CN113504238A - Glass surface defect collecting device and detection method - Google Patents
Glass surface defect collecting device and detection method Download PDFInfo
- Publication number
- CN113504238A CN113504238A CN202110627103.0A CN202110627103A CN113504238A CN 113504238 A CN113504238 A CN 113504238A CN 202110627103 A CN202110627103 A CN 202110627103A CN 113504238 A CN113504238 A CN 113504238A
- Authority
- CN
- China
- Prior art keywords
- defect
- light source
- glass
- glass surface
- box body
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 106
- 239000011521 glass Substances 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000000137 annealing Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 description 4
- 239000000428 dust Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002994 raw material Substances 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
- G01N21/8851—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
-
- 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
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- 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
- G06T7/12—Edge-based segmentation
-
- 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
- G01N2021/8854—Grading and classifying of flaws
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Abstract
The invention discloses a glass surface defect collecting device and a detection method, wherein the collecting device comprises a box body, an industrial camera, an annular light source and a conveyor belt; the industrial camera is installed at the top end in the box body, the conveyor belt is installed at the bottom end in the box body, and the annular light source is installed between the industrial camera and the conveyor belt; the glass is placed on a conveyor belt. According to the invention, the low-angle annular light source is used for acquiring the defect information of the plane glass, so that the irradiation conditions with good uniformity, good stability and high brightness can be provided, the acquisition of the defect information can be improved to the maximum extent, and particularly, the misjudgment and the missed judgment can be reduced aiming at the defects which are small, have shallow scratch depth and are difficult to identify, and the accuracy of the detection system is greatly improved; the defect information is identified and classified by using the deep learning model, so that the defect information on the curved surface can be effectively acquired, and the defect type can be quickly and efficiently detected.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to a glass surface defect collecting device and a detection method.
Background
Glass is an important basic industrial raw material of national economy, and various defects can occur under the influence of technical conditions, production environment or human factors in a complex deep processing process. The surface defects of the glass destroy the appearance quality and the optical uniformity of the glass product, reduce the use value of the glass, and increase the waste of resources if the defects generated in the previous process flow into the next process, so that the glass needs to be detected in time in the production process. The existing glass surface defect detection method is mainly based on the traditional machine vision mode, but the traditional machine vision needs to manually extract the characteristics of the region of interest, is long in time consumption, high in difficulty and non-uniform in standard, and causes great waste of human resources; and because the defect types of the glass are numerous and diversified, the identification rate is low, the defect detection speed is low, and the efficiency is low.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the above-mentioned defects in the prior art, and to provide a glass surface defect collecting device and a detection method.
For this purpose, the glass surface defect collecting device comprises a box body, an industrial camera, an annular light source and a conveyor belt; the industrial camera is installed at the top end in the box body, the conveyor belt is installed at the bottom end in the box body, and the annular light source is installed between the industrial camera and the conveyor belt; the glass is placed on a conveyor belt.
Preferably, the light source device also comprises a light source bracket which is arranged on the box body and can move up and down in the box body; the annular light source is arranged on the light source bracket.
Preferably, the camera fixture is arranged at the top end inside the box body, and the industrial camera is arranged in the camera fixture.
Preferably, the device further comprises a base, and the box body is mounted on the base.
Preferably, the conveying device further comprises a driving motor, and the conveying belt is controlled to rotate by the driving motor.
The invention also provides a glass surface defect detection method by using the glass surface defect acquisition device, which comprises the following steps:
s1: adjusting the height of the annular light source to the height of the maximum width of the glass plane which can be collected by the industrial camera, and collecting pictures;
s2: extracting a circular area polished by the annular light source by adopting an image processing technology, removing redundant interference information, and extracting an ROI (region of interest);
s3: after the ROI interest area is extracted, feature extraction is carried out on the ROI interest area, and feature information is enhanced;
s4: using label software to frame and sort objects such as scratches, dirt, broken edges and the like on the glass surface, and making a data set;
s5: and selecting YOLOv4 as a basic algorithm framework, constructing a YOLOv4 deep learning defect detection network, optimizing a training strategy, learning the defect information through a neural network according to the defect information labeled by a training set by the model to obtain a training weight model, and using the training weight model in a server defect detection module.
Preferably, step S2 includes:
s21: carrying out image enhancement on the image, and enhancing the characteristic information of the defect;
s22: denoising the image by adopting median filtering;
s23: dividing regions by adopting a gray histogram, selecting a circular region needing defect information identification, and eliminating other interference regions.
Preferably, step S3 includes:
s31: performing edge extraction on the defect information by using a sobel operator to highlight the defect information;
s32: fitting according to the shape of the defect information to complete partial defect information;
s33: and the number of data samples is amplified by performing rotation change, scale transformation and translation transformation on the image.
Preferably, step S4 includes:
s41: dividing the defects into three categories, namely scratches (flaws, points and foreign matters), dirt and edge breakage, and manufacturing an equivalent positive sample set, namely a plane glass sample without the defects;
s42: selecting defect characteristics of a target to be detected by using a label software frame, and generating a corresponding xml file, wherein the xml file comprises the position and the category information of the selected defect characteristics;
s43: the data set was divided into three parts, 80% training set, 10% test set and 10% validation set.
Preferably, the method further comprises: further optimizing the model by adopting a DropBlock regularization method, Mosaic data enhancement and cosine annealing learning rate; and the accuracy of the test result is improved by adopting a K-fold cross verification method.
According to the glass surface defect acquisition device and the detection method, the low-angle annular light source is used for acquiring the defect information of the plane glass, so that the irradiation conditions with good uniformity, good stability and high brightness can be provided, the acquisition of the defect information can be improved to the maximum extent, and particularly, the misjudgment and the missed judgment can be reduced aiming at the defects which are small, have shallow scratch depth and are difficult to identify, and the accuracy of a detection system is greatly improved; the defect information is identified and classified by using the deep learning model, the characteristics of the region of interest do not need to be extracted manually, the time consumption is short, the difficulty is low, a large amount of waste of human resources can be avoided, the defect information on the curved surface can be effectively acquired, and the defect type can be detected quickly and efficiently.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic view of a glass surface defect collecting device according to the present invention.
Reference numerals: 1. a box body; 2. an industrial camera; 3. an annular light source; 4. a conveyor belt; 5. a light source holder; 6. a camera fixture; 7. a base; 8. the motor is driven.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, the present embodiment provides a glass surface defect collecting device, which comprises a box body 1, an industrial camera 2, an annular light source 3 and a conveyor belt 4; the industrial camera 2 is arranged at the top end in the box body 1, the conveyor belt 4 is arranged at the bottom end in the box body 1, and the annular light source 3 is arranged between the industrial camera 2 and the conveyor belt 4; the glass is placed on a conveyor belt 4.
In this embodiment, since the dust in the air interferes with the quality of the acquired image under the irradiation of strong light, the dust is easily recognized as a defect, which causes a determination error, and thus the case 1 is provided to operate the acquisition device in a closed space, thereby reducing the probability of erroneous determination.
In the embodiment, the annular light source 3 can provide irradiation conditions with good uniformity, good stability and high brightness, and can improve the acquisition of defect information to the greatest extent, and particularly reduce erroneous judgment and missing judgment aiming at defects which are small, have shallow scratch depths and are difficult to identify, thereby greatly improving the accuracy of the detection system.
The glass surface defect collecting device also comprises a light source bracket 5, wherein the light source bracket 5 is arranged on the box body 1 and can move up and down in the box body 1; the annular light source 3 is mounted on a light source support 5.
In the present embodiment, since the effect produced by the ring-shaped light source 3 is circular, not the information of the entire glass surface but the information of the glass surface within the light source range is exhibited. By installing the ring light source 3 on the light source support 5, the height of the light source support 5 can be adjusted so as to adjust the height of the ring light source 3, so that the ring light source 3 can cover the whole glass, and the industrial camera 2 can acquire the whole glass plane.
The glass surface defect collecting device further comprises a camera clamp 6, the camera clamp 6 is installed at the top end inside the box body 1, and the industrial camera 2 is installed in the camera clamp 6.
In the present embodiment, the camera holder 6 is used to mount the industrial camera 2, and by mounting the industrial camera 2 in the camera holder 6, it is ensured that the industrial camera 2 can be stably mounted on the top end inside the case 1.
The glass surface defect collecting device also comprises a base 7, and the box body 1 is arranged on the base 7; the glass surface defect collecting device further comprises a driving motor 8, and the conveying belt 4 is controlled by the driving motor 8 to rotate.
In this embodiment, the base 7 is used for fixing the box 1, and the driving motor 8 is used for driving the conveyor belt 4 to rotate.
In this embodiment, the process of collecting the glass surface defect image is as follows: control driving motor 8 motion, conveyer belt 4 begins to turn left motion from the right side for planar glass turns left from the right side and moves, and at the in-process that removes, industrial camera 2 from left to right carries out the collection of image to the glass surface, and light source support 5 fixes at 1 certain height of box, and the height of straight line module control light source support 5 of accessible z axle, annular light source 3 is fixed on light source support 5, and annular light source 3 passes through electrical controller and adjusts luminance.
The embodiment also provides a glass surface defect detection method using the glass surface defect acquisition device, which comprises the following steps:
s1: adjusting the height of the annular light source 3 to the height at which the industrial camera 2 can acquire the maximum width of the glass plane, and acquiring pictures;
s2: extracting a circular area polished by the annular light source 3 by adopting an image processing technology, removing redundant interference information, and extracting an ROI (region of interest);
s3: after the ROI interest area is extracted, feature extraction is carried out on the ROI interest area, and feature information is enhanced;
s4: using label software to frame and sort objects such as scratches, dirt, broken edges and the like on the glass surface, and making a data set;
s5: and selecting YOLOv4 as a basic algorithm framework, constructing a YOLOv4 deep learning defect detection network, optimizing a training strategy, learning the defect information through a neural network according to the defect information labeled by a training set by the model to obtain a training weight model, and using the training weight model in a server defect detection module.
In this embodiment, since the industrial camera 2 needs to be adjusted to a certain height, which results in an excessively large area range for recognition compared with the detection effective area, after the picture is acquired, the circular area polished by the annular light source 3 is extracted by adopting an image processing technology, redundant interference information is eliminated, and after the recognition area is extracted, the feature extraction is performed on the recognition area, so that the feature information is enhanced.
Step S2 includes:
s21: carrying out image enhancement on the image, and enhancing the characteristic information of the defect;
s22: denoising the image by adopting median filtering;
s23: dividing regions by adopting a gray histogram, selecting a circular region needing defect information identification, and eliminating other interference regions.
In this embodiment, because the industrial camera 2 inevitably generates noise during the digital-to-electrical conversion process, the median filter is used to denoise the image, and sharp edge information of the image can be protected.
Step S3 includes:
s31: performing edge extraction on the defect information by using a sobel operator to highlight the defect information;
s32: fitting according to the shape of the defect information to complete partial defect information;
s33: and the number of data samples is amplified by performing rotation change, scale transformation and translation transformation on the image.
In the present embodiment, steps S2 and S3 are image preprocessing. Because partial defect has partial information loss in the image preprocessing process, the defect information is discontinuous, and the partial defect information needs to be fitted according to the shape of the defect information. Because the number of the defect samples is small, the number of the data samples needs to be amplified by performing operations such as rotation change, scale transformation, translation transformation and the like on the image.
Step S4 includes:
s41: dividing the defects into three categories, namely scratches (flaws, points and foreign matters), dirt and edge breakage, and manufacturing an equivalent positive sample set, namely a plane glass sample without the defects;
s42: selecting defect characteristics of a target to be detected by using a label software frame, and generating a corresponding xml file, wherein the xml file comprises the position and the category information of the selected defect characteristics;
s43: the data set was divided into three parts, 80% training set, 10% test set and 10% validation set.
The glass surface defect detection method further comprises the following steps: further optimizing the model by adopting a DropBlock regularization method, Mosaic data enhancement and cosine annealing learning rate; and the accuracy of the test result is improved by adopting a K-fold cross verification method.
In this embodiment, the model structure used is a YOLOv4 network, the size of the network input is a multiple of 32, and the appropriate size may be selected according to the performance of the computer GPU. In the model selection of the industrial camera 2, a camera of 500 ten thousand pixels is used, which is sufficient in resolution, and the input picture size is finally selected to be 608 × 608. In order to further optimize the model, a DropBlock regularization method, Mosaic data enhancement, cosine annealing learning rate and the like are adopted, and in order to improve the accuracy of the test result, a K-fold cross-validation method is adopted for verification. And obtaining a training weight after the model is trained, and loading the training weight into a prediction program to detect whether the glass plane has defects.
According to the glass surface defect acquisition device and the detection method, the low-angle annular light source is used for acquiring the defect information of the plane glass, so that the irradiation conditions with good uniformity, good stability and high brightness can be provided, the acquisition of the defect information can be improved to the maximum extent, and particularly, the misjudgment and the missed judgment can be reduced aiming at the defects which are small, have shallow scratch depth and are difficult to identify, and the accuracy of a detection system is greatly improved; the defect information is identified and classified by using the deep learning model, the characteristics of the region of interest do not need to be extracted manually, the time consumption is short, the difficulty is low, a large amount of waste of human resources can be avoided, the defect information on the curved surface can be effectively acquired, and the defect type can be detected quickly and efficiently.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. The glass surface defect acquisition device is characterized by comprising a box body (1), an industrial camera (2), an annular light source (3) and a conveyor belt (4); the industrial camera (2) is arranged at the top end inside the box body (1), the conveyor belt (4) is arranged at the bottom end inside the box body (1), and the annular light source (3) is arranged between the industrial camera (2) and the conveyor belt (4); the glass is placed on a conveyor belt (4).
2. The glass surface defect collecting device of claim 1, further comprising a light source bracket (5), wherein the light source bracket (5) is mounted on the box body (1) and can move up and down in the box body (1); the annular light source (3) is arranged on the light source bracket (5).
3. A glass surface defect collection device according to claim 1, further comprising a camera fixture (6), wherein the camera fixture (6) is mounted at the top end of the interior of the box body (1), and the industrial camera (2) is mounted in the camera fixture (6).
4. A glass surface defect collection device according to claim 1, further comprising a base (7), wherein the housing (1) is mounted on the base (7).
5. A glass surface defect collection device according to claim 1, further comprising a drive motor (8), wherein the conveyor (4) is controlled to rotate by the drive motor (8).
6. A glass surface defect detecting method using the glass surface defect collecting device according to any one of claims 1 to 5, comprising the steps of:
s1: adjusting the height of the annular light source (3) to the height of the maximum width of the glass plane which can be collected by the industrial camera (2), and collecting pictures;
s2: extracting a circular area polished by the annular light source (3) by adopting an image processing technology, removing redundant interference information, and extracting an ROI (region of interest);
s3: after the ROI interest area is extracted, feature extraction is carried out on the ROI interest area, and feature information is enhanced;
s4: using label software to frame and sort objects such as scratches, dirt, broken edges and the like on the glass surface, and making a data set;
s5: and selecting YOLOv4 as a basic algorithm framework, constructing a YOLOv4 deep learning defect detection network, optimizing a training strategy, learning the defect information through a neural network according to the defect information labeled by a training set by the model to obtain a training weight model, and using the training weight model in a server defect detection module.
7. The method for detecting the surface defects of the glass as claimed in claim 6, wherein the step S2 includes:
s21: carrying out image enhancement on the image, and enhancing the characteristic information of the defect;
s22: denoising the image by adopting median filtering;
s23: dividing regions by adopting a gray histogram, selecting a circular region needing defect information identification, and eliminating other interference regions.
8. The method for detecting the surface defects of the glass as claimed in claim 6, wherein the step S3 includes:
s31: performing edge extraction on the defect information by using a sobel operator to highlight the defect information;
s32: fitting according to the shape of the defect information to complete partial defect information;
s33: and the number of data samples is amplified by performing rotation change, scale transformation and translation transformation on the image.
9. The method for detecting the surface defects of the glass as claimed in claim 6, wherein the step S4 includes:
s41: dividing the defects into three types, namely scratches, dirt and edge breakage, and manufacturing an equivalent positive sample set;
s42: selecting defect characteristics of a target to be detected by using a label software frame, and generating a corresponding xml file, wherein the xml file comprises the position and the category information of the selected defect characteristics;
s43: the data set was divided into triplicates, 80% training set, 10% test set and 10% validation set.
10. The method of claim 6, further comprising: further optimizing the model by adopting a DropBlock regularization method, Mosaic data enhancement and cosine annealing learning rate; and the accuracy of the test result is improved by adopting a K-fold cross verification method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627103.0A CN113504238B (en) | 2021-06-04 | 2021-06-04 | Glass surface defect acquisition device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627103.0A CN113504238B (en) | 2021-06-04 | 2021-06-04 | Glass surface defect acquisition device and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113504238A true CN113504238A (en) | 2021-10-15 |
| CN113504238B CN113504238B (en) | 2023-12-22 |
Family
ID=78009039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110627103.0A Active CN113504238B (en) | 2021-06-04 | 2021-06-04 | Glass surface defect acquisition device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113504238B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113137A (en) * | 2021-11-10 | 2022-03-01 | 佛山科学技术学院 | Defect detection system and method for thin film material |
| CN114235847A (en) * | 2021-12-20 | 2022-03-25 | 深圳市尊绅投资有限公司 | Liquid crystal display panel glass substrate surface defect detection device and detection method |
| CN117517348A (en) * | 2023-11-14 | 2024-02-06 | 四川领先微晶玻璃有限公司 | Surface defect detection system based on microcrystalline glass panel finished product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048333A (en) * | 2012-12-07 | 2013-04-17 | 北京优纳科技有限公司 | Appearance detection equipment and method |
| US20130188869A1 (en) * | 2012-01-20 | 2013-07-25 | Korea Advanced Institute Of Science And Technology | Image segmentation method using higher-order clustering, system for processing the same and recording medium for storing the same |
| KR20190114384A (en) * | 2018-03-30 | 2019-10-10 | 광운대학교 산학협력단 | Apparatus and method for skin lesion diagnosis based on neural network |
| CN110389127A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of identification of cermet part and surface defects detection system and method |
| CN110570393A (en) * | 2019-07-31 | 2019-12-13 | 华南理工大学 | mobile phone glass cover plate window area defect detection method based on machine vision |
| CN110672617A (en) * | 2019-09-14 | 2020-01-10 | 华南理工大学 | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision |
| CN110865081A (en) * | 2019-11-19 | 2020-03-06 | 东莞市翔飞智能装备科技有限公司 | Transparent bottle automatic check out system |
| CN112200762A (en) * | 2020-07-02 | 2021-01-08 | 西南科技大学 | Diode glass bulb defect detection method |
-
2021
- 2021-06-04 CN CN202110627103.0A patent/CN113504238B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130188869A1 (en) * | 2012-01-20 | 2013-07-25 | Korea Advanced Institute Of Science And Technology | Image segmentation method using higher-order clustering, system for processing the same and recording medium for storing the same |
| CN103048333A (en) * | 2012-12-07 | 2013-04-17 | 北京优纳科技有限公司 | Appearance detection equipment and method |
| KR20190114384A (en) * | 2018-03-30 | 2019-10-10 | 광운대학교 산학협력단 | Apparatus and method for skin lesion diagnosis based on neural network |
| CN110389127A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of identification of cermet part and surface defects detection system and method |
| CN110570393A (en) * | 2019-07-31 | 2019-12-13 | 华南理工大学 | mobile phone glass cover plate window area defect detection method based on machine vision |
| CN110672617A (en) * | 2019-09-14 | 2020-01-10 | 华南理工大学 | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision |
| CN110865081A (en) * | 2019-11-19 | 2020-03-06 | 东莞市翔飞智能装备科技有限公司 | Transparent bottle automatic check out system |
| CN112200762A (en) * | 2020-07-02 | 2021-01-08 | 西南科技大学 | Diode glass bulb defect detection method |
Non-Patent Citations (3)
| Title |
|---|
| 唐庆菊;刘俊岩;王扬;刘元林;梅晨;: "基于模糊C均值聚类和Canny算子的红外图像边缘识别与缺陷定量检测", 红外与激光工程, no. 09 * |
| 蔡彪;沈宽;付金磊;张理泽;: "基于Mask R-CNN的铸件X射线DR图像缺陷检测研究", 仪器仪表学报, no. 03 * |
| 薛月菊;黄宁;涂淑琴;毛亮;杨阿庆;朱勋沐;杨晓帆;陈鹏飞;: "未成熟芒果的改进YOLOv2识别方法", 农业工程学报, no. 07 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113137A (en) * | 2021-11-10 | 2022-03-01 | 佛山科学技术学院 | Defect detection system and method for thin film material |
| CN114235847A (en) * | 2021-12-20 | 2022-03-25 | 深圳市尊绅投资有限公司 | Liquid crystal display panel glass substrate surface defect detection device and detection method |
| CN117517348A (en) * | 2023-11-14 | 2024-02-06 | 四川领先微晶玻璃有限公司 | Surface defect detection system based on microcrystalline glass panel finished product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113504238B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113504238B (en) | Glass surface defect acquisition device and detection method | |
| CN111815630B (en) | Defect detection method and device for LCD screen | |
| JP5920994B2 (en) | Method and system for identifying well wall boundaries of microplates | |
| CN108918543B (en) | Dynamic detection device and method for mirror surface scratch | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN112330598B (en) | Method, device and storage medium for detecting stiff yarn defects on chemical fiber surface | |
| CN111612737B (en) | Artificial board surface flaw detection device and detection method | |
| JP2013526717A5 (en) | ||
| CN110596116B (en) | Vehicle surface flaw detection method and system | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN108986055B (en) | Visual detection method for tiny cracks on egg shell surface | |
| CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
| CN113777030A (en) | Cloth surface defect detection device and method based on machine vision | |
| CN111474179A (en) | Lens surface cleanliness detection device and method | |
| CN113658131A (en) | Tour type ring spinning broken yarn detection method based on machine vision | |
| CN112927223A (en) | Glass curtain wall detection method based on infrared thermal imager | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| CN114820475A (en) | Edge identification method and system, wafer processing device and method for determining concentric state of wafer and processing table | |
| CN113390882A (en) | Tire inner side defect detector based on machine vision and deep learning algorithm | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN117252861A (en) | Method, device and system for detecting wafer surface defects | |
| CN115063340A (en) | Bacterial colony counting method and bacterial colony counter | |
| CN112798608B (en) | Optical detection device and optical detection method for side wall of inner cavity of mobile phone camera support | |
| CN112987356B (en) | Liquid crystal display panel bottom foreign matter filtering device | |
| Zhang et al. | A LCD screen Mura defect detection method based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |