CN106872488A - A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device - Google Patents
A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device Download PDFInfo
- Publication number
- CN106872488A CN106872488A CN201710259666.2A CN201710259666A CN106872488A CN 106872488 A CN106872488 A CN 106872488A CN 201710259666 A CN201710259666 A CN 201710259666A CN 106872488 A CN106872488 A CN 106872488A
- Authority
- CN
- China
- Prior art keywords
- defect
- surface defect
- substrate
- transparent substrate
- size
- 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 118
- 239000000758 substrate Substances 0.000 title claims abstract description 86
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000003384 imaging method Methods 0.000 claims abstract description 31
- 238000007689 inspection Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000009434 installation Methods 0.000 claims abstract description 4
- 230000000007 visual effect Effects 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 9
- 238000013316 zoning Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 230000001537 neural effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000005329 float glass Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
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
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
Abstract
The invention discloses a kind of double surface defect visible detection methods of rapid large-area transparent substrate and device, method is as follows：N blocks region is divided into according to accuracy of detection and camera lens scope to a kind of large-area transparent substrate, and cover two-sided vision inspection apparatus by region configuration 2n, according to the position location and installation vision inspection apparatus of each anchor point, shoot substrate image, Machine Vision Detection is carried out to substrate image, large-area transparent substrate general image is pieced together again, detection means includes PC control systems, upper imaging modules, connector, lower imaging modules, transparent device and adjuster, the present invention separates the part such as appearance and size Detection task successively from substrate surface defects detection object, detected for a task every time；Intelligent Measurement and the identification of substrate surface defect can be quickly and efficiently realized by the present invention.
Description
Technical field
Detection and identification technology field the present invention relates to transparent substrate surface defect, and in particular to a kind of rapid large-area
The visible detection method and device of the two-sided surface defect of transparent substrate.
Background technology
Large-area transparent substrate is widely used in the fields such as optics, optic communication, laser technology, optical imagery and detection,
Played an important role in flat-faced screen, minisize pick-up head, Biomedical Instruments, advanced laser system.Such as flat-faced screen neck
The quality control of large-area transparent substrate is the key technology that plane shows in domain；Must be each equipped with similar photovoltaic
A piece of substrate, domestic, international market is huge to the demand of substrate, and domestic annual requirement just has 1,000,000,000.
Include spectral detection and surface defects detection to the detection of substrate, wherein surface defect at present generally using it is artificial by
Piece detection method, judged by micro- sem observation under strong illumination, labour intensity greatly, flase drop loss is high, also without
Method realizes on-line checking.Vision-based detection shoots tested object image by video camera, and it is right to be realized using technologies such as image procossings
The on-line intelligence detection of substrate surface defect, not only ensures the every accuracy of detection of substrate, is additionally operable to count all kinds of defects appearance
Probability, carry out quality control.
The automatic detection object of current product defects is generally steel plate, weld seam etc., and key step includes IMAQ and defect
Detection, the selection of defect characteristic parameter, defect recognition and classification.Wherein characteristic parameter selection is to choose one group to distinguish all kinds of defects
The most strong parameter of ability is used as characteristic parameter；Defect recognition judges its class with classification according to the characteristic parameter value of certain defect
Not, generally completed by grader.The defect classification that grader judges is more, institute must the quantity of characteristic parameter increase therewith, classification
Device structure and sorting algorithm are more complicated, and False Rate is raised.By taking BP neural network grader as an example, the network is divided into input layer, hidden
Containing layer, output layer, the wherein neuronal quantity n of input layer is equal to characteristic parameter number；Output layer neuronal quantity m and defect class
Other number is relevant, and classification number is equal to when classification is less；Empirical relation between the neuronal quantity n1 and n, m of hidden layer meets
[research of the wide defects in float glass ONLINE RECOGNITION algorithms of Liu Huai and system realize Central China University of Science and Technology doctor 2011.].
Each layer neuron of the more BP neural networks of visual defects classification is more, and neuronal quantity determines the complexity of BP networks.Cause
The performance of two graders (two classifications of identification), should be preferential better than multi-categorizer (identification two or more classification) under this equal conditions
From two graders [the classifier design research Nanjing Aero-Space University doctor of Wang Yunyun combination prioris
2011.]。
Substrate surface defects detection object includes appearance and size, chamfers defect, interference colours inequality defect, collapse defect, scratch
Defect, point defect, spot print defect.If all kinds of defects of substrate are used uniformly across a grader being identified, necessarily cause algorithm
It is complicated, time-consuming for classification, it is difficult to ensure classification accuracy rate.All kinds of defects of substrate are analyzed, it is found that they have following features：Tiltedly
Incised notch falls into causes appearance and size unqualified；Film color inequality defect causes the color in each region of substrate to there is significant difference；Collapse scarce
It is long and narrow defect area to fall into the common ground of scuffing defect, and difference is to collapse defect to appear in substrate outer edge, scratch defect
Appear in substrate zone line；Point defect is that defect area is rectangle with the common ground of spot print defect, and difference is that point defect is covered
Capping product is small, spot print defect area coverage is big.
The content of the invention
The purpose of the present invention is to solve above-mentioned deficiency, there is provided a kind of two-sided surface defect of rapid large-area transparent substrate
Visible detection method and device.
The purpose of the present invention is achieved through the following technical solutions：
A kind of double surface defect visible detection methods of rapid large-area transparent substrate, specific method is as follows：
A is divided into n blocks region to a kind of large-area transparent substrate according to accuracy of detection and camera lens scope；
B covers two-sided vision inspection apparatus by region configuration 2n, according to the position location and installation vision inspection apparatus of each anchor point；
C shoots substrate image, Machine Vision Detection is carried out to substrate image, then piece together large-area transparent substrate general image；
D extracts substrate outer rim edge, detects substrate appearance and size and positioning；
E judges whether the standard deviation value between the surface defect number average of polylith target area is less than standard deviation difference limen
Value, if it is, performing step F, is otherwise judged to defect of substrate；
F judges in image whether surface defect size size is above standard value, if it is, being judged to defect of substrate；If not,
Then perform step G；
G extracts number of defective areas weighted value, zoning and overall quantity characteristic value, and the characteristic value classified calculating is joined
Numerical value.
It is to extract two outer rim edges in face, the substrate outer rim edge bag that substrate outer rim edge is extracted in step D
Size extraneous surfaces Defect Edge is enclosed, substrate positional parameter is extracted from the edge image according to marginal position；The step D
Also include judging whether substrate appearance and size meets tolerance, if it is, performing above-mentioned steps E；Otherwise it is judged to that size lacks
Fall into.
Step E is comprised the following steps that：The boundary rectangle at each size surface defect edge is extracted, defect ROI is formed, calculated
The Curve-Rectangle characteristic values of defect ROI；The Curve-Rectangle characteristic values of defect ROI are input into Curve-
Rectangle graders, judge the type of size surface defect；The difference that the Curve-Rectangle graders are judged
The characteristic value of model size extraneous surfaces defect is input into different graders respectively；Judge size surface defect in type group
Particular type：Extract the number parameter of all types of defects.
The Curve-Rectangle characteristic values of defect ROI are input into Curve-Rectangle graders, the size of judgement
The defect type of extraneous surfaces includes scratching-collapsing type and spot print-vertex type.
The quantative attribute value of all types of defects is input into host computer, according to surface defect size size in image whether
Be above standard value, if it is, being judged to defect of substrate；If it is not, then performing step G.
The region quantity characteristic value of all types of defects is input into host computer, weighted calculation quantitative value, zoning and
Overall quantity characteristic value, and by the characteristic value classified calculating parameter value, final output substrate surface defects detection result.
A kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate, including two-sided vision-based detection platform, regard
Feel testing equipment and host computer, the two-sided vision-based detection platform is provided with visual detection equipment, the visual detection equipment
Be connected with the host computer by holding wire, the visual detection equipment be double-side detection equipment, including PC control systems, up and down
The upper imaging modules and lower imaging modules for setting gradually, are provided with to be detected big between the upper imaging modules and lower imaging modules
Area transparent substrate, the lower imaging modules are provided with a connector, and the connector passes through holding wire with the PC control systems
Connection, the upper imaging modules are connected by holding wire with the PC control systems.
In addition, being provided with adjuster between the upper imaging modules and the lower imaging modules.
Preferably, the two-sided vision-based detection platform is provided with multiple anchor points, and each anchor point is provided with a vision inspection
Measurement equipment, the visual detection equipment is arranged in streamline direction.
The present invention has following beneficial effect：
The present invention separates the part such as appearance and size Detection task successively from substrate surface defects detection object, and one is directed to every time
Task is detected；Intelligent Measurement and the identification of substrate surface defect can be quickly and efficiently realized by the present invention.
Brief description of the drawings
Fig. 1 is detection method flow chart of the invention；
Fig. 2 is structure chart of the invention；
Fig. 3 is the structure chart of double-face imaging testing equipment of the invention.
Specific embodiment
The present invention is further illustrated below in conjunction with the accompanying drawings：
As shown in figure 1, a kind of double surface defect visible detection methods of rapid large-area transparent substrate, specific method is as follows：
A is divided into n blocks region to a kind of large-area transparent substrate according to accuracy of detection and camera lens scope；
B covers two-sided vision inspection apparatus by region configuration 2n, according to the position location and installation vision inspection apparatus of each anchor point；
C shoots substrate image, Machine Vision Detection is carried out to substrate image, then piece together large-area transparent substrate general image；
D extracts substrate outer rim edge, detects substrate appearance and size and positioning；
E judges whether the standard deviation value between the surface defect number average of polylith target area is less than standard deviation difference limen
Value, if it is, performing step F, is otherwise judged to defect of substrate；
F judges in image whether surface defect size size is above standard value, if it is, being judged to defect of substrate；If not,
Then perform step G；
G extracts number of defective areas weighted value, zoning and overall quantity characteristic value, and the characteristic value classified calculating is joined
Numerical value.
It is to extract two outer rim edges in face, the substrate outer rim edge bag that substrate outer rim edge is extracted in step D
Size extraneous surfaces Defect Edge is enclosed, substrate positional parameter is extracted from the edge image according to marginal position；The step D
Also include judging whether substrate appearance and size meets tolerance, if it is, performing above-mentioned steps E；Otherwise it is judged to that size lacks
Fall into.
Step E is comprised the following steps that：The boundary rectangle at each size surface defect edge is extracted, defect ROI is formed, calculated
The Curve-Rectangle characteristic values of defect ROI；The Curve-Rectangle characteristic values of defect ROI are input into Curve-
Rectangle graders, judge the type of size surface defect；The difference that the Curve-Rectangle graders are judged
The characteristic value of model size extraneous surfaces defect is input into different graders respectively；Judge size surface defect in type group
Particular type：Extract the number parameter of all types of defects.
The Curve-Rectangle characteristic values of defect ROI are input into Curve-Rectangle graders, the size of judgement
The defect type of extraneous surfaces includes scratching-collapsing type and spot print-vertex type.
The quantative attribute value of all types of defects is input into host computer, according to surface defect size size in image whether
Be above standard value, if it is, being judged to defect of substrate；If it is not, then performing step G.
The region quantity characteristic value of all types of defects is input into host computer, weighted calculation quantitative value, zoning and
Overall quantity characteristic value, and by the characteristic value classified calculating parameter value, final output substrate surface defects detection result.
Reference picture 2 ~ 3, a kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate, including the inspection of two-sided vision
Platform 1, visual detection equipment 2 and host computer 3 are surveyed, two-sided vision-based detection platform 1 is provided with visual detection equipment 2, vision inspection
Measurement equipment 2 is connected by holding wire with host computer 3, and two-sided vision-based detection platform is provided with multiple anchor points 20, each anchor point
A visual detection equipment is provided with, and these visual detection equipments are arranged in streamline direction.
Wherein, visual detection equipment 2 be double-side detection equipment, including PC control systems 21, set gradually up and down on into
As module 22 and lower imaging modules 23, large-area transparent base to be detected is provided between upper imaging modules 22 and lower imaging modules 23
Piece 4, lower imaging modules 23 are provided with a connector 24, and connector 24 is connected with PC control systems 21 by holding wire, upper imaging mould
Group 22 is connected by holding wire with PC control systems 21.Imaging modules are wherein gone up for obtaining the image-forming information of front detection, under
Imaging modules 23 are used to obtain the image-forming information of back side detection, in addition, being provided between upper imaging modules 22 and lower imaging modules 23
Adjuster 25, the adjuster 25 is used to adjust imaging modules 22, lower imaging modules 23 with large-area transparent substrate 4 to be detected
The distance between, such that it is able to make its imaging relatively sharp.
Although disclosed herein implementation method as above, described content is only to facilitate understanding the present invention and adopting
Implementation method, is not limited to the present invention.Any those skilled in the art to which this invention pertains, are not departing from this
On the premise of the disclosed spirit and scope of invention, any modification and change can be made in the formal and details implemented,
But scope of patent protection of the invention, must be still defined by the scope of which is defined in the appended claims.
Claims (10)
1. double surface defect visible detection methods of a kind of rapid large-area transparent substrate, it is characterised in that：Specific method is as follows：
A is divided into n blocks region to a kind of large-area transparent substrate according to accuracy of detection and camera lens scope；
B covers two-sided vision inspection apparatus by region configuration 2n, according to the position location and installation vision inspection apparatus of each anchor point；
C shoots substrate image, Machine Vision Detection is carried out to substrate image, then piece together large-area transparent substrate general image；
D extracts substrate outer rim edge, detects substrate appearance and size and positioning；
E judges whether the standard deviation value between the surface defect number average of polylith target area is less than standard deviation difference limen
Value, if it is, performing step F, is otherwise judged to defect of substrate；
F judges in image whether surface defect size size is above standard value, if it is, being judged to defect of substrate；If not,
Then perform step G；
G extracts number of defective areas weighted value, zoning and overall quantity characteristic value, and the characteristic value classified calculating is joined
Numerical value.
2. a kind of double surface defect visible detection methods of rapid large-area transparent substrate according to claim 1, its feature
It is：It is to extract two outer rim edges in face, the substrate outer rim edge bag that substrate outer rim edge is extracted in the step D
Size extraneous surfaces Defect Edge is enclosed, substrate positional parameter is extracted from the edge image according to marginal position；The step D
Also include judging whether substrate appearance and size meets tolerance, if it is, performing above-mentioned steps E；Otherwise it is judged to that size lacks
Fall into.
3. a kind of double surface defect visible detection methods of rapid large-area transparent substrate according to claim 1, its feature
It is：The step E is comprised the following steps that：The boundary rectangle at each size surface defect edge is extracted, defect ROI, meter is formed
Calculate the Curve-Rectangle characteristic values of defect ROI；The Curve-Rectangle characteristic values of defect ROI are input into Curve-
Rectangle graders, judge the type of size surface defect；The difference that the Curve-Rectangle graders are judged
The characteristic value of model size extraneous surfaces defect is input into different graders respectively；Judge size surface defect in type group
Particular type：Extract the number parameter of all types of defects.
4. a kind of double surface defect visible detection methods of rapid large-area transparent substrate according to claim 1, its feature
It is：The Curve-Rectangle characteristic values by defect ROI are input into Curve-Rectangle graders, the size of judgement
The defect type of extraneous surfaces includes scratching-collapsing type and spot print-vertex type.
5. a kind of double surface defect visible detection methods of rapid large-area transparent substrate according to claim 1, its feature
It is：The quantative attribute value of all types of defects is input into host computer, whether is surpassed according to surface defect size size in image
Standard value is crossed, if it is, being judged to defect of substrate；If it is not, then performing step G.
6. a kind of double surface defect visible detection methods of rapid large-area transparent substrate according to claim 1, its feature
It is：The region quantity characteristic value of all types of defects is input into host computer, weighted calculation quantitative value, zoning and entirety
Quantative attribute value, and by the characteristic value classified calculating parameter value, final output substrate surface defects detection result.
7. double surface defect vision inspection apparatus of a kind of rapid large-area transparent substrate, including two-sided vision-based detection platform, vision
Testing equipment and host computer, the two-sided vision-based detection platform are provided with visual detection equipment, and the visual detection equipment is led to
Cross holding wire to be connected with the host computer, it is characterised in that the visual detection equipment is double-side detection equipment, including PC controls
System, the upper imaging modules for setting gradually up and down and lower imaging modules, are provided between the upper imaging modules and lower imaging modules
Large-area transparent substrate to be detected, the lower imaging modules are provided with a connector, the connector and the PC control systems
Connected by holding wire, the upper imaging modules are connected by holding wire with the PC control systems.
8. a kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate according to claim 7, its feature
It is to be provided with adjuster between the upper imaging modules and the lower imaging modules.
9. a kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate according to claim 7, its feature
It is that the two-sided vision-based detection platform is provided with multiple anchor points, and each anchor point is provided with a visual detection equipment.
10. a kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate according to claim 9, its feature
It is that the visual detection equipment is arranged in streamline direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710259666.2A CN106872488A (en) | 2017-04-20 | 2017-04-20 | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710259666.2A CN106872488A (en) | 2017-04-20 | 2017-04-20 | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106872488A true CN106872488A (en) | 2017-06-20 |
Family
ID=59162938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710259666.2A Pending CN106872488A (en) | 2017-04-20 | 2017-04-20 | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106872488A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473179A (en) * | 2019-07-30 | 2019-11-19 | 上海深视信息科技有限公司 | A kind of film surface defects detection method, system and equipment based on deep learning |
| CN111242902A (en) * | 2020-01-02 | 2020-06-05 | 天津瑟威兰斯科技有限公司 | Method, system and equipment for identifying and detecting parts based on convolutional neural network |
| CN112102255A (en) * | 2020-08-21 | 2020-12-18 | 杭州培慕科技有限公司 | Intelligent defect rating method based on X-ray imaging image in industrial scene |
| CN112730452A (en) * | 2020-12-22 | 2021-04-30 | 苏州京浜光电科技股份有限公司 | Method for detecting surface defects of optical filter |
| CN113865483A (en) * | 2021-09-14 | 2021-12-31 | 佛山市博顿光电科技有限公司 | Method, device and system for monitoring position of substrate in film coating machine and film coating machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1789990A (en) * | 2005-12-01 | 2006-06-21 | 渤海船舶重工有限责任公司 | Automatic online detection method for defects on upper and lower surfaces during steel plate pretreatment process |
| US20130286396A1 (en) * | 2010-12-28 | 2013-10-31 | Olympus Corporation | Inspection device |
| CN103759644A (en) * | 2014-01-23 | 2014-04-30 | 广州市光机电技术研究院 | Separating and refining type intelligent optical filter surface defect detecting method |
| CN104713885A (en) * | 2015-03-04 | 2015-06-17 | 中国人民解放军国防科学技术大学 | Structured light-assisted binocular measuring method for on-line detection of PCB |
| CN105842885A (en) * | 2016-03-21 | 2016-08-10 | 凌云光技术集团有限责任公司 | Liquid crystal screen defect layered positioning method and device |
| CN206684071U (en) * | 2017-04-20 | 2017-11-28 | 广东振华科技股份有限公司 | A kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate |
-
2017
- 2017-04-20 CN CN201710259666.2A patent/CN106872488A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1789990A (en) * | 2005-12-01 | 2006-06-21 | 渤海船舶重工有限责任公司 | Automatic online detection method for defects on upper and lower surfaces during steel plate pretreatment process |
| US20130286396A1 (en) * | 2010-12-28 | 2013-10-31 | Olympus Corporation | Inspection device |
| CN103759644A (en) * | 2014-01-23 | 2014-04-30 | 广州市光机电技术研究院 | Separating and refining type intelligent optical filter surface defect detecting method |
| CN104713885A (en) * | 2015-03-04 | 2015-06-17 | 中国人民解放军国防科学技术大学 | Structured light-assisted binocular measuring method for on-line detection of PCB |
| CN105842885A (en) * | 2016-03-21 | 2016-08-10 | 凌云光技术集团有限责任公司 | Liquid crystal screen defect layered positioning method and device |
| CN206684071U (en) * | 2017-04-20 | 2017-11-28 | 广东振华科技股份有限公司 | A kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473179A (en) * | 2019-07-30 | 2019-11-19 | 上海深视信息科技有限公司 | A kind of film surface defects detection method, system and equipment based on deep learning |
| CN110473179B (en) * | 2019-07-30 | 2022-03-25 | 上海深视信息科技有限公司 | Method, system and equipment for detecting surface defects of thin film based on deep learning |
| CN111242902A (en) * | 2020-01-02 | 2020-06-05 | 天津瑟威兰斯科技有限公司 | Method, system and equipment for identifying and detecting parts based on convolutional neural network |
| CN112102255A (en) * | 2020-08-21 | 2020-12-18 | 杭州培慕科技有限公司 | Intelligent defect rating method based on X-ray imaging image in industrial scene |
| CN112102255B (en) * | 2020-08-21 | 2024-01-23 | 杭州培慕科技有限公司 | Intelligent defect grading method based on X-ray imaging image in industrial scene |
| CN112730452A (en) * | 2020-12-22 | 2021-04-30 | 苏州京浜光电科技股份有限公司 | Method for detecting surface defects of optical filter |
| CN113865483A (en) * | 2021-09-14 | 2021-12-31 | 佛山市博顿光电科技有限公司 | Method, device and system for monitoring position of substrate in film coating machine and film coating machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106872488A (en) | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device | |
| TWI603074B (en) | Optical film defect detection method and system thereof | |
| CN112352149A (en) | System and method for automatically analyzing air samples | |
| CN102854192B (en) | Method for detecting apple surface defect based on apple surface defect detecting system | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN103761529A (en) | Open fire detection method and system based on multicolor models and rectangular features | |
| CN109946303A (en) | Check device and method | |
| CN111047655A (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
| CN109856156A (en) | A kind of display panel tiny flaw determination method and device based on AOI | |
| CN102221559A (en) | Online automatic detection method of fabric defects based on machine vision and device thereof | |
| CN105046700A (en) | Brightness correction and color classification-based fruit surface defect detection method and system | |
| CN103759644B (en) | A kind of separation refinement intelligent detecting method of optical filter blemish | |
| CN110070526A (en) | Defect inspection method based on the prediction of deep neural network temperature figure | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN112394064A (en) | Point-line measuring method for screen defect detection | |
| WO2023168972A1 (en) | Linear array camera-based copper surface defect detection method and apparatus | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN112819844A (en) | Image edge detection method and device | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN108195847A (en) | A kind of relief pattern Online Video detection device and its detection method | |
| CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
| CN113962929A (en) | Photovoltaic cell assembly defect detection method and system and photovoltaic cell assembly production line | |
| CN206684071U (en) | A kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170620 |
|
| WD01 | Invention patent application deemed withdrawn after publication |