CN115436394A - Appearance defect detection system and method - Google Patents
Appearance defect detection system and method Download PDFInfo
- Publication number
- CN115436394A CN115436394A CN202211039631.5A CN202211039631A CN115436394A CN 115436394 A CN115436394 A CN 115436394A CN 202211039631 A CN202211039631 A CN 202211039631A CN 115436394 A CN115436394 A CN 115436394A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- appearance
- defects
- mirror surface
- 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 254
- 238000001514 detection method Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000001502 supplementing effect Effects 0.000 claims abstract description 8
- 238000004891 communication Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims abstract 7
- 241000283070 Equus zebra Species 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 12
- 208000034656 Contusions Diseases 0.000 claims description 11
- 208000034526 bruise Diseases 0.000 claims description 11
- 238000000227 grinding Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 5
- 231100000241 scar Toxicity 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 11
- 239000000463 material Substances 0.000 description 8
- 239000013589 supplement Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application provides an appearance defect detection system and method, and the system comprises: the first detection device comprises a first camera and a first light source which are fixed on the multidimensional adjusting platform, and the first light source is used for supplementing light to the mirror surface workpiece so that the first camera acquires a first image of the mirror surface workpiece; the second detection device comprises a second camera and a second light source which are fixed on the multidimensional adjusting platform, and the second light source is used for supplementing light to the mirror surface workpiece so that the second camera collects a second image of the mirror surface workpiece; the computing equipment comprises a first detection module and a second detection module, the computing equipment is in communication connection with the first camera and the second camera, the first detection module is used for detecting whether the mirror surface workpiece has the appearance defects of the first type or not according to the first image, and the second detection module is used for detecting whether the mirror surface workpiece has the appearance defects of the second type or not according to the second image. This application can carry out full automated inspection to the appearance defect of mirror surface work piece, and it is high to detect the accuracy, and the practicality is strong, and application scope is wide.
Description
Technical Field
The application relates to the technical field of machine vision detection, in particular to an appearance defect detection system and method.
Background
In the machining process, certain defects exist in the appearance of part of workpieces, wherein the appearance defects mainly comprise scratch defects, material grain defects, bruise defects, invisible defects, grinding mark defects, pinhole defects, zebra defect and the like. On an industrial production line, if workpieces with appearance quality defects flow into the next production process, assembly is blocked and deformed, the quality of an assembly part is affected, the assembly part can be scrapped and stopped seriously, the production efficiency of an automatic production line is greatly affected, and potential economic loss and credit risk are brought to production enterprises. In order to meet the requirements of production speed and product quality, the appearance performance indexes are required to be detected in cooperation with all the processes on the production line.
The existing appearance defect detection method is mainly manual detection. The manual detection of the appearance defects is performed by methods such as hand touch, visual inspection, light reflection, light projection and the like. The whole detection efficiency is lower, and the working strength of each worker is higher. The detection worker is easily influenced by other external factors, such as visual fatigue and the like, the phenomenon of missed detection and false detection easily occurs, the detection accuracy is not high, the final product quality is influenced, and especially in the large-batch industrial production process, the detection speed and the detection accuracy are difficult to meet the requirements.
Disclosure of Invention
In view of this, the present application provides an appearance defect detection system and method, which can perform full-automatic detection on an appearance defect of a mirror surface workpiece, and have high detection accuracy, strong practicability, and a wide application range.
In a first aspect, an embodiment of the present application provides an appearance defect detecting system, which includes an object stage and a multi-dimensional adjusting platform, wherein the multi-dimensional adjusting platform is erected above the object stage, the object stage is configured to load a mirror surface workpiece to be detected, and the appearance defect detecting system further includes: the first detection device comprises a first camera and a first light source which are fixed on the multidimensional adjusting platform, the first camera and the first light source are distributed from top to bottom, and the first light source is used for supplementing light to the mirror surface workpiece so that the first camera acquires a first image of the mirror surface workpiece; the second detection device comprises a second camera and a second light source which are fixed on the multi-dimensional adjusting platform, the second camera and the second light source are distributed from top to bottom, and the second light source is used for supplementing light to the mirror surface workpiece so that the second camera acquires a second image of the mirror surface workpiece; the computing device is in communication connection with the first camera and the second camera, the first detection module is used for detecting whether the mirror surface workpiece has a first type of appearance defects according to the first image, and the second detection module is used for detecting whether the mirror surface workpiece has a second type of appearance defects according to the second image.
In an embodiment, the first type of appearance defect includes at least one of scratch defect, grain defect, bruise defect, and non-visible defect, and the second type of appearance defect includes at least one of wear scar defect, pinhole defect, and zebra defect.
In an embodiment, the first camera includes an FA lens, the second camera includes a telecentric lens, the FA lens and the telecentric lens are spaced apart, the FA lens is disposed along a first straight line, the telecentric lens is disposed along a second straight line, and the first straight line is parallel to the second straight line.
In one embodiment, the first light source comprises an annular light source, the annular light source is disposed along a first straight line, and the second light source comprises a coaxial light source, the coaxial light source is disposed along a second straight line.
In an embodiment, the computing device further includes an image preprocessing module, and the image preprocessing module is configured to perform position correction and image segmentation on the first image and the second image.
In an embodiment, the multi-dimensional adjustment platform includes an X-axis servo module, a Y-axis servo module, a Z-axis servo module, the X-axis servo module is erected on the top of the stage, the Y-axis servo module is arranged at the bottom of the X-axis servo module, the Z-axis servo module is hung on the X-axis servo module, the appearance defect detection system further includes a baffle plate, the baffle plate is installed on the Z-axis servo module, and the first detection device and the second detection device are arranged on the baffle plate.
The embodiment further provides an appearance defect detection method, which includes:
acquiring a first image of the mirror surface workpiece acquired by a first camera under the supplementary lighting of a first light source, and acquiring a second image of the mirror surface workpiece acquired by a second camera under the supplementary lighting of a second light source;
preprocessing the first image and the second image to obtain a preprocessed first image and a preprocessed second image;
performing appearance defect detection on the preprocessed first image through a first preset algorithm to obtain a first appearance detection result;
performing appearance defect detection on the preprocessed second image through a second preset algorithm to obtain a second appearance detection result;
and obtaining an appearance detection result of the mirror surface workpiece based on the first appearance detection result and the second appearance detection result.
In an embodiment, the performing, by using a first preset algorithm, appearance defect detection on the preprocessed first image to obtain a first appearance detection result includes: and searching for defects of the preprocessed first image through the first preset algorithm to determine whether the mirror surface workpiece has a first type of appearance defects, wherein the first type of appearance defects comprise at least one of scratch defects, texture defects, bruise defects and invisible light defects.
In an embodiment, the performing, by using a second preset algorithm, appearance defect detection on the preprocessed second image to obtain a second appearance detection result includes: and searching for defects of the preprocessed second image through the second preset algorithm to determine whether the mirror surface workpiece has second type of appearance defects, wherein the second type of appearance defects comprise at least one of grinding mark defects, pinhole defects and zebra stripe defects.
In one embodiment, after determining that the mirror workpiece has a defect, the method further comprises: and judging whether the defect degree of the defects of the mirror surface workpiece is within the corresponding preset defect degree requirement range or not by using a preset condition detection algorithm, and if the defect degree of the defects is within the preset defect degree requirement range, ignoring the defects of the mirror surface workpiece.
According to the appearance defect detection system and method provided by the embodiment of the application, a first camera in a first detection mechanism collects a first image of a mirror surface element under the light supplement of a first light source, a second camera in a second detection mechanism collects a second image of the mirror surface element under the light supplement of a second light source, a computing device is in communication connection with the first camera and the second camera, whether the mirror surface workpiece has the appearance defect of a first type or not is detected by arranging a first detection module according to the first image, whether the mirror surface workpiece has the appearance defect of a second type or not is detected by arranging a second detection module according to the second image, and a targeted detection method is adopted for different defects, so that the full-automatic detection of the appearance defect of the mirror surface workpiece is realized, the accuracy of the appearance detection is improved, the labor cost is saved, and the production efficiency is improved.
Drawings
Fig. 1 is a schematic structural diagram of an appearance defect detecting system according to an embodiment of the present application.
Fig. 2 is a block diagram of a computing device of an appearance defect detecting system according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a part of the appearance defect detecting system shown in fig. 1.
Fig. 4 is a schematic structural diagram of an appearance defect detecting system according to an embodiment of the present application.
Fig. 5 is a flowchart illustrating steps of a method for detecting an appearance defect according to an embodiment of the present application.
FIG. 6 is a flowchart illustrating steps of a sub-step of the visual defect detection method shown in FIG. 5.
FIG. 7 is a flowchart illustrating steps of one sub-step of the visual defect detection method shown in FIG. 5.
Description of the main elements
Appearance defect detection system 100
Suction bottom die 111
Y-axis servo module 122
Z-axis servo module 123
Baffle 124
First detecting device 130
FA lens 133
Second detecting device 140
Preprocessing module 153
First straight line L1
Second straight line L2
Fusion module 14
Calculation module 15
Electronic device 20
Processor 21
Memory 22
The following detailed description will further illustrate the present application in conjunction with the above-described figures.
The specific implementation mode is as follows:
the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application.
In the embodiments of the present application, "at least one" means one or more, and a plurality means two or more. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It should be noted that in the embodiments of the present application, the terms "first", "second", and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or order. The features defined as "first", "second" may explicitly or implicitly include one or more of the features described. In the description of the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or illustrations. Any embodiment or design described herein as "exemplary" or "such as" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an appearance defect detecting system 100 according to an embodiment of the present application.
Specifically, the appearance defect detecting system 100 includes an object stage 110 and a multi-dimensional adjusting platform 120, the multi-dimensional adjusting platform 120 is erected above the object stage 110, and the object stage 110 is used for loading the mirror surface workpiece 10 to be detected.
The appearance defect detecting system 100 may include a first detecting device 130 and a second detecting device 140, the first detecting device 130 includes a first camera 131 and a first light source 132 fixed to the multi-dimensional adjusting platform 120, the first camera 131 and the first light source 132 are distributed from top to bottom, and the first light source 132 is configured to supplement light to the mirror-surface workpiece 10, so that the first camera 131 collects a first image of the mirror-surface workpiece 10. The second detecting device 140 includes a second camera 141 and a second light source 142 fixed to the multi-dimensional adjusting platform 120, the second camera 141 and the second light source 142 are distributed from top to bottom, and the second light source 142 is used for supplementing light to the mirror surface workpiece 10, so that the second camera 141 acquires a second image of the mirror surface workpiece 10.
As further shown in fig. 2, the appearance defect detecting system 100 further includes a computing device 150, which includes a first detecting module 151 and a second detecting module 152, wherein the computing device 150 is communicatively connected to the first camera 131 and the second camera 141, the first detecting module 151 is configured to detect whether the mirror workpiece 10 has a first type of appearance defect according to the first image, and the second detecting module 152 is configured to detect whether the mirror workpiece 10 has a second type of appearance defect according to the second image.
In an embodiment, the computing device 150 further includes an image preprocessing module 153, and the image preprocessing module 153 is configured to perform position correction and image segmentation on the first image and the second image.
In this embodiment, the image preprocessing module 153 performs position correction and image segmentation on the first image and the second image in advance, and then the first detection module 151 and the second detection module 152 perform defect detection on the preprocessed images respectively, so as to improve the accuracy of the appearance defect detection.
Further, the first camera 131 and the second camera 141 may be CCD industrial cameras or other types of cameras, the computing device 150 may be an industrial control computer or other types of computing devices, and the computing device 150 is in communication connection with the first camera 131 and the second camera 141 to acquire a first image acquired by the first camera 131 for the first detection module 151 to perform the appearance defect detection and acquire a second image acquired by the second camera 141 for the second detection module 152 to perform the appearance defect detection.
In this embodiment, the first camera 131 in the first detection mechanism collects the first image of the mirror-surface workpiece 10 under the supplementary lighting of the first light source 132, the second camera 141 in the second detection mechanism collects the second image of the mirror-surface workpiece 10 under the supplementary lighting of the second light source 142, the computing device 150 is in communication connection with the first camera 131 and the second camera 141, and detects whether the mirror-surface workpiece 10 has the first type of appearance defect according to the first image by setting the first detection module 151, and detects whether the mirror-surface workpiece 10 has the second type of appearance defect according to the second image by setting the second detection module 152, and adopts a targeted detection device for different defects, so that the full-automatic detection of the appearance defect of the mirror-surface workpiece is realized, the accuracy of the appearance detection is improved, the labor cost is saved, and the production efficiency is improved.
In one embodiment, the first type of appearance defect may include at least one of scratch defect, grain defect, bruise defect, and black light defect, and the second type of appearance defect may include at least one of wear mark defect, pinhole defect, and zebra defect.
In this embodiment, the first detecting module 151 detects whether the mirror-surface workpiece 10 has defects such as scratch defects, material defects, bruise defects, and invisible defects based on the first image, and the second detecting module 152 detects whether the mirror-surface workpiece 10 has defects such as wear marks, pin holes, and zebra defects based on the second image, and different detecting methods are adopted for different defects, so that the accuracy of detecting the appearance defects can be effectively improved.
As further shown in connection with fig. 3, the first camera 131 includes an FA lens 133, the second camera 141 includes a telecentric lens 143, the FA lens 133 is spaced apart from the telecentric lens 143, the FA lens 133 is disposed along a first straight line L1, the telecentric lens 143 is disposed along a second straight line L2, and the first straight line L1 is parallel to the second straight line L2.
Further, the first light source 132 includes an annular light source 134, the annular light source 134 is disposed along a first straight line L1, the second light source 142 includes a coaxial light source 144, and the coaxial light source 144 is disposed along a second straight line L2.
In this embodiment, the FA lens 133 supplements light in cooperation with the annular light source 134 to assist the first camera 131 to complete the acquisition of the first image, so that the first detection module 151 detects the first type of appearance defects (scratch defects, texture defects, bruise defects, and non-visible defects) according to the first image. The first image acquired by the means can obviously show the defects such as scratch defects, material grain defects, bruise defects, invisible light defects and the like, so that the accuracy of defect detection is effectively improved. The telecentric lens 143 is used for supplementing light in cooperation with the coaxial light source 144 to assist the second camera 141 in completing the acquisition of the second image, so that the second detection module 152 detects the second type of appearance defects (wear scar defects, pinhole defects, zebra stripe defects) according to the second image. The first image acquired by the means can obviously show defects such as grinding mark defects, pinhole defects, zebra stripe defects and the like, so that the accuracy of defect detection is effectively improved.
In one embodiment, the multi-dimensional adjustment platform 120 includes an X-axis servo module 121, a Y-axis servo module 122, and a Z-axis servo module 123, the X-axis servo module 121 is mounted on the top of the stage 110, the Y-axis servo module 122 is mounted on the bottom of the X-axis servo module 121, the Z-axis servo module 123 is suspended on the X-axis servo module 121, the appearance defect detection system 100 further includes a baffle 124, the baffle 124 is mounted on the Z-axis servo module 123, and the first detection device 130 and the second detection device 140 are mounted on the baffle 124.
In this embodiment, the positions of the first detecting device 130 and the second detecting device 140 are adjusted by the cooperation of the X-axis servo module 121, the Y-axis servo module 122 and the Z-axis servo module 123, so as to comprehensively detect the mirror workpiece 10, thereby improving the flexibility and the practicability of the detection. The baffle 124 is used for carrying the first detecting device 130 and the second detecting device 140, and meanwhile, the baffle 124 is also used for shielding the first camera 131 and the second camera 141 from light, so that the imaging definition is improved.
In one embodiment, a suction bottom mold 111 is disposed above the stage 110 for fixing the mirror surface workpiece 10 placed on the stage 110.
As further shown in fig. 4, the appearance defect detecting system 100 is accommodated in the control cabinet 160, a display 161 is disposed right in front of the control cabinet 160, the display 161 is electrically connected to the computing device 150, and the display 161 is used for displaying the detection result of the mirror surface workpiece 10, so as to facilitate the operator to view the detection result. The display 161 can also display the batch yield, the product yield, and the like of the mirror surface workpiece 10, and enrich the function of the appearance defect detecting system 100.
The work flow of the appearance defect detecting system 100 provided in the above implementation is as follows: firstly, manually placing a mirror surface workpiece 10 to be detected on an objective table 110, and fixing the mirror surface workpiece 10 by using a suction bottom die 111; secondly, the first detection device 130 and the second detection device 140 are adjusted by the multi-dimensional adjusting platform 120, and the first detection device 130 and the second detection device 140 are moved to the upper part of the mirror surface workpiece 10 to collect a first image and a second image; thirdly, the image preprocessing module 153 preprocesses the first image and the second image to meet the detection requirement; fourthly, the first detection module 151 adopts a targeted detection device for different defects after preprocessing, so that full-automatic detection of the workpiece is realized, the accuracy of appearance detection is improved, the labor cost is saved, and the production efficiency is improved.
Referring to fig. 5, fig. 5 is a flowchart illustrating steps of a method for detecting an appearance defect according to an embodiment of the present disclosure.
Specifically, the method for detecting the appearance defects of the mirror surface workpiece 10 may include:
s1, acquiring a first image of a mirror surface workpiece acquired by a first camera under the supplementary lighting of a first light source, and acquiring a second image of a mirror surface workpiece 10 acquired by a second camera under the supplementary lighting of a second light source.
Specifically, the first camera 131 includes an FA lens 133, the second camera 141 includes a telecentric lens 143, the FA lens 133 is disposed spaced apart from the telecentric lens 143, the FA lens 133 is disposed along a first straight line L1, the telecentric lens 143 is disposed along a second straight line L2, and the first straight line L1 is parallel to the second straight line L2.
Further, the first light source 132 includes an annular light source 134, the annular light source 134 is disposed along a first straight line L1, the second light source 142 includes a coaxial light source 144, and the coaxial light source 144 is disposed along a second straight line L2.
In this embodiment, the FA lens 133 cooperates with the annular light source 134 to supplement light to assist the first camera 131 to complete the collection of the first image, the telecentric lens 143 cooperates with the coaxial light source 144 to supplement light to assist the second camera 141 to complete the collection of the second image.
And S2, preprocessing the first image and the second image to obtain a preprocessed first image and a preprocessed second image.
Specifically, the first image and the second image are subjected to position correction and image segmentation processing to obtain a preprocessed first image and a preprocessed second image.
And S3, performing appearance defect detection on the preprocessed first image through a first preset algorithm to obtain a first appearance detection result.
Specifically, the defect search is performed on the preprocessed first image through a first preset algorithm to determine whether the mirror surface workpiece 10 has a first type of appearance defect, where the first type of appearance defect includes at least one of scratch defect, grain defect, bruise defect, and non-visible defect.
And S4, performing appearance defect detection on the preprocessed second image through a second preset algorithm to obtain a second appearance detection result.
Specifically, the defect search is performed on the preprocessed second image through a second preset algorithm to determine whether the mirror surface workpiece 10 has a second type of appearance defect, where the second type of appearance defect includes at least one of a grinding mark defect, a pinhole defect, and a zebra defect.
And S5, obtaining an appearance detection result of the mirror surface workpiece 10 based on the first appearance detection result and the second appearance detection result.
Specifically, after determining that the mirror workpiece 10 has a defect, the method further includes: and judging whether the defect degree of the defects of the mirror surface workpiece 10 is within the corresponding preset defect degree requirement range or not by using a preset condition detection algorithm, and if the defect degree of the defects is within the preset defect degree requirement range, ignoring the defects of the mirror surface workpiece 10.
As further shown in conjunction with fig. 6, step S3 may include:
and S31, judging whether the scratch defect exists or not.
And if the first image does not have the scratch defect, continuously searching other defects.
If the first image has a scratch defect, the process goes to step S311.
S311, judging whether the gray value is larger than a preset threshold value.
And if the gray value of the area where the scratch defect is located in the first image is smaller than a preset threshold value, ignoring the scratch defect.
And S312, judging whether the scratch length is greater than a preset threshold value.
And if the scratch length in the first image is smaller than a preset threshold value, ignoring the scratch defect.
If the gray value of the area where the scratch defect is located in the first image is larger than the preset threshold value and the scratch length is larger than the preset threshold value, the mirror surface workpiece 10 is unqualified.
Further, step S3 may further include:
and S32, judging whether the blank line defect exists or not.
If the first image does not have the material grain defect, other defects are continuously searched.
If the first image has a texture defect, go to step S321.
S321, judging whether the length of the material grain is larger than a preset threshold value.
If the length of the material grain in the first image is smaller than a preset threshold value, the defect of the material grain is ignored.
If the length of the material grain in the first image is greater than the preset threshold value, the mirror surface workpiece 10 is unqualified.
Further, step S3 may further include:
and S33, judging whether the collision defect exists or not.
If the first image has no bruise defect, other defects are continuously searched.
If the first image has a scratch defect, the process goes to step S331.
And S331, judging whether the damage length is larger than a preset threshold value.
If the collision length in the first image is smaller than the preset threshold value, the collision defect is ignored.
If the length of the scratch in the first image is greater than the preset threshold, the mirror surface workpiece 10 is not qualified.
Further, step S3 may further include:
and S34, judging whether the invisible light defect exists or not.
If the first image has no invisible light defect, other defects are continuously searched.
If the first image has the invisible light defect, the process goes to step S341.
S341, determining whether the area of the invisible light is larger than a preset threshold.
If the area of the invisible light in the first image is smaller than the preset threshold value, the invisible light defect is ignored.
If the area of the invisible light in the first image is larger than the preset threshold, the mirror surface workpiece 10 is unqualified.
As further shown in conjunction with fig. 7, step S4 may include:
and S41, judging whether the grinding crack defect exists or not.
If the second image does not have the grinding defect, other defects are continuously searched.
If the second image has a wear scar defect, go to step S411.
S411, judging whether the length of the grinding crack is larger than a preset threshold value.
If the length of the grinding mark in the second image is smaller than a preset threshold value, the grinding mark defect is ignored.
If the length of the grinding crack in the second image is larger than the preset threshold value, the mirror surface workpiece 10 is unqualified.
Further, step S4 may further include:
and S42, judging whether the pinhole defect exists or not.
And if the pinhole defect does not exist in the first image, continuously searching other defects.
If the first image has a pinhole defect, go to step S421.
And S421, judging whether the area of the pinhole is larger than a preset threshold value.
If the pinhole area in the first image is smaller than the preset threshold value, ignoring the pinhole defect.
If the area of the region where the pinhole is located in the first image is larger than the preset threshold value, the mirror surface workpiece 10 is unqualified.
Further, step S4 may further include:
and S43, judging whether the zebra stripes exist.
And if the zebra stripe defect does not exist in the first image, other defects are continuously searched.
If the first image has the zebra defect, the process goes to step S431.
And S431, judging whether the zebra stripe length is larger than a preset threshold value.
And if the zebra stripe length in the first image is smaller than a preset threshold value, ignoring the zebra stripe defect.
If the zebra stripes in the first image are longer than the preset threshold, the mirror surface workpiece 10 is not qualified.
It should be noted that the apparent defect detection method provided by the present application is not limited to detecting the defects listed in the above embodiments. The preset threshold value can be set according to actual production needs, so that the purpose of improving the product percent of pass is achieved.
In this embodiment, in order to improve the defect detection accuracy, firstly, a certain number of samples need to be accumulated, and each group of samples should include various characteristics, such as parameters of gray scale value, length, shape, and area, and the defect can be detected more easily by applying a certain gain to the defect parameters. And then, establishing different types of preset algorithms according to the sample data of the sample library. Finally, different types of defects in the first image collected by the first camera 131 and the second image collected by the second camera 141 are searched by using different preset algorithms. Different detection methods are adopted for different defects, so that the accuracy of defect detection can be effectively improved, and the product percent of pass is improved.
In the appearance defect detecting system 100 and method provided by the embodiment of the present application, the first camera 131 in the first detecting mechanism collects the first image of the mirror surface workpiece 10 under the light supplement of the first light source 132, the second camera 141 in the second detecting mechanism collects the second image of the mirror surface workpiece 10 under the light supplement of the second light source 142, the computing device 150 is in communication connection with the first camera 131 and the second camera 141, the first detecting module 151 is arranged to detect whether the mirror surface workpiece 10 has the first type of appearance defect according to the first image, the second detecting module 152 is arranged to detect whether the mirror surface workpiece 10 has the second type of appearance defect according to the second image, and a targeted detecting method is adopted for different defects, so that the full automatic detection of the appearance defect of the mirror surface workpiece is realized, the accuracy of the appearance detection is improved, the labor cost is saved, and the production efficiency is improved.
Those of ordinary skill in the art will recognize that the specific embodiments described in this specification may vary from name to name, and that the above description is intended merely to illustrate the structure of the application. Equivalent or simple changes in the structure, features and principles of the present application are included in the protection scope of the present application. Various modifications or additions may be made to the described embodiments or methods may be similarly employed by those skilled in the art without departing from the scope of the present application as defined in the appending claims.
Claims (10)
1. The utility model provides an appearance defect detecting system, includes objective table and multidimension regulation platform, multidimension regulation platform erects in the top of objective table, the objective table is used for loading the mirror surface work piece that awaits measuring, its characterized in that, appearance defect detecting system still includes:
the first detection device comprises a first camera and a first light source which are fixed on the multi-dimensional adjusting platform, the first camera and the first light source are distributed from top to bottom, and the first light source is used for supplementing light to the mirror surface workpiece so that the first camera acquires a first image of the mirror surface workpiece;
the second detection device comprises a second camera and a second light source which are fixed on the multi-dimensional adjusting platform, the second camera and the second light source are distributed from top to bottom, and the second light source is used for supplementing light to the mirror surface workpiece so that the second camera acquires a second image of the mirror surface workpiece;
the computing device is in communication connection with the first camera and the second camera, the first detection module is used for detecting whether the mirror surface workpiece has a first type of appearance defects according to the first image, and the second detection module is used for detecting whether the mirror surface workpiece has a second type of appearance defects according to the second image.
2. The visual defect detection system of claim 1, wherein the first type of visual defect comprises at least one of a scratch defect, a grain defect, a bruise defect, an invisible defect, and the second type of visual defect comprises at least one of a wear scar defect, a pinhole defect, a zebra defect.
3. The appearance defect detection system of claim 1, wherein said first camera comprises an FA lens, said second camera comprises a telecentric lens, said FA lens spaced from said telecentric lens, said FA lens disposed along a first line, said telecentric lens disposed along a second line, said first line being parallel to said second line.
4. The visual defect inspection system of claim 3, wherein said first light source comprises an annular light source, said annular light source being disposed along a first line, said second light source comprising a coaxial light source, said coaxial light source being disposed along said second line.
5. The appearance defect detection system of claim 1, wherein the computing device further comprises an image pre-processing module for performing position correction and image segmentation processing on the first image and the second image.
6. The visual defect inspection system of claim 1, wherein the multi-dimensional adjustment platform comprises an X-axis servo module, a Y-axis servo module, and a Z-axis servo module, the X-axis servo module is mounted on the top of the stage, the Y-axis servo module is mounted on the bottom of the X-axis servo module, the Z-axis servo module is suspended on the X-axis servo module, the visual defect inspection system further comprises a baffle plate mounted on the Z-axis servo module, and the first inspection device and the second inspection device are mounted on the baffle plate.
7. An appearance defect detection method is characterized by comprising the following steps:
acquiring a first image of the mirror surface workpiece acquired by a first camera under the supplementary lighting of a first light source, and acquiring a second image of the mirror surface workpiece acquired by a second camera under the supplementary lighting of a second light source;
preprocessing the first image and the second image to obtain a preprocessed first image and a preprocessed second image;
performing appearance defect detection on the preprocessed first image through a first preset algorithm to obtain a first appearance detection result;
performing appearance defect detection on the preprocessed second image through a second preset algorithm to obtain a second appearance detection result;
and obtaining an appearance detection result of the mirror surface workpiece based on the first appearance detection result and the second appearance detection result.
8. The method for detecting appearance defects according to claim 7, wherein the detecting the appearance defects of the preprocessed first image by the first preset algorithm to obtain a first appearance detection result, includes: and searching for defects of the preprocessed first image through the first preset algorithm to determine whether the mirror surface workpiece has a first type of appearance defects, wherein the first type of appearance defects comprise at least one of scratch defects, texture defects, bruise defects and invisible light defects.
9. The method for detecting appearance defects according to claim 7, wherein the detecting the appearance defects of the preprocessed second image by a second preset algorithm to obtain a second appearance detection result comprises: and searching for defects of the preprocessed second image through the second preset algorithm to determine whether the mirror surface workpiece has second type of appearance defects, wherein the second type of appearance defects comprise at least one of grinding mark defects, pinhole defects and zebra stripe defects.
10. The visual defect inspection method of claim 8 or claim 9, wherein determining that the mirror surface workpiece has a defect further comprises: and judging whether the defect degree of the defects of the mirror surface workpiece is within the corresponding preset defect degree requirement range or not by using a preset condition detection algorithm, and if the defect degree of the defects is within the preset defect degree requirement range, ignoring the defects of the mirror surface workpiece.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211039631.5A CN115436394A (en) | 2022-08-29 | 2022-08-29 | Appearance defect detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211039631.5A CN115436394A (en) | 2022-08-29 | 2022-08-29 | Appearance defect detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115436394A true CN115436394A (en) | 2022-12-06 |
Family
ID=84245216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211039631.5A Pending CN115436394A (en) | 2022-08-29 | 2022-08-29 | Appearance defect detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115436394A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115690103A (en) * | 2022-12-30 | 2023-02-03 | 北京阿丘科技有限公司 | Product appearance detection method, device, equipment and storage medium |
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
| CN116106322A (en) * | 2023-04-12 | 2023-05-12 | 广州诺顶智能科技有限公司 | Automatic detection device for appearance of ceramic substrate |
-
2022
- 2022-08-29 CN CN202211039631.5A patent/CN115436394A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
| CN115690103A (en) * | 2022-12-30 | 2023-02-03 | 北京阿丘科技有限公司 | Product appearance detection method, device, equipment and storage medium |
| CN116106322A (en) * | 2023-04-12 | 2023-05-12 | 广州诺顶智能科技有限公司 | Automatic detection device for appearance of ceramic substrate |
| CN116106322B (en) * | 2023-04-12 | 2023-08-29 | 广州诺顶智能科技有限公司 | Automatic detection device for appearance of ceramic substrate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115436394A (en) | Appearance defect detection system and method | |
| CN102253048B (en) | Machine vision detection method and system for detection of various products | |
| CN106226325B (en) | A kind of seat surface defect detecting system and its method based on machine vision | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN112819844B (en) | Image edge detection method and device | |
| CN107515481A (en) | The detection method and device of a kind of display panel | |
| CN108414531A (en) | A kind of fexible film defect detecting device and its detection method based on machine vision | |
| CN112730432A (en) | Laser welding defect detection equipment and detection method for lithium battery of mobile phone | |
| CN114136975A (en) | Intelligent detection system and method for surface defects of microwave bare chip | |
| CN112881427A (en) | Electronic component defect detection device and method based on visible light and infrared thermal imaging | |
| CN114894808A (en) | Device and method for detecting defects of heat pipe orifice based on machine vision | |
| CN114252452A (en) | Online detection device and method for appearance defects and contour dimension of small-sized revolving body | |
| CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
| CN113504239B (en) | Quality control data analysis method | |
| CN109557098A (en) | Metal surface detection system based on machine vision | |
| CN114820439A (en) | PCB bare board defect detection system and method based on AOI | |
| CN114612423A (en) | Chip packaging defect detection method | |
| CN113641155A (en) | High-temperature forging detection control system | |
| CN111307817B (en) | Online detection method and system for PCB production process of intelligent production line | |
| CN112461846A (en) | Workpiece defect detection method and device | |
| CN110763688B (en) | System and method for detecting redundant materials in blind holes | |
| CN112378797A (en) | Full-automatic indentation measuring device and method | |
| CN113305017B (en) | Comprehensive intelligent detection and sorting method for full-automatic valve element | |
| CN113727022B (en) | Method and device for collecting inspection image, electronic equipment and storage medium | |
| Giesko et al. | Advanced mechatronic system for in-line automated optical inspection of metal parts |
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 |