CN109211917A - A kind of general complex surface defect inspection method - Google Patents
A kind of general complex surface defect inspection method Download PDFInfo
- Publication number
- CN109211917A CN109211917A CN201810947943.3A CN201810947943A CN109211917A CN 109211917 A CN109211917 A CN 109211917A CN 201810947943 A CN201810947943 A CN 201810947943A CN 109211917 A CN109211917 A CN 109211917A
- Authority
- CN
- China
- Prior art keywords
- image
- product
- checked
- master pattern
- complex 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000007547 defect Effects 0.000 title claims abstract description 28
- 238000007689 inspection Methods 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000005286 illumination Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 12
- 238000013459 approach Methods 0.000 claims abstract description 9
- 230000005477 standard model Effects 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G01N21/8851—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
Abstract
The present invention relates to a kind of general complex surface defect inspection methods, comprising the following steps: Step 1: building master pattern collection；Step 2: acquiring the image of product to be checked；Step 3: being pre-processed to the image of product to be checked；Step 4: extracting image key points；Step 5: reference standard model, is the image of infinite approach master pattern by the Image Adjusting of product to be checked, generates the test model of product to be checked；Step 6: being detected by image comparison technology contrast standard model and test model realization to defect；Step 7: output test result.To the stability requirement of illumination without so harsh, acquisition image and processing image distribute method of the invention automatically, can quickly, accurate, steadily detection of complex surface all kinds of defects, it is alternative or even surmount artificial detection.
Description
Technical field
The invention discloses a kind of general complex surface defect inspection methods, belong to machine vision imaging, defects detection skill
Art field.
Background technique
In recent years, with the arrival in industrial 4.0 epoch, the speed that industrial technology is changed is getting faster, pushes increasingly
More conventionally manufactured industries changes to intelligence manufacture and automated production manufacture direction.
Manufacturing enterprise can all face Quality Detection problem, and past manufacturing works generally use the mode of artificial detection, but
With the raising of production technology and the development of society, human cost continues to increase, and manual detection efficiency is low, fatiguability, subjectivity
The drawbacks such as property is big are also gradually exposed, and are increasingly difficult to meet enterprise demand.
To improve competitiveness, reducing cost, raising product yield and quality stability, replaced manually with machine vision technique
Method becomes a kind of development trend for surface defects detection, because mechanical vision inspection technology has 100% full inspection, never tired
The advantages such as clear, the differentiation detection of labor, standard.
NI Vision Builder for Automated Inspection refers to that will be ingested target by machine vision product (i.e. image-pickup device) is converted into figure
As signal, sends dedicated image processing system to, obtain the shape information of target subject, according to pixel distribution and brightness, face
The information such as color, are transformed into digitized signal；Picture system carries out various operations to extract clarification of objective, in turn to these signals
The device action at scene is controlled according to the result of differentiation.
At present the similar NI Vision Builder for Automated Inspection or method that occurs in the industry generally comprise lighting system, image capturing system,
Algorithm process system, kinetic control system etc..In order to guarantee that the validity of whole system, lighting system are needed for different products
Corresponding lighting device is selected, while to guarantee the stability of lighting device, to guarantee to reach best using effect.But
In practical application in industry, it is difficult to go frequently to replace lighting device for different product types, because will cause cost in this way
Effective run time that is excessively high or influencing vision system.Under the premise of having configured lighting system, but need to camera lens into
Row accurate alignment, reduces influence of the image deformation to detection, and requirement of the NI Vision Builder for Automated Inspection to camera lens is harsher.Algorithm
Processing system needs to be corresponding to it using multiple groups configuration parameter for different product types, and the operation difficulty of operator is larger.
Problem above causes similar at present NI Vision Builder for Automated Inspection or method applicability poor, including to different model product
Difference characteristic (difference of component, defect classification and state etc.) adaptability it is poor, suitable to equipment operation external environment
Answering property is poor, equipment debugging and operability are poor, in the case where comprehensively considering the indexs such as inspection rate to most of product itself
There is the defects detection effect of deformation undesirable；Such as the methods of " template matching ", " background modeling " used by usually are general
Universal process method in meaning can not yet set up the valid model for test object.
Summary of the invention
It in order to solve the above-mentioned technical problem, can be fast the invention proposes a kind of general complex surface defect inspection method
Speed, all defect for precisely, steadily detecting complex surface, achieve the purpose that substitution even surmounts artificial detection.
In the present invention, complex surface is primarily referred to as the surface of Non-smooth surface, is the product surface with various assemblies.
The technical solution adopted by the present invention to solve the technical problems are as follows:
A kind of general complex surface defect inspection method, comprising the following steps:
Step 1: building master pattern collection；
Step 2: acquiring the image of product to be checked；
Step 3: being pre-processed to the image of product to be checked；
Step 4: extracting image key points；
Step 5: reference standard model, is the image of infinite approach master pattern by the Image Adjusting of product to be checked, generates
The test model of product to be checked；
Step 6: being detected by image comparison technology contrast standard model and test model realization to defect；
Step 7: output test result.
Further, in step 1, the process of master pattern collection is constructed are as follows:
Select a small amount of random sample of a kind of product；
The image of collecting sample；
Principal component analysis is carried out to the image of sample, the dimension of data is reduced, makes to reduce association between image data to the greatest extent；
Extract the primary focus for capableing of representative image；
Corresponding model is generated according to the primary focus of each image, and by Gauss modeling algorithm, each model is raw
At final master pattern；
It establishes master pattern collection and inspection software is written.
Further, above-mentioned steps two are automatically performed to step 7 by a detection device.
Further, the detection device includes illumination system, image capturing system, image processing system, motion control
System.
Further, in step 2, the image of product to be checked is acquired by an image capturing system.
Further, the compatible most of camera models of described image acquisition system, when needing replacing camera, the detection
Device can Adaptive matching camera, without doing other configurations.
Further, it in step 3, is carried out using image of the frequency domain filtering technology to collected product to be checked general
Denoising, operated using grayscale equalization, weaken the even influence of uneven illumination.
Further, in step 5, use " minimum energy matching " technology adaptively by the Image Adjusting of product to be checked for
The image of infinite approach master pattern, to generate the test model of product to be checked.
Further, when using " minimum energy matching " technical treatment image, using master pattern key point as deformation control
Amount processed, restrains according to energy, and under the traction of key point, image changes from trend master pattern, final to restrain and infinitely approach
Master pattern, to generate the test model of product to be checked.
Illumination system is used to provide the illumination of testing product needs, since the detection algorithm of the detection device considers
Influence of the illumination to detection effect increases algorithm in algorithm for design to the adaptivity of light change, therefore the detection fills
The stability requirement to illumination is set without so harshness, is adapted to a certain range of light intensity variation.
The detection device is only responsible for acquisition using acquisition image and the processing automatic distribution principle of image, image capturing system
Image, image processing system distribute a certain arithmetic element and remove processing image；When multiple images acquisition system works at the same time, image
Processing system is responsible for scheduling, allows each arithmetic element to be involved in operation, avoids the wasting of resources.
Kinetic control system is responsible for carrying product to be checked, while image processing system being cooperated to do corresponding movement, such as triggers
Image capturing system acquires image and lighting system switching.
Have following technical effect that the stability requirement to illumination is no so harsh using technical solution of the present invention,
Acquisition image and processing image distribute automatically, can quickly, accurate, steadily detection of complex surface all kinds of defects, it is alternative
Even surmount artificial detection.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, with presently preferred embodiments of the present invention and attached drawing will be cooperated to be described in detail below.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of one embodiment of general complex surface defect inspection method of the present invention；
Fig. 2 is the flow diagram that master pattern collection is constructed in the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Referring to Fig. 1, for according to a kind of process of general complex surface defect inspection method of one embodiment of the present of invention
Schematic diagram, specifically includes the following steps:
Step 1: building master pattern collection, referring specifically to Fig. 2, for the process signal for constructing master pattern collection in the present invention
Figure, comprising the following steps: select a small amount of random sample of a kind of product, the image of collecting sample leads the image of sample
Constituent analysis reduces the dimension of data, makes to reduce association between image data to the greatest extent, extracts the chief for capableing of representative image
Point generates corresponding model according to the primary focus of each image, and by Gauss modeling algorithm, each model is generated final
Master pattern, establish master pattern collection and inspection software be written.
The step of constructing master pattern collection is completed offline, and writes data into inspection software, subsequent step 2 to step
Seven be on-line checking treatment process, and the master pattern collection by importing off-line phase building works.Below to on-line checking
The step for the treatment of process two to step 7 is specifically described.
Step 2 is automatically performed to step 7 by a detection device, and the detection device includes that illumination system, image are adopted
Collecting system, image processing system, kinetic control system.Illumination system is used to provide the illumination of testing product needs, due to described
The detection algorithm of detection device considers influence of the illumination to detection effect, and algorithm is increased in algorithm for design and is become to illumination
The adaptivity changed, therefore the detection device is no to the stability requirement of illumination so harsh, is adapted to a certain range of
Light intensity variation.The detection device is only responsible for adopting using acquisition image and the processing automatic distribution principle of image, image capturing system
Collect image, image processing system distributes a certain arithmetic element and removes processing image；When multiple images acquisition system works at the same time, figure
As processing system is responsible for scheduling, allows each arithmetic element to be involved in operation, avoid the wasting of resources.Kinetic control system is responsible for carrying
Product to be checked, while image processing system being cooperated to do corresponding movement, such as trigger image capturing system acquisition image and illumination
System switching.
In step 2, the image of product to be checked is acquired by an image capturing system, described image acquisition system is compatible
Most of camera models, when needing replacing camera, the detection device can Adaptive matching camera, match without doing other
It sets.
In step 3, the image of product to be checked is pre-processed, using frequency domain filtering technology to collected to be checked
The image of product carries out general denoising, is operated using grayscale equalization, weakens the even influence of uneven illumination.
In step 4, image key points are extracted；
In step 5, reference standard model, using " minimum energy matching " technology adaptively by the image of product to be checked
It is adjusted to the image of infinite approach master pattern, to generate the test model of product to be checked.Using " minimum energy matching "
When technical treatment image, using master pattern key point as shape control amount, restrained according to energy, under the traction of key point, figure
It is final to restrain and infinitely approach master pattern as changing from trend master pattern, to generate the test model of product to be checked.
In step 6, defect is detected by image comparison technology contrast standard model and test model realization.
In step 7, output test result.
The above is only a preferred embodiment of the present invention, it is not intended to restrict the invention, it is noted that for this skill
For the those of ordinary skill in art field, without departing from the technical principles of the invention, can also make it is several improvement and
Modification, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (9)
1. a kind of general complex surface defect inspection method, which comprises the following steps:
Step 1: building master pattern collection；
Step 2: acquiring the image of product to be checked；
Step 3: being pre-processed to the image of product to be checked；
Step 4: extracting image key points；
Step 5: reference standard model, is the image of infinite approach master pattern by the Image Adjusting of product to be checked, generates to be checked
The test model of product；
Step 6: being detected by image comparison technology contrast standard model and test model realization to defect；
Step 7: output test result.
2. a kind of general complex surface defect inspection method according to claim 1, it is characterised in that: in step 1,
Construct the process of master pattern collection are as follows:
Select a small amount of random sample of a kind of product；
The image of collecting sample；
Principal component analysis is carried out to the image of sample, the dimension of data is reduced, makes to reduce association between image data to the greatest extent；
Extract the primary focus for capableing of representative image；
Corresponding model is generated according to the primary focus of each image, and by Gauss modeling algorithm, each model is generated most
Whole master pattern；
It establishes master pattern collection and inspection software is written.
3. a kind of general complex surface defect inspection method according to claim 1, it is characterised in that: the step 2 is extremely
Step 7 is automatically performed by a detection device.
4. a kind of general complex surface defect inspection method according to claim 3, it is characterised in that: the detection device
Including illumination system, image capturing system, image processing system, kinetic control system.
5. a kind of general complex surface defect inspection method according to claim 1, it is characterised in that: in step 2,
The image of product to be checked is acquired by an image capturing system.
6. a kind of general complex surface defect inspection method according to claim 5, it is characterised in that: described image acquisition
The most of camera models of system compatible, when needing replacing camera, the detection device can Adaptive matching camera, without doing
Other configurations.
7. a kind of general complex surface defect inspection method according to claim 1, it is characterised in that: in step 3,
General denoising is carried out using image of the frequency domain filtering technology to collected product to be checked, is grasped using grayscale equalization
Make, weakens the even influence of uneven illumination.
8. a kind of general complex surface defect inspection method according to claim 1, it is characterised in that: in step 5,
Use minimum energy matching technique adaptively by the Image Adjusting of product to be checked for the image of infinite approach master pattern, thus raw
At the test model of product to be checked.
