. The binary images of the two differential images are subjected to phase comparison, so that different parts of the binary images of the two differential images can be removed, and the same parts are reserved, namely, the defect areas in the images to be detected are reserved. It can be understood that the two contrast images play the role of the template image through the differential back-phase and process.
And 5: the processing module 20 determines the defect of which the area in the binarized image of the image to be detected is greater than or equal to the preset defect area threshold value according to the preset defect area threshold value, so as to obtain a defect detection result. The method specifically comprises the following steps:
step 501: connected domain analysis is carried out on the binary image of the image to be detected, the connected domain analysis is four-connected domain analysis or eight-connected domain analysis, and the eight-connected domain analysis is adopted in the embodiment.
As shown in fig. 10, by eight-connected domain analysis, it can be obtained that four defects exist in a small region of a defect region, and at this time, the position and area (the number of included pixels) corresponding to each defect can be obtained by analysis. By adopting eight-connected domain analysis, the close defect characteristics in the image to be detected are taken as a related defect, so that the problem that the defect is judged wrongly due to the fact that the same defect is split into two or more defects after image processing and the different areas of the defects are smaller than the preset defect area is avoided.
Step 502: and obtaining a connected region with the area larger than or equal to the preset defect area threshold value according to the preset defect area threshold value.
For example, when the preset defect area threshold is 50, the connected region corresponding to only one defect in fig. 10 is greater than 50, and when the preset defect area threshold is 20, the connected regions corresponding to two defects in fig. 10 are greater than 20, at this time, the connected regions may be marked on the binarized image of the image to be detected, and the positions and the number of the defects may be recorded and then used for defect analysis.
Step 503: and obtaining the defect area and position of the corresponding defect of the communication region. The processing module 20 sends the defect detection result to the display module 30, and the defect detection result is displayed in the display module 30. The marked binarized image of the image to be detected may be displayed in the display module 30, or the defect area and position of the defect may be output, the number of defects being greater than the preset defect area threshold. For example, when the number of defects is greater than the preset number, the current piece to be detected is judged to be a defective product, and subsequent detection is not performed, so that the detection efficiency is improved.
In summary, the detection method forms two differential images through two comparison images, obtains the binary image of the image to be detected through the phase-joining mode of the binary images of the two differential images, reduces the complex calculation of the binary processing of the image to be detected, and realizes the defect detection on the premise of no template image.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (10)
1. A method of detection, comprising:
acquiring an image to be detected and at least two comparison images adjacent to the image to be detected;
acquiring a differential image of the image to be detected and the contrast image;
determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image;
performing phase and processing on at least two binary images to obtain a binary image of the image to be detected;
and determining the defect of which the area is larger than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result.
2. The detection method as claimed in claim 1, wherein said determining a binarization threshold value based on a gray histogram of said difference image comprises:
obtaining a preset defect area threshold according to the size of the image to be detected and a preset defect area ratio;
and obtaining a binarization threshold value according to the gray level histogram, the threshold value deviation value and the preset defect area threshold value.
3. The detection method as claimed in claim 2, wherein the obtaining a binarization threshold value according to the gray level histogram, the threshold deviation value and the preset defect area threshold value comprises:
obtaining an accumulated sum of the number of pixel values in the gray histogram in a manner that one end of the gray histogram is accumulated towards the middle; obtaining another accumulated sum of the number of pixel values in the gray histogram in a manner that another end of the gray histogram is accumulated toward the middle;
determining a first pixel value and a second pixel value corresponding to the two accumulated sums respectively equal to the preset defect area threshold;
and superposing the threshold deviation value on the first pixel value and the second pixel value respectively to obtain a binarization threshold value.
4. The detection method according to claim 3, wherein said binarizing said difference image to obtain a binarized image of said difference image comprises:
setting the pixel value of a pixel point with a pixel value P of P1 not less than P2 in the differential image as 0, and setting the pixel values of pixel points with other pixel values in the differential image as a first preset pixel value to obtain a binary image of the differential image, wherein P1 is the superposition value of the first pixel value and the threshold deviation value, and P2 is the superposition value of the second pixel value and the threshold deviation value.
5. The detection method according to any one of claims 1 to 4, wherein the determining the defect of which the area in the binarized image of the image to be detected is greater than or equal to the preset defect area threshold value according to the preset defect area threshold value to obtain a defect detection result comprises:
carrying out connected domain analysis on the binary image of the image to be detected;
according to a preset defect area threshold value, obtaining a connected region with the area larger than or equal to the preset defect area threshold value;
and obtaining the defect area and the position of the corresponding defect of the communication area.
6. The detection method of claim 5, wherein the connected domain analysis is a four connected domain analysis or an eight connected domain analysis.
7. A detection device, comprising:
the image acquisition module is used for acquiring an image to be detected and at least two comparison images adjacent to the image to be detected;
the processing module is used for acquiring a difference image of the image to be detected and the comparison image; determining a binarization threshold value according to the gray level histogram of the difference image, and performing binarization processing on the difference image to obtain a binarization image of the difference image; performing phase and processing on at least two binary images to obtain a binary image of the image to be detected; and determining the defect of which the area is larger than or equal to the preset defect area threshold value in the binary image of the image to be detected according to the preset defect area threshold value to obtain a defect detection result.
8. The detection apparatus as claimed in claim 7, wherein the processing module is configured to determine a binarization threshold according to a gray level histogram of the difference image, and comprises:
the processing module obtains a preset defect area threshold according to the size of the image to be detected and a preset defect area proportion; and obtaining a binarization threshold value according to the gray level histogram, the threshold value deviation value and the preset defect area threshold value.
9. The detection apparatus according to claim 7, wherein the processing module is configured to determine, according to a preset defect area threshold, a defect in the binarized image of the image to be detected, the area of which is greater than or equal to the preset defect area threshold, and obtain a defect detection result, and includes:
the processing module is used for carrying out connected domain analysis on the binary image of the image to be detected; according to a preset defect area threshold value, obtaining a connected region with the area larger than or equal to the preset defect area threshold value; and obtaining the defect area and the position of the corresponding defect of the communication area.
10. A computer-readable storage medium, characterized in that the medium has stored thereon a program executable by a processor to implement the detection method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111168471.XA CN113935927A (en) | 2021-09-29 | 2021-09-29 | Detection method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111168471.XA CN113935927A (en) | 2021-09-29 | 2021-09-29 | Detection method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935927A true CN113935927A (en) | 2022-01-14 |
Family
ID=79277874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111168471.XA Pending CN113935927A (en) | 2021-09-29 | 2021-09-29 | Detection method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935927A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648531A (en) * | 2022-05-20 | 2022-06-21 | 领伟创新智能系统(浙江)有限公司 | Solar panel surface dust identification method based on color channel brightness distribution |
| CN116758031A (en) * | 2023-06-16 | 2023-09-15 | 上海感图网络科技有限公司 | Golden finger defect rechecking method, device, equipment and storage medium |
-
2021
- 2021-09-29 CN CN202111168471.XA patent/CN113935927A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648531A (en) * | 2022-05-20 | 2022-06-21 | 领伟创新智能系统(浙江)有限公司 | Solar panel surface dust identification method based on color channel brightness distribution |
| CN116758031A (en) * | 2023-06-16 | 2023-09-15 | 上海感图网络科技有限公司 | Golden finger defect rechecking method, device, equipment and storage medium |
| CN116758031B (en) * | 2023-06-16 | 2024-03-29 | 上海感图网络科技有限公司 | Golden finger defect rechecking method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4776308B2 (en) | Image defect inspection apparatus, image defect inspection system, defect classification apparatus, and image defect inspection method | |
| JP4095860B2 (en) | Defect inspection method and apparatus | |
| TWI412739B (en) | Defect detection method and defect detection apparatus | |
| CN113935927A (en) | Detection method, device and storage medium | |
| JP2009259036A (en) | Image processing device, image processing method, image processing program, recording medium, and image processing system | |
| CN114022503A (en) | Detection method, detection system, device and storage medium | |
| CN111583258B (en) | Defect detection method, device, system and storage medium | |
| CN113785181A (en) | OLED screen point defect judgment method and device, storage medium and electronic equipment | |
| JP4244046B2 (en) | Image processing method and image processing apparatus | |
| KR101022187B1 (en) | Substrate inspection device | |
| JP2005165387A (en) | Method and device for detecting stripe defective of picture and display device | |
| JPH11337498A (en) | Apparatus and method for inspecting printed circuit board | |
| KR100754969B1 (en) | Image inspecting apparatus, image inspecting method, and computer-readable storage medium | |
| JP2006266943A (en) | Apparatus and method for inspecting defect | |
| JPH06207909A (en) | Inspection apparatus for surface defect | |
| JP3536884B2 (en) | Semiconductor wafer defect classification method and apparatus | |
| JP3906221B2 (en) | Image processing method and image processing apparatus | |
| JP2019100937A (en) | Defect inspection device and defect inspection method | |
| JP2831273B2 (en) | Appearance inspection method | |
| JP3753234B2 (en) | Defect detection method | |
| JP2009074828A (en) | Flaw detection method and flaw detector | |
| CN112801112B (en) | Image binarization processing method, device, medium and equipment | |
| JP2007047122A (en) | Image defect inspection device, defect classification device, and image defect inspection method | |
| Doniwar et al. | PCB Faults detection using Image processing | |
| JP2676990B2 (en) | Wiring pattern inspection equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |