CN117611566A - Defect detection method, defect detection system, electronic equipment and storage medium - Google Patents
Defect detection method, defect detection system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117611566A CN117611566A CN202311667644.1A CN202311667644A CN117611566A CN 117611566 A CN117611566 A CN 117611566A CN 202311667644 A CN202311667644 A CN 202311667644A CN 117611566 A CN117611566 A CN 117611566A
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- edge position
- coordinate data
- sub
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 154
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000012216 screening Methods 0.000 claims abstract description 24
- 230000002950 deficient Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 abstract description 33
- 238000001914 filtration Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 238000009499 grossing Methods 0.000 description 6
- 238000005192 partition Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a defect detection method, a defect detection system, electronic equipment and a storage medium. The method comprises the steps of obtaining an image of an object to be detected; dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions; and extracting point coordinates of the edge position in any sub-region to obtain a point coordinate data set. And screening the point coordinate data set based on the fitting condition to obtain the effective point coordinate data set. And selecting a defect judging area, setting a return parameter and a threshold value, and judging a defect result of the defect judging area. In the fitting condition screening process, required data of defect detection are synchronously acquired, return parameters and threshold values are set, defect detection is rapidly achieved, and defect coordinates are acquired. The defect detection method has the advantages of small calculated amount and low hardware resource consumption, and is suitable for high-speed parallel operation of the FPGA; and the method does not limit the currently acquired edge data of the object to be detected or fit the screened coordinates, and has strong applicability and high detection efficiency.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a defect detection method, system, electronic device, and storage medium.
Background
With the development of defect detection technology, the method for automatically detecting the appearance defects of industrial products by using an artificial intelligence algorithm gradually replaces manual detection to improve the defect detection efficiency has very important application prospect.
The lines or lines present on the image generally correspond to the boundaries of the actual object. Many industrial detection scenes need to detect the linear edge, for example, most of linear detection algorithms such as linear boundaries of electronic elements and linear boundaries of mechanical parts only output linear coordinate information, and no information prompt or judgment condition about whether defects exist in the linear boundaries.
Based on the technical problems, chinese patent CN 115222701A discloses a surface defect detection method and system based on straight line fitting. The application establishes a datum line by straight line fitting based on the acquisition of continuous data in any direction, judges whether a sampling point is a defect point based on a datum value corresponding to the datum line, and judges the defect type. For the non-continuous data, the method of judging with the straight line fitting result as a reference is not referred to in this patent. In addition, the method is not operable for straight line fitting results and fitting results obtained by other methods.
Chinese patent CN 115375679B discloses a method and apparatus for locating a defective chip by edge and point searching. The patent proposes that a morphological gradient algorithm is adopted to detect the edge of a defective chip based on the position information of the defective chip, and the center position of the chip is determined; and after scoring and covering operation is carried out according to the best chip outline and a preset rectangular area, carrying out edge straight line fitting operation by adopting a preset least square method to obtain a defect center coordinate, and dividing the preset rectangular area according to the center position of the chip. This patent is different from the technical means of the present application.
Disclosure of Invention
The present invention provides a defect detection method, system, electronic device and storage medium, which can solve at least one of the above technical problems.
In order to achieve the above purpose, the present invention proposes the following technical solutions:
a defect detection method, comprising:
acquiring an image of an object to be measured;
dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions;
extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions;
screening the point coordinate data set based on fitting conditions to obtain an effective point coordinate data set;
and selecting a defect judging area, setting a return parameter and a threshold value, and judging a defect result of the defect judging area.
Further, the dividing the image along any edge position direction to obtain sub-regions corresponding to a plurality of edge position directions includes: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
Further, the setting the return parameter and the threshold value includes: in the defect judging area, the ratio of the number of sub-areas of the effective point coordinate data set to the number of sub-areas of the point coordinate data set is taken as a return parameter.
Further, the judging the defect result of the defect judging area includes: if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, judging that the defect judging area is defective, and synchronously acquiring the point coordinates of the defect.
Further, the method further comprises the following steps: and obtaining a fitting result of the image to be measured based on the effective point coordinate data set.
Further, the method further comprises the following steps: based on the defect result, the user selects to output or not to output the fitting result of the image to be measured.
The invention also provides a defect detection system, which comprises:
the acquisition unit acquires an image of an object to be detected;
the data screening unit is used for dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions; extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions; screening the point coordinate data set based on fitting conditions to obtain an effective point coordinate data set;
a defect detection unit for selecting a defect determination area, setting a return parameter and a threshold value, and determining a defect result of the defect determination area; in the defect judging area, the ratio of the number of the subareas of the effective point coordinate data set to the number of the subareas of the point coordinate data set is used as a return parameter; if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, judging that the defect judging area is defective, and synchronously acquiring the point coordinates of the defect;
the fitting unit is used for obtaining a fitting result of the image to be measured based on the effective point coordinate data set; based on the defect result, the user selects to output or not to output the fitting result of the image to be measured.
Further, the dividing the image along any edge position direction to obtain sub-regions corresponding to a plurality of edge position directions includes: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
The invention also proposes an electronic device comprising a memory in which a computer program is stored and a processor arranged to run the computer program to perform the above-mentioned defect detection method.
The present invention also proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a defect detection method as described above.
The beneficial effects of the invention are as follows:
1. the application provides a defect detection method, which is used for extracting an ROI (region of interest) based on an acquired image of an object to be detected, synchronously setting a return parameter and a threshold of a current ROI, rapidly judging whether the current ROI is a defect ROI, and obtaining coordinate information of a defect;
2. based on the judging result of the defect ROI, the user can flexibly set whether to output the fitting result of the current ROI;
3. the method is suitable for any edge fitting/detecting method, does not limit whether the currently acquired edge data of the object to be detected are continuous, and is high in applicability and high in detecting efficiency;
4. according to the defect detection method, required data of defect detection are synchronously acquired in the screening process of fitting conditions, and compared with a traditional screening mode, the defect detection method is small in calculated amount, low in hardware resource consumption and suitable for FPGA high-speed parallel operation.
Drawings
FIG. 1 is a flow chart of a defect detection method;
FIG. 2 is a schematic illustration of defect detection of a straight edge;
FIG. 3 is a schematic diagram of defect detection of a curved edge.
Description of the embodiments
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
As shown in fig. 1, the present invention proposes a defect detection method, which is suitable for high-speed operation of an FPGA, and includes:
and acquiring an image of the object to be measured.
Dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions. And extracting point coordinates of edge positions in any sub-region to obtain a point coordinate data set of a plurality of sub-regions. The method specifically comprises the following steps: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
In this embodiment, an image of the object to be measured is acquired, and based on the boundary of the object to be measured, an image edge curve corresponding to the boundary may be coarsely located from the image. And taking the tangential direction of the image edge curve as the edge position direction, and equidistantly arranging a plurality of blocks along the edge position direction to obtain sub-areas corresponding to the plurality of edge position directions. At this time, the sub-regions are distributed along the edge position direction. The image edge curve in the invention comprises straight lines and curved lines.
Preferably, if the pipeline operation is performed, a template library can be established, and standard images are established for the same type of similar products. The edge curve of the standard image is used as a rough positioning reference, so that the data processing efficiency is accelerated.
As shown in fig. 2, at least one region of interest ROI (region of interest) in the image is extracted, and the current ROI is segmented into a plurality of sub-regions along the vertical edge position direction by employing a plurality of matrix segments. Preferably, a sector-shaped partition may be used to obtain several sub-regions, and the partition shape is not limited in this embodiment, but the selection range of any sub-region must be kept consistent.
If the current image to be measured is circular or similar in edge position, the embodiment provides a sub-region segmentation schematic diagram for the current image. As shown in fig. 3, any rectangular block is equidistantly arranged along the edge of the outer circle, and is perpendicular to the tangential direction of the circular arc.
Extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions, wherein the method specifically comprises the following steps:
performing row-column operation on the image data in the subareas to obtain a one-dimensional vector; wherein the row-column operation is a column average operation or a row average operation; and smoothing the one-dimensional vector by adopting Gaussian filtering to filter out tiny noise points, so that the image of the currently processed subarea is clearer and more reliable, and gradient calculation is facilitated. Preferably, the sub-area image can be simply smoothed by adopting small-size mean filtering or median filtering according to actual conditions.
And carrying out gradient calculation on the sub-region image subjected to the smoothing treatment to obtain the position and the size of a gradient extreme value, and outputting point coordinates (x, y) of the edge position according to preset gradient screening conditions. Preferably, the second derivative may also be used to obtain the point coordinates of the edge location.
The processing of image data in the above-described sub-areas is only illustrated as an example. Preferably, filtering and denoising can be performed on the image to realize smoothing treatment; performing row-column operation to obtain a one-dimensional vector; and gradient calculation or second derivative is adopted for the one-dimensional vector to obtain the point coordinates of the edge position. Or the first derivative or the second derivative is adopted to obtain edge points of the subareas; performing row-column operation to obtain a one-dimensional vector; and finally, filtering and denoising.
And sequentially processing the image data in the subareas to obtain a point coordinate data set of a plurality of subareas.
And screening the point coordinate data set based on the fitting condition to obtain the effective point coordinate data set.
In general, in order to meet the requirement of subsequent straight line fitting or curve fitting, the actual edge information closer to the object to be measured is obtained, and condition screening is performed on the obtained point coordinates to obtain an effective point coordinate data set. The specific screening conditions are optionally set by the user.
And obtaining a fitting result of the image to be measured based on the effective point coordinate data set.
And acquiring an effective point coordinate data set by the screening point coordinate data set, wherein the subarea containing the effective point coordinates is an effective subarea. And carrying out data fitting on the current ROI based on the coordinate data in the effective region to obtain a fitting result of the current ROI, thereby obtaining a fitting result of the image to be measured. In this embodiment, the continuity of the effective sub-region is not limited, that is, the continuity of the coordinates of the points in the current ROI is not limited; similarly, the continuity of fitting data of the image to be measured is not limited.
And selecting a defect judging area, setting a return parameter and a threshold value, and judging a defect result of the defect judging area. In the present application, the defect determination area may be a single sub-area or a set of multiple sub-areas, and the maximum selection range of the defect determination area is all sub-areas.
The method comprises the following steps: in the defect judging area, the ratio of the number of sub-areas of the effective point coordinate data set to the number of sub-areas of the point coordinate data set is taken as a return parameter.
The judgment conditions are as follows: if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, it is determined that there is a defect in the defect determination area, and the point coordinates of the defect (position) are synchronously acquired.
In this embodiment, the ROI is used as the defect determination area, so as to sequentially implement defect determination of any ROI, thereby completing defect determination of the image to be measured. The method comprises the following steps:
through the screening process of the effective subregions, the following can be known: the total number of sub-regions in the current ROI is L0, the number of effective sub-regions is L1, and a return parameter length_per=L1/L0 of the current ROI is set; or the return parameter is set to be the ratio of the non-valid sub-area to the total number of sub-areas, i.e., length_per= (L0-L1)/L0. A threshold value of length_per is set, and if the current ROI does not satisfy the threshold value, the current ROI is determined as a defective ROI, and the point coordinates of the defective position are acquired.
Through the defect judging process, finally outputting defect information, wherein the defect information comprises that the current ROI is a defect ROI or that the current ROI is a non-defect ROI; if the current ROI is the defect ROI, synchronously outputting the point coordinates of the defect position.
The above defect ROI determination process can occur before ROI fitting, and determine whether to continue the ROI fitting process according to the determination result of the defect ROI, so as to improve the data processing efficiency and increase the referential of the output result.
The above-mentioned defect ROI determination process may also occur after ROI fitting, and the determination result of the defect ROI may be used as one of the determination bases for the accuracy of the ROI fitting result.
In this embodiment, according to the determination result of the defect ROI, the user can set whether to output the fitting result of the current ROI.
In the fitting process of the ROI, the return parameters and the threshold value are set by using the screening result of the effective point coordinates, so that whether the current ROI is a defect ROI or not is rapidly judged, and defect coordinate information is synchronously acquired; no new operation process is generated in the process, i.e. the hardware resource consumption is not increased.
Based on the same inventive concept, the invention also provides a defect detection system, comprising:
and the acquisition unit acquires an image of the object to be detected.
The data screening unit is used for dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions; and extracting point coordinates of edge positions in any sub-region to obtain a point coordinate data set of a plurality of sub-regions. The method specifically comprises the following steps: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
In this embodiment, an image of the object to be measured is acquired, and based on the boundary of the object to be measured, an image edge curve corresponding to the boundary may be coarsely located from the image. And taking the tangential direction of the image edge curve as the edge position direction, and equidistantly arranging a plurality of blocks along the edge position direction to obtain sub-areas corresponding to the plurality of edge position directions. At this time, the sub-regions are distributed along the edge position direction. The image edge curve in the invention comprises straight lines and curved lines.
Preferably, if the pipeline operation is performed, a template library can be established, and standard images are established for the same type of similar products. The edge curve of the standard image is used as a rough positioning reference, so that the data processing efficiency is accelerated.
As shown in fig. 2, at least one region of interest ROI (region of interest) in the image is extracted, and the current ROI is segmented into a plurality of sub-regions along the vertical edge position direction by employing a plurality of matrix segments. Preferably, a sector-shaped partition may be used to obtain several sub-regions, and the partition shape is not limited in this embodiment, but the selection range of any sub-region must be kept consistent.
If the current image to be measured is circular or similar in edge position, the embodiment provides a sub-region segmentation schematic diagram for the current image. As shown in fig. 3, any rectangular block is equidistantly arranged along the edge of the outer circle, and is perpendicular to the tangential direction of the circular arc.
Extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions, wherein the method specifically comprises the following steps:
performing row-column operation on the image data in the subareas to obtain a one-dimensional vector; wherein the row-column operation is a column average operation or a row average operation; and smoothing the one-dimensional vector by adopting Gaussian filtering to filter out tiny noise points, so that the image of the currently processed subarea is clearer and more reliable, and gradient calculation is facilitated. Preferably, the sub-area image can be simply smoothed by adopting small-size mean filtering or median filtering according to actual conditions.
And carrying out gradient calculation on the sub-region image subjected to the smoothing treatment to obtain the position and the size of a gradient extreme value, and outputting point coordinates (x, y) of the edge position according to preset gradient screening conditions. Preferably, the second derivative may also be used to obtain the point coordinates of the edge location.
The processing of image data in the above-described sub-areas is only illustrated as an example. Preferably, filtering and denoising can be performed on the image to realize smoothing treatment; performing row-column operation to obtain a one-dimensional vector; and gradient calculation or second derivative is adopted for the one-dimensional vector to obtain the point coordinates of the edge position. Or the first derivative or the second derivative is adopted to obtain edge points of the subareas; performing row-column operation to obtain a one-dimensional vector; and finally, filtering and denoising.
And sequentially processing the image data in the subareas to obtain a point coordinate data set of a plurality of subareas.
And screening the point coordinate data set based on the fitting condition to obtain the effective point coordinate data set.
In general, in order to meet the requirement of subsequent straight line fitting or curve fitting, the actual edge information closer to the object to be measured is obtained, and condition screening is performed on the obtained point coordinates to obtain an effective point coordinate data set. The specific screening conditions are optionally set by the user.
A defect detection unit for selecting a defect determination area, setting a return parameter and a threshold value, and determining a defect result of the defect determination area; in the defect judging area, the ratio of the number of the subareas of the effective point coordinate data set to the number of the subareas of the point coordinate data set is used as a return parameter; if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, judging that the defect judging area is defective, and synchronously acquiring the point coordinates of the defect. In the present application, the defect determination area may be a single sub-area or a set of multiple sub-areas, and the maximum selection range of the defect determination area is all sub-areas.
In this embodiment, the ROI is used as the defect determination area, so as to sequentially implement defect determination of any ROI, thereby completing defect determination of the image to be measured. The method comprises the following steps:
through the screening process of the effective subregions, the following can be known: the total number of sub-regions in the current ROI is L0, the number of effective sub-regions is L1, and a return parameter length_per=L1/L0 of the current ROI is set; or the return parameter is set to be the ratio of the non-valid sub-area to the total number of sub-areas, i.e., length_per= (L0-L1)/L0. A threshold value of length_per is set, and if the current ROI does not satisfy the threshold value, the current ROI is determined as a defective ROI, and the point coordinates of the defective position are acquired.
Through the defect judging process, finally outputting defect information, wherein the defect information comprises that the current ROI is a defect ROI or that the current ROI is a non-defect ROI; if the current ROI is the defect ROI, synchronously outputting the point coordinates of the defect position.
The fitting unit is used for obtaining a fitting result of the image to be measured based on the effective point coordinate data set; based on the defect result, the user selects to output or not to output the fitting result of the image to be measured.
And acquiring an effective point coordinate data set by the screening point coordinate data set, wherein the subarea containing the effective point coordinates is an effective subarea. And carrying out data fitting on the current ROI based on the coordinate data in the effective region to obtain a fitting result of the current ROI, thereby obtaining a fitting result of the image to be measured. In this embodiment, the continuity of the effective sub-region is not limited, that is, the continuity of the coordinates of the points in the current ROI is not limited; similarly, the continuity of fitting data of the image to be measured is not limited.
In the system, the operation sequence of the defect detection unit and the fitting unit is not distinguished.
The operation process of the defect detection unit can occur before the fitting unit, and the determination result of the defect ROI is used for determining whether to continue the ROI fitting process, so that the data processing efficiency is improved, and the referential of the output result is increased.
The defect detection unit may also take the determination result of the defect ROI after the fitting unit as one of the determination bases for the accuracy of the ROI fitting result. In this embodiment, the user may set whether to output the fitting result of the current ROI according to the determination result of the defective ROI.
The invention also proposes an electronic device comprising a memory in which a computer program is stored and a processor arranged to run the computer program to perform the above-mentioned defect detection method.
The present invention also proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a defect detection method as described above.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A defect detection method, comprising:
acquiring an image of an object to be measured;
dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions;
extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions;
screening the point coordinate data set based on fitting conditions to obtain an effective point coordinate data set;
and selecting a defect judging area, setting a return parameter and a threshold value, and judging a defect result of the defect judging area.
2. The defect detection method according to claim 1, wherein the dividing the image along any one of the edge position directions to obtain sub-regions corresponding to a plurality of edge position directions comprises: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
3. The defect detection method of claim 1, wherein the setting of the return parameter and the threshold value comprises: in the defect judging area, the ratio of the number of sub-areas of the effective point coordinate data set to the number of sub-areas of the point coordinate data set is taken as a return parameter.
4. The defect detection method of claim 1, wherein the judging of the defect result of the defect determination area comprises: if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, judging that the defect judging area is defective, and synchronously acquiring the point coordinates of the defect.
5. The defect detection method of claim 1, further comprising: and obtaining a fitting result of the image to be measured based on the effective point coordinate data set.
6. The defect detection method of claim 5, further comprising: based on the defect result, the user selects to output or not to output the fitting result of the image to be measured.
7. A defect detection system, comprising:
the acquisition unit acquires an image of an object to be detected;
the data screening unit is used for dividing the image along any edge position direction to obtain subareas corresponding to a plurality of edge position directions; extracting point coordinates of edge positions in any sub-region to obtain point coordinate data sets of a plurality of sub-regions; screening the point coordinate data set based on fitting conditions to obtain an effective point coordinate data set;
a defect detection unit for selecting a defect determination area, setting a return parameter and a threshold value, and determining a defect result of the defect determination area; in the defect judging area, the ratio of the number of the subareas of the effective point coordinate data set to the number of the subareas of the point coordinate data set is used as a return parameter; if the return parameter of the defect judging area meets the threshold value, judging that the defect judging area is free of defects; otherwise, judging that the defect judging area is defective, and synchronously acquiring the point coordinates of the defect;
the fitting unit is used for obtaining a fitting result of the image to be measured based on the effective point coordinate data set; based on the defect result, the user selects to output or not to output the fitting result of the image to be measured.
8. The defect detection system of claim 7, wherein the dividing the image along any edge position direction to obtain sub-regions corresponding to a plurality of edge position directions comprises: based on the boundary of the measured object, roughly positioning an image edge curve corresponding to the boundary in the image, and taking the tangential direction of the image edge curve as the edge position direction; and arranging a plurality of blocks at equal intervals along the edge position direction to obtain sub-areas corresponding to the edge position directions.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the defect detection method of any of claims 1-6.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the defect detection method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311667644.1A CN117611566A (en) | 2023-12-07 | 2023-12-07 | Defect detection method, defect detection system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311667644.1A CN117611566A (en) | 2023-12-07 | 2023-12-07 | Defect detection method, defect detection system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117611566A true CN117611566A (en) | 2024-02-27 |
Family
ID=89957810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311667644.1A Pending CN117611566A (en) | 2023-12-07 | 2023-12-07 | Defect detection method, defect detection system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117611566A (en) |
-
2023
- 2023-12-07 CN CN202311667644.1A patent/CN117611566A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108682008B (en) | A kind of Leukocyte Image clarity evaluation method and device | |
| CN113781402A (en) | Method and device for detecting chip surface scratch defects and computer equipment | |
| KR101647010B1 (en) | Computer-implemented methods, computer-readable media, and systems for determining one or more characteristics of a wafer | |
| Karthikeyan et al. | Analysis of image segmentation for radiographic images | |
| CN110648350A (en) | Liver blood vessel segmentation method and device and electronic equipment | |
| CN111027343A (en) | Bar code area positioning method and device | |
| CN112308854A (en) | Automatic detection method and system for chip surface flaws and electronic equipment | |
| JP2005278690A (en) | Method for detecting nodular shadow from three-dimensional chest ct image using computer, apparatus therefor and computer program | |
| CN110544262A (en) | cervical cell image segmentation method based on machine vision | |
| JP2006292593A (en) | Flaw detector, flaw detecting method, computer program and recording medium | |
| KR101929669B1 (en) | The method and apparatus for analyzing an image using an entropy | |
| WO2022229638A1 (en) | Method & apparatus for processing microscope images of cells and tissue structures | |
| CN117611619A (en) | Linear fitting method, linear fitting system, electronic equipment and storage medium | |
| CN112147147A (en) | Edge defect detection method, edge defect detection device and quality detection equipment | |
| CN112396618B (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| CN114913112A (en) | Method, device and equipment for detecting double edges of wafer | |
| JP3330829B2 (en) | Automatic detection method of evaluable area in images of machine parts | |
| CN115861315B (en) | Defect detection method and device | |
| CN117611566A (en) | Defect detection method, defect detection system, electronic equipment and storage medium | |
| CN111681181A (en) | Method for evaluating fabric surface pilling degree | |
| CN116433978A (en) | Automatic generation and automatic labeling method and device for high-quality flaw image | |
| JP2000028539A (en) | Defect detecting device | |
| CN111681229B (en) | Deep learning model training method, wearable clothes flaw identification method and wearable clothes flaw identification device | |
| RU2734791C2 (en) | Recording histopathological images | |
| CN110634124A (en) | Method and equipment for area detection |
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 |