9. a kind of general complex surface defect inspection method according to claim 8, it is characterised in that: using energy level
When small matching technique processing image, using master pattern key point as shape control amount, restrained according to energy, in the traction of key point
Under, image changes from trend master pattern, and it is final to restrain and infinitely approach master pattern, to generate the test mould of product to be checked
Type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947943.3A CN109211917A (en) | 2018-08-20 | 2018-08-20 | A kind of general complex surface defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947943.3A CN109211917A (en) | 2018-08-20 | 2018-08-20 | A kind of general complex surface defect inspection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109211917A true CN109211917A (en) | 2019-01-15 |
Family
ID=64989348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810947943.3A Pending CN109211917A (en) | 2018-08-20 | 2018-08-20 | A kind of general complex surface defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109211917A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160207A (en) * | 2021-05-07 | 2021-07-23 | 北京平恒智能科技有限公司 | Environment self-adaptive product defect detection method based on whiteboard illumination compensation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101049022A (en) * | 2004-10-28 | 2007-10-03 | 康宁股份有限公司 | Inspection system and method for identifying surface and body defects in a glass sheet |
| CN101398393A (en) * | 2007-09-28 | 2009-04-01 | 上海华虹Nec电子有限公司 | Silicon chip product defect analysis method and device |
| US20100021067A1 (en) * | 2006-06-16 | 2010-01-28 | Nobuyuki Otsu | Abnormal area detection apparatus and abnormal area detection method |
| US20130113913A1 (en) * | 2011-11-03 | 2013-05-09 | Pratt & Whitney | System and Method for Data-Driven Automated Borescope Inspection |
| CN105158269A (en) * | 2015-09-29 | 2015-12-16 | 中国科学院上海光学精密机械研究所 | Large-diameter plane optical element defect three-dimensional fast dark field detection device and method |
| CN105405116A (en) * | 2014-09-04 | 2016-03-16 | 南京理工大学 | Stereo matching method based on graph cut |
| CN105424726A (en) * | 2016-01-12 | 2016-03-23 | 苏州富鑫林光电科技有限公司 | Machine vision based light-emitting panel detection method |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN107123105A (en) * | 2017-01-20 | 2017-09-01 | 南京理工大学 | Images match defect inspection method based on FAST algorithms |
-
2018
- 2018-08-20 CN CN201810947943.3A patent/CN109211917A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101049022A (en) * | 2004-10-28 | 2007-10-03 | 康宁股份有限公司 | Inspection system and method for identifying surface and body defects in a glass sheet |
| US20100021067A1 (en) * | 2006-06-16 | 2010-01-28 | Nobuyuki Otsu | Abnormal area detection apparatus and abnormal area detection method |
| CN101398393A (en) * | 2007-09-28 | 2009-04-01 | 上海华虹Nec电子有限公司 | Silicon chip product defect analysis method and device |
| US20130113913A1 (en) * | 2011-11-03 | 2013-05-09 | Pratt & Whitney | System and Method for Data-Driven Automated Borescope Inspection |
| CN105405116A (en) * | 2014-09-04 | 2016-03-16 | 南京理工大学 | Stereo matching method based on graph cut |
| CN105158269A (en) * | 2015-09-29 | 2015-12-16 | 中国科学院上海光学精密机械研究所 | Large-diameter plane optical element defect three-dimensional fast dark field detection device and method |
| CN105424726A (en) * | 2016-01-12 | 2016-03-23 | 苏州富鑫林光电科技有限公司 | Machine vision based light-emitting panel detection method |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN107123105A (en) * | 2017-01-20 | 2017-09-01 | 南京理工大学 | Images match defect inspection method based on FAST algorithms |
Non-Patent Citations (2)
| Title |
|---|
| 夏奇: "基于点模式匹配和能量最小化的模板定位算法", 《华中科技大学学报（自然科学版）》 * |
| 郭斯羽: "《面向检测的图像处理技术》", 31 August 2015, 湖南大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160207A (en) * | 2021-05-07 | 2021-07-23 | 北京平恒智能科技有限公司 | Environment self-adaptive product defect detection method based on whiteboard illumination compensation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107845087B (en) | Method and system for detecting uneven brightness defect of liquid crystal panel | |
| CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
| CN110261410A (en) | A kind of detection device and method of glass lens defect | |
| CN109507192A (en) | A kind of magnetic core detection method of surface flaw based on machine vision | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| JP6208426B2 (en) | Automatic unevenness detection apparatus and automatic unevenness detection method for flat panel display | |
| CN117095005B (en) | Plastic master batch quality inspection method and system based on machine vision | |
| CN104809725A (en) | Cloth defect visual identify detecting device and method | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN116990993B (en) | LCD display panel quality detection method | |
| CN109211917A (en) | A kind of general complex surface defect inspection method | |
| Zhang et al. | Fabric defect detection based on visual saliency map and SVM | |
| CN111161228B (en) | Button surface defect detection method based on transfer learning | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN109584224B (en) | Method for analyzing and displaying X-ray image of casting | |
| CN110376215A (en) | The nonstandard automatic detection device of bearing chamfer and method | |
| CN109859169B (en) | TFT-LCD module white print detection method based on convolutional neural network | |
| CN112861817A (en) | Instrument noise image processing method | |
| CN111626339A (en) | Method for detecting abnormal die cavity of injection molding machine with light shadow and jitter influence resistance | |
| CN104048968A (en) | Industrial processing part automatic defect identification system | |
| CN111145193A (en) | Adaptive global threshold value binarization method | |
| CN110544230A (en) | LED screen inspection method and system based on 5G | |
| JP2014135007A (en) | Flat panel display automatic unevenness detection device and automatic unevenness detection method | |
| CN117252864B (en) | Steel production device smoothness detection system based on identification analysis | |
| CN208026642U (en) | A kind of pad of engine defect detecting device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |