CN116188379A - Edge defect detection method, device, electronic equipment and storage medium - Google Patents
Edge defect detection method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116188379A CN116188379A CN202211685257.6A CN202211685257A CN116188379A CN 116188379 A CN116188379 A CN 116188379A CN 202211685257 A CN202211685257 A CN 202211685257A CN 116188379 A CN116188379 A CN 116188379A
- Authority
- CN
- China
- Prior art keywords
- defect detection
- detection area
- edge
- contour
- target
- 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
Images
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
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
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 application discloses an edge defect detection method, an edge defect detection device, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring an image of a workpiece to be detected; determining a target detection area at the edge outline of the workpiece image to be detected; determining a target segmentation threshold of the target detection area according to normal distribution of edge contour pixel values; dividing the target detection area based on the target division threshold value to obtain a first defect detection area; and determining a defect detection result of the first defect detection area based on the image characteristic data of the first defect detection area. According to the method, the first defect detection area suspected to have defects is determined through normal distribution of edge contour pixel values, the defects on the contour are primarily screened, the repeated judgment is carried out according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no over-detection and no omission.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly relates to an edge defect detection method, an edge defect detection device, electronic equipment and a storage medium.
Background
In industrial detection, a background with larger difference can be set through a light source so as to highlight the outline of a detected product, and aiming at defects on the outline, an outline extraction method is often adopted for edge defect detection.
However, when the outline is relatively irregular or similar to the normal outline, the outline extracting method is affected by the texture on the surface of the product, the accuracy of defect detection is greatly reduced, and when the outline and the background have smaller differences, the product is easy to overstock or miss, and the accuracy of good product detection is lower.
Therefore, how to accurately detect the weak defects of the contour edge on the premise of ensuring no over-detection and no over-detection is a problem to be solved in industrial detection.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides the edge defect detection method, the device, the electronic equipment and the storage medium, and the weak defects of the contour edge can be accurately detected on the premise of ensuring no over-detection and no omission.
In a first aspect, the present application provides an edge defect detection method, including:
Acquiring an image of a workpiece to be detected;
determining a target detection area at the edge outline of the workpiece image to be detected;
determining a target segmentation threshold of the target detection area according to normal distribution of edge contour pixel values;
dividing the target detection area based on the target division threshold value to obtain a first defect detection area;
and determining a defect detection result of the first defect detection area based on the image characteristic data of the first defect detection area.
According to the edge defect detection method, the first defect detection area suspected to have defects is determined through normal distribution of the edge contour pixel values, the defects on the contour are subjected to preliminary screening, the defect detection result of the first defect detection area is determined according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no overstock and omission.
According to one embodiment of the present application, the determining the target segmentation threshold of the target detection area according to the normal distribution of the edge contour pixel values includes:
second-order derivation is carried out on the edge profile of the target detection area, and the pixel standard deviation and the pixel mean value of the target detection area are obtained;
And determining the target segmentation threshold value based on the pixel standard deviation and the pixel mean value according to the normal distribution of the edge contour pixel values.
According to an embodiment of the present application, the dividing the target detection area based on the target division threshold value, to obtain a first defect detection area includes:
dividing a first contour region in the target detection region based on the target division threshold value, and reserving a second contour region in the target detection region, wherein the first contour region is used for representing a region where a normal contour pixel point is located, and the second contour region is used for representing a region where an abnormal contour pixel point is located;
the second contour region is determined as the first defect detection region.
According to an embodiment of the present application, the determining, based on the image feature data of the first defect detection area, a defect detection result of the first defect detection area includes:
acquiring first image feature data of the first defect detection area, and acquiring second image feature data of a first contour area in the target detection area, wherein the first contour area is used for representing an area where normal contour pixel points are located;
And determining a defect detection result of the first defect detection area based on the first image characteristic data and the second image characteristic data.
According to an embodiment of the present application, the first image feature data is a first gray level average value of the first defect detection area, the second image feature data is a second gray level average value of the first contour area, and determining the defect detection result of the first defect detection area based on the first image feature data and the second image feature data includes:
and under the condition that the second gray level average value is determined to be larger than the target gray level value range where the first gray level average value is, determining the first defect detection area as a defect area.
According to an embodiment of the present application, after the target detection area is segmented based on the target segmentation threshold to obtain a first defect detection area, before determining a defect detection result of the first defect detection area based on image feature data of the first defect detection area, the method further includes:
performing adaptive threshold segmentation based on the first defect detection area, and determining a first contour edge of the first defect detection area;
And cutting along the direction perpendicular to the first contour edge based on the first contour edge to obtain the cut first defect detection area.
In a second aspect, the present application provides an edge defect detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring an image of the workpiece to be detected;
the first processing module is used for determining a target detection area at the edge outline in the workpiece image to be detected;
the second processing module is used for determining a target segmentation threshold value of the target detection area according to normal distribution of edge contour pixel values;
the third processing module is used for dividing the target detection area based on the target division threshold value to obtain a first defect detection area;
and a fourth processing module, configured to determine a defect detection result of the first defect detection area based on the image feature data of the first defect detection area.
According to the edge defect detection device, the first defect detection area suspected to have defects is determined through normal distribution of the edge contour pixel values, the defects on the contour are subjected to preliminary screening, the defect detection result of the first defect detection area is determined according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no overstock and omission.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the edge defect detection method according to the first aspect when executing the computer program.
In a fourth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the edge defect detection method as described in the first aspect above.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the edge defect detection method as described in the first aspect above.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, wherein:
FIG. 1 is a schematic flow chart of an edge defect detection method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a contour edge defect detection process according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a target detection area provided in an embodiment of the present application;
fig. 4 is a schematic diagram of a suspected defect area determination flow provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of a suspicious region determination procedure according to an embodiment of the present application;
FIG. 6 is one of the schematic diagrams of the first defect detection area provided in the embodiment of the present application;
FIG. 7 is a second schematic diagram of a first defect detection area according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a defect detection result provided in an embodiment of the present application;
FIG. 9 is a schematic diagram of an edge defect detecting device according to an embodiment of the present disclosure;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 11 is a hardware schematic of an electronic device provided in an embodiment of the present application.
Detailed Description
Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The edge defect detection method, the edge defect detection device, the electronic device and the readable storage medium provided by the embodiment of the application are described in detail below with reference to the accompanying drawings through specific embodiments and application scenes thereof.
The edge defect detection method can be applied to the terminal, and can be specifically executed by hardware or software in the terminal.
The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet having a touch sensitive surface (e.g., a touch screen display and/or a touch pad). It should also be appreciated that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or a touch pad).
In the following various embodiments, a terminal including a display and a touch sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.
The implementation main body of the edge defect detection method provided in the embodiment of the present application may be an electronic device or a functional module or a functional entity capable of implementing the edge defect detection method in the electronic device, where the electronic device mentioned in the embodiment of the present application includes, but is not limited to, a mobile phone, a tablet computer, a camera, a wearable device, and the like, and the edge defect detection method provided in the embodiment of the present application is described below by taking the electronic device as an implementation main body as an example.
In industrial detection, a background with large variability can be set by a light source to highlight the outline of a detected product, wherein the background with large variability can highlight the external outline of the detected product by combining the light source, and the corresponding outline also exists inside the surface of the product. When the comparison between the contour and the difference is obvious, the method of extracting the contour is often adopted for edge defect detection aiming at the defects on the contour edge.
However, when the outline is relatively irregular or similar to the normal outline, the outline extracting method is affected by the texture on the surface of the product, the accuracy of defect detection is greatly reduced, when the outline and the background are small in difference, the product is easy to overstock or miss-check, whether the product is good or bad is difficult to judge, and the accuracy of good detection is low.
Therefore, how to accurately detect the weak defects of the contour edge on the premise of ensuring no over-detection and no over-detection is a problem to be solved in industrial detection.
The following describes in detail the edge defect detection method provided in the embodiment of the present application with reference to fig. 1 to 8.
As shown in fig. 1, the edge defect detection method includes: steps 110 to 150.
In this step, a workpiece image to be detected of the workpiece to be detected, which includes pixels of the contour edge of the workpiece for which defect detection is required, may be acquired by an industrial imaging system.
The workpiece to be detected can be a display screen to be detected, and the workpiece image to be detected is used for detecting weak defects of the outline edge of the display screen.
In practical implementation, the workpiece image to be detected acquired by the industrial imaging system may be a gray scale image or a color image.
It should be noted that, the image size of the workpiece image to be detected may be adjusted according to parameters such as the size of the workpiece to be detected and the detection requirement, for example, the image size of the workpiece image to be detected of the display screen to be detected may be 5120×5120.
After the image of the workpiece to be detected is acquired, an edge contour area of the workpiece to be detected can be acquired according to the modeling contour and the rough positioning information, and the edge contour area is taken as a target detection area.
In the embodiment, the target detection area at the edge contour of the workpiece to be detected is determined, and the relevant processing of defect detection is performed on the target detection area, so that the data processing amount of defect detection can be reduced, and the influence of the area outside the edge contour of the workpiece to be detected on edge defect detection is avoided.
For example, as shown in fig. 3, in the white frame, to determine a target detection area at an edge contour in an image of a workpiece to be detected, edge defect detection is performed for the target detection area in the white frame.
In practical implementation, the target detection area may be one or more, and the number of edge contours required for edge defect detection is determined according to the workpiece to be detected.
For example, the workpiece to be detected is a display screen, and the outline position of the display screen comprises four parts, namely an upper part, a lower part, a left part and a right part, and four target detection areas are correspondingly determined according to the image of the workpiece to be detected.
And 130, determining a target segmentation threshold value of the target detection region according to the normal distribution of the edge contour pixel values.
The pixel values of the edge contour pixel values of the workpiece to be detected are compared with the pixel values of the background area to obtain normal distribution, and the target segmentation threshold value of the target detection area is determined according to the distribution probability of abnormal pixel points in the normal distribution.
And 140, dividing the target detection area based on the target division threshold value to obtain a first defect detection area.
The first defect detection area is an area suspected to be defective in the target detection area.
In this step, the target detection region is segmented according to a target segmentation threshold determined by a normal distribution of edge contour pixel values, to obtain a first defect detection region.
In this embodiment, the possible positions of the suspected defects are determined through normal distribution, the defects on the contour are subjected to preliminary screening, and the first defect detection area suspected to be defective in the target detection area is determined.
In addition, if the contour is relatively irregular or similar to the normal contour, the weak defect of the contour edge is determined as an abnormal value pixel point in the normal distribution analysis, that is, the target detection area is divided based on the target division threshold value, and the obtained first defect detection area includes the weak defect.
In this step, feature sampling may be performed on the first defect detection area, image feature data of the first defect detection area may be obtained, and defect detection may be performed on the image feature data of the first defect detection area, to obtain a defect detection result of the first defect detection area.
In the embodiment, a target segmentation threshold is determined according to normal distribution of edge contour pixel values, a target detection area is segmented, and a first defect detection area suspected to have defects in the target detection area is primarily screened; and then, carrying out a re-judgment through the image characteristic data of the first defect detection area, and judging whether the area suspected to have the defect currently has a real defect or not.
It should be noted that, based on normal distribution analysis, determining possible positions of suspected defects, completing preliminary screening of defects on the outline, wherein a first defect detection area obtained by preliminary screening comprises obvious defects and weak defects; because of the influence of polishing, different boundary contour features of the workpiece to be detected also have differences, the contours are sampled, feature information on the contours corresponding to suspected defects is obtained for image processing, and the first defect detection area is accurately judged, so that good product distinguishing is facilitated.
Fig. 2 is a schematic diagram of a contour edge defect detection flow provided in an embodiment of the present application, where, as shown in fig. 2, an image of a workpiece to be detected is first collected, and a target detection area in the image of the workpiece to be detected is obtained.
And determining a target segmentation threshold according to the normal distribution of the edge contour pixel values, segmenting a target detection region, and determining a suspected defect region, namely a first defect detection region.
And carrying out repeated judgment on the suspicious region of the first defect detection region by using the image characteristic data to judge whether the current suspicious region has a real defect or not, so as to obtain a defect detection result of the first defect detection region.
According to the edge defect detection method provided by the embodiment of the application, the first defect detection area suspected to have defects is determined through normal distribution of the edge contour pixel values, the defects on the contour are subjected to preliminary screening, the defect detection result of the first defect detection area is determined according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no overstock and omission.
In some embodiments, step 130, determining the target segmentation threshold of the target detection region according to the normal distribution of edge contour pixel values may include:
Second-order derivation is carried out on the edge profile of the target detection area, and the pixel standard deviation and the pixel mean value of the target detection area are obtained;
and determining a target segmentation threshold value based on the pixel standard deviation and the pixel mean value according to the normal distribution of the edge contour pixel values.
In this embodiment, the edge contour of the target detection area is subjected to second order derivative in a direction perpendicular to the edge contour, the gradient of the edge contour of the target detection area is solved, and then the pixel standard deviation and the pixel mean of the target detection area are calculated.
The pixel values of the edge contour obey normal distribution, the distribution probability corresponding to normal pixel points and abnormal pixel points is obtained through normal distribution analysis, and the target segmentation threshold of the target detection area is determined by analyzing the relationship between the pixel standard deviation and the pixel mean value and the segmentation threshold through linear regression according to the pixel standard deviation and the pixel mean value of the target detection area and combining the distribution probability of the abnormal pixel points in the normal distribution.
When the first defect detection area is determined on the target detection area, second order derivation is performed on the edge profile of the target detection area, the target segmentation threshold is determined based on the distribution probability of outlier pixels in the front-to-back distribution model by using the pixel difference between the edge and other areas except the edge, the target detection area is segmented and marked, and the position of the suspected defect area is determined, so that the method is not only suitable for the primary screening of defects on the bright edge profile, but also suitable for the primary screening of defects on the dark edge profile.
Taking a workpiece to be detected comprising four edges, namely an upper edge, a lower edge, a left edge and a right edge as an example.
Dividing the acquired workpiece image to be detected into an upper part, a lower part, a left part and a right part according to the outline position to obtain four target detection areas, performing second order derivation on the outline, calculating the relation between the pixel standard deviation and the pixel mean value corresponding to each target detection area, analyzing the relation between the pixel standard deviation and the pixel mean value and the segmentation threshold value based on linear regression, and after determining the target segmentation threshold value, segmenting the outline to obtain suspected defect areas corresponding to each area, and obtaining four first defect detection areas.
It should be noted that, only the target detection area close to the outline width is taken, defect characteristics are compared and screened out, interference of background parts can be reduced, each edge is independently sampled and analyzed, influence of uneven illumination on defect detection can be reduced, and detection accuracy is improved.
In some embodiments, step 140 of dividing the target detection area based on the target division threshold to obtain the first defect detection area may include:
dividing a first contour area in a target detection area based on a target dividing threshold value, and reserving a second contour area in the target detection area, wherein the first contour area is used for representing an area where a normal contour pixel point is located, and the second contour area is used for representing an area where an abnormal contour pixel point is located;
The second contour region is determined as the first defect detection region.
It can be understood that the pixel points of the abnormal contour and the normal contour have differences, and the target segmentation threshold value is determined based on normal distribution, so that the position of the pixel point of the abnormal contour can be determined, the normal contour can be segmented when image segmentation is performed, and the abnormal part on the contour can not be segmented.
A specific embodiment of determining the first defect detection area is described below.
Fig. 4 is a schematic diagram of a suspected defect area determining process provided in an embodiment of the present application, and as shown in fig. 4, the suspected defect area determining process is as follows:
(1) Acquiring a target detection area: and acquiring position information of the edge profile of the workpiece to be detected, dividing the position information into four target detection areas, namely an upper edge, a lower edge, a left edge and a right edge, and cutting out the image of the workpiece to be detected to obtain a corresponding area image.
(2) Gradient calculation: and carrying out Gaussian second derivatives on the images of the four target detection areas of the upper edge, the lower edge, the left edge and the right edge, obtaining the second derivatives of the left edge and the right edge in the X direction, and obtaining the second derivatives of the left edge and the right edge in the Y direction.
Wherein, the X direction is the image perpendicular to the left and right edges, and the Y direction is the image perpendicular to the upper and lower edges.
(3) Determining a target segmentation threshold based on the normal distribution: the position of an abnormal pixel point on the outline is required to be determined, the derived image is required to be calculated, the standard deviation and the mean value of the pixels are calculated, the pixel value of the boundary outline is compared with the background area to be subjected to normal distribution, then the relation between the standard deviation and the mean value and the segmentation threshold value is calculated based on the linear regression model, and after the target segmentation threshold value is determined, the corresponding image is segmented.
(4) Screening suspected defect areas: the outline of the suspected defect area is different from the normal outline, the normal outline is brighter, the abnormal pixel values are removed based on the normal distribution, the normal outline can be segmented, and the abnormal part on the outline can not be segmented.
In this embodiment, the suspected defect area, i.e., the first defect detection area, is also obtained by comparing the image with the original image area and using the area features to exclude some minor interference.
In some embodiments, step 150, determining the defect detection result of the first defect detection area based on the image feature data of the first defect detection area may include:
acquiring first image feature data of a first defect detection area, and acquiring second image feature data of a first contour area in a target detection area, wherein the first contour area is used for representing an area where normal contour pixel points are located;
A defect detection result of the first defect detection area is determined based on the first image feature data and the second image feature data.
In this embodiment, the second image feature data of the first contour region of the normal contour is compared with the first image feature data of the first defect detection region suspected of having a defect, and the first defect detection region suspected of having a defect that is screened out first is re-judged to determine whether the first defect detection region has a real defect.
In some embodiments, the first image feature data is a first gray scale average of the third contour region, the second image feature data is a second gray scale average of the first contour region, and determining the defect detection result of the first defect detection region based on the first image feature data and the second image feature data may include:
and under the condition that the second gray level average value is determined to be larger than the target gray level value range where the first gray level average value is, determining the first defect detection area as a defect area.
In this embodiment, the gray average value (first gray average value) of the first defect detection area suspected to have a defect and the gray average value (second gray average value) of the first contour area of the normal contour are sampled and calculated, and the first gray average value and the second gray average value are compared to compare the difference of gray features between the two areas.
In actual execution, the first gray average value and the second gray average value are both numerical values, and the first gray average value and the second gray average value are directly compared in size, so that the over-detection condition can be possibly caused, and the gray characteristic reference is expanded into the target gray value range based on the first gray average value, so that the accuracy of defect judgment is ensured, and the over-detection condition can be effectively prevented.
In this embodiment, when it is determined that the second gray average value is greater than the target gray value range in which the first gray average value is located, it indicates that there is a real defect in the first defect detection area, and the first defect detection area is a defect area.
In some embodiments, after dividing the target detection area based on the target division threshold in step 140 to obtain the first defect detection area, before determining the defect detection result of the first defect detection area based on the image feature data of the first defect detection area in step 150, the edge defect detection method further includes:
performing adaptive threshold segmentation based on the first defect detection area, and determining a first contour edge of the first defect detection area;
Based on the first contour edge, cutting is carried out along the direction perpendicular to the first contour edge, and a cut first defect detection area is obtained.
After a first defect detection area suspected to have defects is determined, positioning a contour boundary in the first defect detection area through self-adaptive threshold segmentation, and determining a first contour edge of the first defect detection area; and cutting the first contour edge along the direction perpendicular to the first contour edge to obtain a cut first defect detection area.
In this example, the cutting is performed along the direction perpendicular to the first contour edge, so that the feature part of the first contour edge can be retained to the maximum extent, and the defect re-judgment is performed for the cut first defect detection area, so that the influence of the features other than the contour edge features on the edge defect detection can be effectively avoided, and the accuracy of defect detection can be improved.
For example, the first defect detection area shown in fig. 6 is subjected to adaptive threshold segmentation, the edge contour is positioned and then cut, so that the cut first defect detection area shown in fig. 7 can be obtained, the influence of features other than the contour edge features on edge defect detection can be effectively avoided, and the accuracy of defect detection is improved.
In practical implementation, the clipping may be performed along a direction perpendicular to the first contour edge, which may be expanding and contracting the first defect detection area along a direction perpendicular to the first contour edge, and the expanded and contracted pixel range may be adjusted according to the sizes of the first defect detection area and the first contour edge.
For example, in the first defect detection area, the first contour edge is positioned through self-adaptive threshold segmentation, the first contour edge is a left edge and a right edge, the left edge area and the right edge area are expanded and contracted left and right, the area is translated to the left and right by 10 pixels, and the translated area is differentiated, so that the total expansion and contraction width is 20 pixels, and the characteristic part of the first contour edge is effectively ensured to be reserved.
Take the first defect detection area of four edges, up, down, left and right as an example.
Fig. 5 is a schematic diagram of a suspicious region determination flow provided in the embodiment of the present application, and as shown in fig. 5, the suspicious region first defect detection regions of the four edges of the upper, lower, left and right are determined.
After the suspected defect area is obtained, positioning the edge of the outline, carrying out left and right area expansion and contraction aiming at the left and right edges, carrying out upper and lower area expansion and contraction aiming at the upper and lower edges, and then cutting to obtain an image of the outline area, namely a first defect detection area after cutting of the upper, lower, left and right edges. And (3) sampling on the cut edge image corresponding to each edge, calculating the gray average value of the suspicious region of the first defect detection region, comparing the gray differences of the suspicious defect and the normal outline region, and screening out the real defect.
One specific embodiment is described below.
(1) And judging a suspected area.
And dividing a first defect detection area suspected to have defects in the target detection area according to the normal distribution of the edge contour pixel values.
It should be noted that, when the number of the first defect detection areas existing in the target detection area is determined to be 0, the workpiece to be detected is directly determined to be a good product.
(2) And acquiring a contour area image.
And (3) positioning the outline boundary in the first defect detection area through self-adaptive threshold segmentation, then carrying out left and right expansion and contraction on the left and right edge areas, translating the area left and right by 10 pixels, and carrying out difference on the translated area to ensure that the total expansion and contraction is 20 pixels, so that the area near the outline is ensured to be acquired, and the upper edge and the lower edge adopt the same operation. And finally obtaining a contour area image with a 20-pixel width taking the contour as the center, namely a first defect detection area after clipping.
(3) And sampling and calculating the gray average value of the suspicious region.
It should be noted that, the first defect detection area is not all abnormal outlines, in this embodiment, the normal outline areas on the four outlines may be sampled respectively, for a certain outline, the normal outline area with the largest area on the outline is selected, the average gray value of the area is calculated as the second gray average value, and the average gray value of the suspicious area in the first defect detection area is calculated as the first gray average value.
(4) And determining defects.
Comparing the second gray level average value obtained by sampling with the first gray level average value, comparing the difference of gray level characteristics, eliminating the normal outline area in the first defect detection area, and determining that the normal outline area is a real defect, wherein the difference is larger than the reference, for example, the part outlined by the white square box as shown in fig. 8 is the real defect.
According to the edge defect detection method provided by the embodiment of the application, the execution body can be an edge defect detection device. In the embodiment of the present application, an edge defect detection device is described by taking an example in which the edge defect detection device performs an edge defect detection method.
The embodiment of the application also provides an edge defect detection device.
As shown in fig. 9, the edge defect detecting apparatus includes:
an acquisition module 910, configured to acquire an image of a workpiece to be detected;
a first processing module 920, configured to determine a target detection area at an edge contour in an image of a workpiece to be detected;
a second processing module 930, configured to determine a target segmentation threshold of the target detection region according to the normal distribution of the edge contour pixel values;
a third processing module 940, configured to segment the target detection area based on the target segmentation threshold to obtain a first defect detection area;
A fourth processing module 950, configured to determine a defect detection result of the first defect detection area based on the image feature data of the first defect detection area.
According to the edge defect detection device provided by the embodiment of the application, the first defect detection area suspected to have defects is determined through normal distribution of the edge contour pixel values, the defects on the contour are subjected to preliminary screening, the defect detection result of the first defect detection area is determined according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no overstock and omission.
In some embodiments, the second processing module 930 is configured to perform second order derivative on the edge profile of the target detection area, and obtain a pixel standard deviation and a pixel mean of the target detection area;
and determining a target segmentation threshold value based on the pixel standard deviation and the pixel mean value according to the normal distribution of the edge contour pixel values.
In some embodiments, the third processing module 940 is configured to segment a first contour region in the target detection region based on the target segmentation threshold, and reserve a second contour region in the target detection region, where the first contour region is used for representing a region where the normal contour pixel point is located, and the second contour region is used for representing a region where the abnormal contour pixel point is located;
The second contour region is determined as the first defect detection region.
In some embodiments, the fourth processing module 950 is configured to obtain first image feature data of a first defect detection area, and obtain second image feature data of a first contour area in the target detection area, where the first contour area is used for representing an area where the normal contour pixel points are located;
a defect detection result of the first defect detection area is determined based on the first image feature data and the second image feature data.
In some embodiments, the first image feature data is a first gray scale average of the first defect detection area, the second image feature data is a second gray scale average of the first contour area, and the fourth processing module 950 is configured to determine the first defect detection area as the defect area if it is determined that the second gray scale average is greater than a target gray scale range in which the first gray scale average is located based on the first image feature data and the second image feature data.
In some embodiments, the fourth processing module 950 is further configured to determine a first contour edge of the first defect detection area based on adaptive thresholding of the first defect detection area;
based on the first contour edge, cutting is carried out along the direction perpendicular to the first contour edge, and a cut first defect detection area is obtained.
The edge defect detection device in the embodiment of the application may be an electronic device, or may be a component in the electronic device, for example, an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-mobile personal computer, UMPC, netbook or personal digital assistant (personal digital assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The edge defect detection device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.
The edge defect detection device provided in the embodiment of the present application can implement each process implemented by the embodiments of the methods of fig. 1 to 8, and in order to avoid repetition, a detailed description is omitted here.
In some embodiments, as shown in fig. 10, the embodiment of the present application further provides an electronic device 1000, including a processor 1001, a memory 1002, and a computer program stored in the memory 1002 and capable of running on the processor 1001, where the program when executed by the processor 1001 implements the processes of the above-mentioned edge defect detection method embodiment, and the same technical effects can be achieved, and for avoiding repetition, a description is omitted herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.
Fig. 11 is a schematic hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 1100 includes, but is not limited to: radio frequency unit 1101, network module 1102, audio output unit 1103, input unit 1104, sensor 1105, display unit 1106, user input unit 1107, interface unit 1108, memory 1109, and processor 1110.
Those skilled in the art will appreciate that the electronic device 1100 may further include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 1110 by a power management system, such as to perform functions such as managing charging, discharging, and power consumption by the power management system. The electronic device structure shown in fig. 11 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than illustrated, or may combine some components, or may be arranged in different components, which are not described in detail herein.
The input unit 1104, in this embodiment, a camera, is configured to obtain an image of a workpiece to be detected;
a processor 1110 for determining a target detection area at an edge profile in an image of a workpiece to be detected;
determining a target segmentation threshold of a target detection area according to normal distribution of edge contour pixel values;
dividing the target detection area based on a target division threshold value to obtain a first defect detection area;
and determining a defect detection result of the first defect detection area based on the image characteristic data of the first defect detection area.
According to the electronic equipment provided by the embodiment of the application, the first defect detection area suspected to have defects is determined through normal distribution of the edge contour pixel values, the defects on the contour are subjected to preliminary screening, the defect detection result of the first defect detection area is determined according to the image characteristic data of the first defect detection area, and the weak defects on the contour edge can be accurately detected on the premise of ensuring no overstock and omission.
In some embodiments, the processor 1110 is further configured to perform second order derivative on the edge profile of the target detection area, and obtain a pixel standard deviation and a pixel mean of the target detection area;
And determining a target segmentation threshold value based on the pixel standard deviation and the pixel mean value according to the normal distribution of the edge contour pixel values.
In some embodiments, the processor 1110 is further configured to segment a first contour region in the target detection region based on the target segmentation threshold, and reserve a second contour region in the target detection region, where the first contour region is used for representing a region where the normal contour pixel point is located, and the second contour region is used for representing a region where the abnormal contour pixel point is located;
the second contour region is determined as the first defect detection region.
In some embodiments, the processor 1110 is further configured to obtain first image feature data of a first defect detection area, and obtain second image feature data of a first contour area in the target detection area, where the first contour area is used for representing an area where the normal contour pixel point is located;
a defect detection result of the first defect detection area is determined based on the first image feature data and the second image feature data.
In some embodiments, the first image feature data is a first gray scale average of the first defect detection area, the second image feature data is a second gray scale average of the first contour area, and the processor 1110 is further configured to determine that the first defect detection area is a defect area if it is determined that the second gray scale average is greater than a target gray scale value range in which the first gray scale average is located.
In some embodiments, the processor 1110 is further configured to, after dividing the target detection area based on the target division threshold value to obtain the first defect detection area, determine, based on image feature data of the first defect detection area, a defect detection result of the first defect detection area before:
performing adaptive threshold segmentation based on the first defect detection area, and determining a first contour edge of the first defect detection area;
based on the first contour edge, cutting is carried out along the direction perpendicular to the first contour edge, and a cut first defect detection area is obtained.
It should be appreciated that in embodiments of the present application, the input unit 1104 may include a graphics processor (Graphics Processing Unit, GPU) 11041 and a microphone 11042, the graphics processor 11041 processing image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also referred to as a touch screen. The touch panel 11071 may include two parts, a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.
The memory 1109 may be used to store software programs as well as various data. The memory 1109 may mainly include a first memory area storing programs or instructions and a second memory area storing data, wherein the first memory area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory 1109 may include volatile memory or nonvolatile memory, or the memory 1109 may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (ddr SDRAM), enhanced SDRAM (Enhanced SDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). Memory 1109 in embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.
The embodiment of the present application further provides a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program when executed by a processor implements each process of the above-mentioned edge defect detection method embodiment, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application also provides a computer program product, which comprises a computer program, and the computer program realizes the edge defect detection method when being executed by a processor.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, and the processor is configured to run a program or an instruction, implement each process of the above embodiment of the edge defect detection method, and achieve the same technical effect, so that repetition is avoided, and no further description is provided here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. An edge defect detection method, comprising:
acquiring an image of a workpiece to be detected;
determining a target detection area at the edge outline of the workpiece image to be detected;
determining a target segmentation threshold of the target detection area according to normal distribution of edge contour pixel values;
Dividing the target detection area based on the target division threshold value to obtain a first defect detection area;
and determining a defect detection result of the first defect detection area based on the image characteristic data of the first defect detection area.
2. The edge defect detection method of claim 1, wherein determining the target segmentation threshold for the target detection region based on the normal distribution of edge contour pixel values comprises:
second-order derivation is carried out on the edge profile of the target detection area, and the pixel standard deviation and the pixel mean value of the target detection area are obtained;
and determining the target segmentation threshold value based on the pixel standard deviation and the pixel mean value according to the normal distribution of the edge contour pixel values.
3. The edge defect detection method of claim 1, wherein the segmenting the target detection area based on the target segmentation threshold to obtain a first defect detection area comprises:
dividing a first contour region in the target detection region based on the target division threshold value, and reserving a second contour region in the target detection region, wherein the first contour region is used for representing a region where a normal contour pixel point is located, and the second contour region is used for representing a region where an abnormal contour pixel point is located;
The second contour region is determined as the first defect detection region.
4. The edge defect detection method of any of claims 1-3, wherein the determining a defect detection result for the first defect detection area based on image feature data for the first defect detection area comprises:
acquiring first image feature data of the first defect detection area, and acquiring second image feature data of a first contour area in the target detection area, wherein the first contour area is used for representing an area where normal contour pixel points are located;
and determining a defect detection result of the first defect detection area based on the first image characteristic data and the second image characteristic data.
5. The edge defect detection method of claim 4, wherein the first image feature data is a first gray scale average of the first defect detection area, the second image feature data is a second gray scale average of the first contour area, and the determining the defect detection result of the first defect detection area based on the first image feature data and the second image feature data comprises:
And under the condition that the second gray level average value is determined to be larger than the target gray level value range where the first gray level average value is, determining the first defect detection area as a defect area.
6. An edge defect detection method according to any one of claims 1-3, wherein after said dividing said target detection area based on said target division threshold to obtain a first defect detection area, said method further comprises, prior to determining a defect detection result of said first defect detection area based on image feature data of said first defect detection area:
performing adaptive threshold segmentation based on the first defect detection area, and determining a first contour edge of the first defect detection area;
and cutting along the direction perpendicular to the first contour edge based on the first contour edge to obtain the cut first defect detection area.
7. An edge defect detecting apparatus, comprising:
the acquisition module is used for acquiring an image of the workpiece to be detected;
the first processing module is used for determining a target detection area at the edge outline in the workpiece image to be detected;
the second processing module is used for determining a target segmentation threshold value of the target detection area according to normal distribution of edge contour pixel values;
The third processing module is used for dividing the target detection area based on the target division threshold value to obtain a first defect detection area;
and a fourth processing module, configured to determine a defect detection result of the first defect detection area based on the image feature data of the first defect detection area.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the edge defect detection method according to any of claims 1-6 when the program is executed by the processor.
9. A non-transitory computer readable storage medium, having stored thereon a computer program, which when executed by a processor implements the edge defect detection method according to any of claims 1-6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the edge defect detection method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685257.6A CN116188379A (en) | 2022-12-27 | 2022-12-27 | Edge defect detection method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685257.6A CN116188379A (en) | 2022-12-27 | 2022-12-27 | Edge defect detection method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116188379A true CN116188379A (en) | 2023-05-30 |
Family
ID=86437538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211685257.6A Pending CN116188379A (en) | 2022-12-27 | 2022-12-27 | Edge defect detection method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116188379A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036350A (en) * | 2023-10-08 | 2023-11-10 | 保定来福汽车照明集团沧州有限公司 | Defect detection method, device, terminal and storage medium for metal lamp holder welding mud |
| CN117095009A (en) * | 2023-10-20 | 2023-11-21 | 山东绿康装饰材料有限公司 | PVC decorative plate defect detection method based on image processing |
-
2022
- 2022-12-27 CN CN202211685257.6A patent/CN116188379A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036350A (en) * | 2023-10-08 | 2023-11-10 | 保定来福汽车照明集团沧州有限公司 | Defect detection method, device, terminal and storage medium for metal lamp holder welding mud |
| CN117036350B (en) * | 2023-10-08 | 2023-12-15 | 保定来福汽车照明集团沧州有限公司 | Defect detection method, device, terminal and storage medium for metal lamp holder welding mud |
| CN117095009A (en) * | 2023-10-20 | 2023-11-21 | 山东绿康装饰材料有限公司 | PVC decorative plate defect detection method based on image processing |
| CN117095009B (en) * | 2023-10-20 | 2024-01-12 | 山东绿康装饰材料有限公司 | PVC decorative plate defect detection method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109142366B (en) | Spherical shell defect detection method and device and computer readable storage medium | |
| CN110766679B (en) | Lens contamination detection method and device and terminal equipment | |
| CN116188379A (en) | Edge defect detection method, device, electronic equipment and storage medium | |
| CN109242853B (en) | PCB defect intelligent detection method based on image processing | |
| CN108830780B (en) | Image processing method and device, electronic device and storage medium | |
| US20220383463A1 (en) | Method and device for image fusion, computing processing device, and storage medium | |
| CN113379723B (en) | Irregular glue overflow port detection method, device, equipment and storage medium | |
| KR20130072073A (en) | Apparatus and method for extracting edge in image | |
| CN113781406B (en) | Scratch detection method and device for electronic component and computer equipment | |
| CN112308797A (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN109961016B (en) | Multi-gesture accurate segmentation method for smart home scene | |
| CN116109572A (en) | Workpiece edge weak defect detection method and device and electronic equipment | |
| CN111912846A (en) | Machine vision-based surface defect and edge burr detection method | |
| CN117115130A (en) | Wafer edge defect detection method and device | |
| CN114298985B (en) | Defect detection method, device, equipment and storage medium | |
| CN113284113B (en) | Glue overflow flaw detection method, device, computer equipment and readable storage medium | |
| CN112532884B (en) | Identification method and device and electronic equipment | |
| CN113034530A (en) | Mobile phone placement detection method and device | |
| CN114913112A (en) | Method, device and equipment for detecting double edges of wafer | |
| CN114418848B (en) | Video processing method and device, storage medium and electronic equipment | |
| CN114359176B (en) | Panel detection method and device, electronic equipment and storage medium | |
| CN114723728A (en) | Method and system for detecting CD line defects of silk screen of glass cover plate of mobile phone camera | |
| CN113034529A (en) | Equipment image extraction method and device based on mini-mobile phone detector | |
| CN112529766A (en) | Image processing method and device and electronic equipment | |
| CN112183277A (en) | Detection method and device for abandoned object and lost object, terminal equipment and storage medium |
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 |