CN109001213A - A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method - Google Patents
A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method Download PDFInfo
- Publication number
- CN109001213A CN109001213A CN201810799385.0A CN201810799385A CN109001213A CN 109001213 A CN109001213 A CN 109001213A CN 201810799385 A CN201810799385 A CN 201810799385A CN 109001213 A CN109001213 A CN 109001213A
- Authority
- CN
- China
- Prior art keywords
- image
- reel
- substrate
- defect
- flexible
- 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
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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention discloses a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method, comprising: (1) carries out optical imagery acquisition to image by optical imagery acquisition system；(2) all image mosaics after the completion of shooting are formed by complete flexibility IC substrate image by image co-registration；(3) exterior substrate parameter detecting is carried out to flexible IC substrate image.Exterior substrate parameter detecting of the invention acquires bands of a spectrum first with high light spectrum image-forming technology and analyzes bands of a spectrum, can detect bump mark, scuffing/scratch and defect of damaging；Secondly image is smoothly pre-processed, removes noise；Image is acquired again and is converted to gray level image after fusion treatment；Then oxide regions and appearance color defect are detected by automatic clustering method；Contamination and foreign matter defect are detected finally by Edge Gradient Feature method.The present invention solves the detection problem of the apparent parameter in flexible IC substrate reel-to-reel production process.
Description
Technical field
The present invention relates to the detection technique fields of flexible IC substrate, and in particular to outside a kind of reel-to-reel ultrathin flexible IC substrate
See detection method.
Background technique
Flexible IC substrate has a wide range of applications in many industries, mechanical, electrical including car industry, military/aerospace, calculating
Letter, medical treatment and consumer products etc..Flexible IC substrate use demand all over the world is increasing year by year, and most important application is
On mobile phone and other handheld communications and computer equipment (such as PDA).Since flexible IC substrate belongs to high density ultra thin substrate,
So higher to various aspects technical requirements.Reel-to-reel ultrathin flexible IC substrate is high-volume production flexible printed circuit (FPW)
Technique, equipment, design, in terms of high investment, to reach stringent process control and low labor cost, have as far as possible
Few operation and the advantages of big output, so the detection to its apparent parameter is particularly important.And research of the China to flexible IC substrate
Less, the existing stage does not find the pertinent literature in relation to the detection of flexibility IC exterior substrate.So China is to high density flexible
The research of IC substrate is also in a primary stage.
Summary of the invention
It is an object of the invention to overcome deficiencies of the prior art, a kind of reel-to-reel ultrathin flexible IC base is provided
Plate appearance detecting method solves the apparent parameter detection problem in flexible IC substrate reel-to-reel production process.
The purpose of the present invention is realized at least through one of following technical solution.
A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method comprising:
(1) optical imagery acquisition is carried out to image by optical imagery acquisition system；
(2) all image mosaics after the completion of shooting are formed by complete flexibility IC substrate image by image co-registration；
(3) exterior substrate parameter detecting is carried out to flexible IC substrate image.
Further, step (1) the optical imagery acquisition system includes that optical imaging system and metallography microscope imaging are adopted
Collecting system, wherein optical imaging system acquires flexibility IC substrate by high light spectrum image-forming technology while shooting, collecting process
Bands of a spectrum；Micro-imaging acquisition system is completed by camera shooting while moving stage.
Further, step (3) specifically includes:
(3.1) high light spectrum image-forming technology is used, for detecting bump mark, scuffing/scratch and defect of damaging；
(3.2) image smoothing pre-processes, and using Gaussian filter, removes noise；
(3.3) color image gray processing removes redundant color spatial information；
(3.4) automatic cluster, for detecting oxidation and appearance color defect；
(3.5) Edge Gradient Feature, for detecting contamination and foreign matter defect.
Further, step (3.4) specifically includes:
The two-dimensional histogram of (3.4.1) calculating image: setting background for yellow and black, other colors are set as target,
Construction pixel can establish two dimensional gray histogram to the subordinating degree function of target and background in the picture limit of corresponding target and background
Figure；
(3.4.2) seeks clusters number K value: since normal flexibility IC substrate color only has black background and yellow route, institute
Centainly it is more than or equal to 2 with the K value of automatic cluster number；
The judgement of (3.4.3) oxidation and appearance color: if K=2, determine flexibility IC substrate non-oxidation and appearance color defect；
If K > 2, determine that flexibility IC substrate has oxidation or appearance color defect.
Further, step (3.5) specifically includes:
The detection of (3.5.1) edge feature: the side merged based on wavelet modulus maxima with the grey value mathematical morphology of improvement is used
Edge detection method carries out edge feature detection；
(3.5.2) region shape determines: can determine whether there is contamination or foreign matter defect, institute according to the shape that edge detection goes out
Stating contamination includes oil stain, glue mark, the finger marking.
Further, the detective operators for improving grey value mathematical morphology are first to carry out opening operation reflation fortune to image
It calculates；Secondly image first closed operation is carried out to corrode again；It is poor that finally the image after the first step and second step operation is made.
Further, the step (2) is that the image after acquiring carries out fusion treatment.Since image is to pass through high-resolution
Rate metallography microscope imaging system acquisition, so whole Image Acquisition of flexibility IC substrate is merged later by shooting multiple images
It forms.Therefore the purpose is to have which kind of defect to lay the groundwork for detection flexibility IC substrate.
Further, the purpose of the step (3) is outer in the production process of system solution flexibility IC substrate reel-to-reel
See parameter detecting.Including high light spectrum image-forming technology, image smoothing pretreatment, color image gray processing, automatic cluster and side
Edge feature extraction.
Further, in step (3.1) described high light spectrum image-forming technology, due to the appearance of reel-to-reel ultrathin flexible IC substrate
Detection include bump mark, scuffing/scratch, contamination, foreign matter, oxidation, fold/wrinkle, damage, appearance color, wherein bump mark, draw
Wound/scratch and the grating beam splitting principle progress optical detection being suitble to using high light spectrum image-forming technology of damaging.Grating beam splitting principle are as follows:
In classical physics, when light wave passes through the barrier of slit, aperture or disk etc, difference can occur for the light of different wave length
The curved scattered propagation of degree, then diffraction light splitting is carried out by grating, form a bands of a spectrum.One-dimension information i.e. in space passes through camera lens
After slit, the light of different wave length is according to different degrees of curved scattered propagation, then each point on one dimensional image, by grating into
The light splitting of row diffraction, forms a bands of a spectrum, is irradiated on detector, each location of pixels on detector and intensity characterization spectrum and
Intensity.The corresponding spectral coverage of one point, a line then corresponds to a spectrum face, therefore it is on the line of one, space that detector is imaged every time
Spectral information, pass through machinery again and push away to obtain space two-dimension image and sweep, the image and spectroscopic data for completing entire plane are adopted
Collection.Can be distinguished by bands of a spectrum bump mark, scratch scratch, fold wrinkle, the crackled defect of appearances such as damage.
Further, during described image smoothly pre-processes, mainly image denoising is handled, and generally uses Gaussian smoothing low pass
Filter removes picture noise.Keep image smoother, and more accurate in automatic cluster and Edge Gradient Feature, thus smart
Standard determines whether open defect.
Further, in the color image gray processing.Since flexible IC substrate only has black background and yellow copper wire, institute
The RGB color image of script triple channel can be reduced to single pass gray level image with color image gray processing, can made original
3 byte storage images are needed, 1 byte is now only needed, reduces the occupied space of image.Reach removal redundant color space letter
The purpose of breath saves the time for subsequent operation.
Further, the step (3.5) is stain and foreign matter defect using the detection of Edge Gradient Feature method.The production of contamination
Product characteristic refers to that there are oil stain, glue mark, finger marking etc. in copper-clad plate surface.It is external that the product characteristic of foreign matter refers to that copper-clad plate surface has
Object.These are the depth of substrate color on the main influence of flexible IC substrate.Its detailed step is as follows:
The detection of I edge feature；Use the edge detection merged based on wavelet modulus maxima with the grey value mathematical morphology of improvement
Method.Wherein, grey value mathematical morphology has erosion operation, dilation operation, opening operation and closed operation.Improve ash value mathematical morphology
Detective operators be first to image carry out the operation of opening operation reflation；Secondly image first closed operation is carried out to corrode again；Finally will
It is poor that image after the first step and second step morphology operations is made.
II region shape determines；According to edge detection go out shape can determine whether exist stain (including oil stain, glue mark,
The finger marking) or foreign matter defect.
Compared with prior art, the invention has the advantages that and effect:
(1) present invention physical imperfection that has detected flexible IC substrate quick and lossless by optical imaging system.
(2) present invention accelerates the detection speed of oxidation and appearance color defects detection using automatic clustering method.
(3) present invention is formed a prompt judgement using Edge Gradient Feature method, and whether there is or not stain and foreign matter defect.
(4) present invention has an important breakthrough to flexible IC substrate during manufacturing process, improves flexible IC
The production efficiency of substrate.
Detailed description of the invention
Fig. 1 is the flow chart of optical imagery acquisition system in embodiment.
Fig. 2 is the flow chart of the image fusion system in embodiment.
Fig. 3 is exterior substrate parameter detecting system flow chart in embodiment.
Fig. 4 is automatic clustering method flow chart in embodiment.
Specific embodiment
With reference to the accompanying drawing and specific embodiment, implementation of the invention is described further, but implementation of the invention
It is without being limited thereto with protecting, if it is noted that the following process or parameter for having not special detailed description, is those skilled in the art
Member can refer to the prior art understand or realize.
A kind of ultrathin flexible IC exterior substrate detection system of the present embodiment mainly includes three parts: (1) optical imagery
Acquisition system；(2) image fusion system；(3) exterior substrate parameter detecting system.Wherein optical imagery acquisition system includes optics
Imaging system and metallography microscope imaging acquisition system.The software development kit of high light spectrum image-forming technology can be embedded in camera, i.e. phase
Machine acquires bands of a spectrum while shooting process and detects the physical imperfection of flexible IC substrate, is flexible IC exterior substrate detection system
The first step and subsequent image processing success key.It can avoid fortune if acquiring again after objective table movement is stablized
Dynamic model paste or flating phenomenon, the effect of this image is preferable, and the detection of physical imperfection is more acurrate.Optical imagery acquisition system
Flow chart it is as shown in Fig. 1.The basic operation of the system is relevant parameter and the current location for first setting camera；Secondly it advises
Pull the acquisition path of article carrying platform, i.e., article carrying platform is needed from where where be moved to could be complete Image Acquisition
It is whole；Then moving stage is shot again after stablizing again for camera shooting, and high light spectrum image-forming technology acquires bands of a spectrum while shooting；Most
Judge whether objective table is moved to set destination afterwards, the acquisition of image is completed if reaching, otherwise continues Image Acquisition
Operation.
Fig. 2 is image fusion system flow chart.The purpose of image fusion system be will occur in collection process blur motion,
The image of situations such as distortion or folding first carries out correction process；By treated, image splices again, obtains complete flexibility
IC substrate；The apparent parameter of flexibility IC substrate image could be detected after so that image is normally identified.
Fig. 3 is flexibility IC exterior substrate parameter detecting system flow chart.Specially bands of a spectrum are analyzed first, are detected recessed
Convex epirelief, scuffing/scratch and defect of damaging；Secondly image is smoothly pre-processed, generally using Gaussian filter to figure
As being smoothed, there is decrease of noise functions；Gray level image is acquired and be converted to after fusion treatment to image again, can be made
Originally need 3 bytes for storing image, and existing needs 1 byte, reduces the occupied space of image；Then by automatic
Clustering method detection oxidation and appearance color defect；It is stain and foreign matter defect finally by the detection of Edge Gradient Feature method.
Fig. 4 is automatic clustering method flow chart.The two-dimensional histogram of image is calculated first.Yellow and black are set as carrying on the back
Scape, other colors are set as target, degree of membership of the construction pixel to target and background in the picture limit of corresponding target and background
Function can establish two-dimensional gray histogram.
The present embodiment is using automatic clustering method detection oxide regions and appearance color defect.The product characteristic of oxidation refers to
There is visibility rust staining on copper-clad plate surface.Flexible IC substrate image is made of black background and yellow copper wire, face in copper oxidation process
The color color that gradually reddens from yellow turns black again, so flexibility IC substrate is oxidized and can be determined with the variation of color.Appearance color
Product characteristic refer to copper-clad plate copper face and there is color difference in the face PI in same volume.Its detailed step are as follows:
I calculates the two-dimensional histogram of image.Background is set by yellow and black, other colors are set as target, in corresponding mesh
Construction pixel can establish two-dimensional gray histogram to the subordinating degree function of target and background in the picture limit of mark and background.
II seeks clusters number K value.It is fitted with parabola, clusters number K is determined roughly by wave crest number.But by
Situations such as there may be noises in image sets so the probability for falling in and putting under envelope parabola need to be calculated first if probability is less than
Definite valuet, then can determine that the value under the wave crest is noise.WhereintIt can be determined in advance by the training to image.Due to normal soft
Property IC substrate color is fairly simple, only black background and yellow route, so the K value of automatic cluster number is centainly more than or equal to
2。
The judgement of III oxidation and appearance color.If K=2, flexibility IC substrate non-oxidation and appearance color defect are determined.If
K > 2 determine that flexibility IC substrate has oxidation or appearance color defect.
Claims (6)
1. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method, characterized by comprising:
(1) optical imagery acquisition is carried out to image by optical imagery acquisition system；
(2) all image mosaics after the completion of shooting are formed by complete flexibility IC substrate image by image co-registration；
(3) exterior substrate parameter detecting is carried out to flexible IC substrate image.
2. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method according to claim 1, it is characterised in that step
(1) the optical imagery acquisition system includes optical imaging system and metallography microscope imaging acquisition system, wherein optical imagery system
System acquires the bands of a spectrum of flexibility IC substrate by high light spectrum image-forming technology while shooting, collecting process；Micro-imaging acquisition system
It is completed by camera shooting while moving stage.
3. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method according to claim 1, it is characterised in that step
(3) it specifically includes:
(3.1) high light spectrum image-forming technology is used, for detecting bump mark, scuffing/scratch and defect of damaging；
(3.2) image smoothing pre-processes, and using Gaussian filter, removes noise；
(3.3) color image gray processing removes redundant color spatial information；
(3.4) automatic cluster, for detecting oxidation and appearance color defect；
(3.5) Edge Gradient Feature, for detecting contamination and foreign matter defect.
4. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method according to claim 3, which is characterized in that step
(3.4) it specifically includes:
The two-dimensional histogram of (3.4.1) calculating image: setting background for yellow and black, other colors are set as target,
Construction pixel can establish two dimensional gray histogram to the subordinating degree function of target and background in the picture limit of corresponding target and background
Figure；
(3.4.2) seeks clusters number K value: since normal flexibility IC substrate color only has black background and yellow route, institute
Centainly it is more than or equal to 2 with the K value of automatic cluster number；
The judgement of (3.4.3) oxidation and appearance color: if K=2, determine flexibility IC substrate non-oxidation and appearance color defect；
If K > 2, determine that flexibility IC substrate has oxidation or appearance color defect.
5. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method according to claim 3, which is characterized in that step
(3.5) it specifically includes:
The detection of (3.5.1) edge feature: the side merged based on wavelet modulus maxima with the grey value mathematical morphology of improvement is used
Edge detection method carries out edge feature detection；
(3.5.2) region shape determines: can determine whether there is contamination or foreign matter defect, institute according to the shape that edge detection goes out
Stating contamination includes oil stain, glue mark, the finger marking.
6. a kind of reel-to-reel ultrathin flexible IC exterior substrate detection method according to claim 5, which is characterized in that described
The detective operators for improving grey value mathematical morphology are first to carry out the operation of opening operation reflation to image；Secondly image is first closed
Operation is corroded again；It is poor that finally the image after the first step and second step operation is made.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810799385.0A CN109001213B (en) | 2018-07-19 | 2018-07-19 | Reel-to-reel ultrathin flexible IC substrate appearance detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810799385.0A CN109001213B (en) | 2018-07-19 | 2018-07-19 | Reel-to-reel ultrathin flexible IC substrate appearance detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109001213A true CN109001213A (en) | 2018-12-14 |
| CN109001213B CN109001213B (en) | 2021-08-10 |
Family
ID=64596930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810799385.0A Active CN109001213B (en) | 2018-07-19 | 2018-07-19 | Reel-to-reel ultrathin flexible IC substrate appearance detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109001213B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110118786A (en) * | 2019-05-07 | 2019-08-13 | 鲁班嫡系机器人（深圳）有限公司 | Detection method, detection device and industrial equipment |
| CN113052829A (en) * | 2021-04-07 | 2021-06-29 | 深圳市磐锋精密技术有限公司 | Mainboard AOI detection method based on Internet of things |
| CN114419034A (en) * | 2022-03-16 | 2022-04-29 | 深圳市杰美特科技股份有限公司 | Automatic detection method, system and medium for intelligent wearable silica gel material |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913468A (en) * | 2014-03-31 | 2014-07-09 | 湖南大学 | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line |
| WO2016043397A1 (en) * | 2014-09-16 | 2016-03-24 | 한화테크윈 주식회사 | Glass defect detection method and apparatus using hyperspectral imaging technique |
| CN107064166A (en) * | 2016-01-13 | 2017-08-18 | Ap系统股份有限公司 | Dispose object analysis device, processing unit and disposal object analysis method |
| CN107369176A (en) * | 2017-07-14 | 2017-11-21 | 华南理工大学 | A kind of flexible IC substrates oxidation area detection system and method |
| CN107462587A (en) * | 2017-08-31 | 2017-12-12 | 华南理工大学 | A kind of the precise vision detecting system and method for flexible IC substrates bump mark defect |
-
2018
- 2018-07-19 CN CN201810799385.0A patent/CN109001213B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913468A (en) * | 2014-03-31 | 2014-07-09 | 湖南大学 | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line |
| WO2016043397A1 (en) * | 2014-09-16 | 2016-03-24 | 한화테크윈 주식회사 | Glass defect detection method and apparatus using hyperspectral imaging technique |
| CN107064166A (en) * | 2016-01-13 | 2017-08-18 | Ap系统股份有限公司 | Dispose object analysis device, processing unit and disposal object analysis method |
| CN107369176A (en) * | 2017-07-14 | 2017-11-21 | 华南理工大学 | A kind of flexible IC substrates oxidation area detection system and method |
| CN107462587A (en) * | 2017-08-31 | 2017-12-12 | 华南理工大学 | A kind of the precise vision detecting system and method for flexible IC substrates bump mark defect |
Non-Patent Citations (2)
| Title |
|---|
| JOSHUA D. CALDWELL ET AL : "Luminescence Imaging of Extended Defects in SiC via Hyperspectral Imaging", 《MATERIALS SCIENCE FORUM》 * |
| 孙晓婷: "PCB视觉检测系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110118786A (en) * | 2019-05-07 | 2019-08-13 | 鲁班嫡系机器人（深圳）有限公司 | Detection method, detection device and industrial equipment |
| CN113052829A (en) * | 2021-04-07 | 2021-06-29 | 深圳市磐锋精密技术有限公司 | Mainboard AOI detection method based on Internet of things |
| CN114419034A (en) * | 2022-03-16 | 2022-04-29 | 深圳市杰美特科技股份有限公司 | Automatic detection method, system and medium for intelligent wearable silica gel material |
| CN114419034B (en) * | 2022-03-16 | 2022-07-12 | 深圳市杰美特科技股份有限公司 | Automatic detection method, system and medium for intelligent wearable silica gel material |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109001213B (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112927189B (en) | Edge reflection light spot eliminating method in visual inspection of surface flaws of electroplated workpiece | |
| CN111833306B (en) | Defect detection method and model training method for defect detection | |
| Huang et al. | HRIPCB: a challenging dataset for PCB defects detection and classification | |
| CN112308832B (en) | Bearing quality detection method based on machine vision | |
| CN108280822A (en) | The detection method and device of screen cut | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| CN108876768B (en) | Shadow defect detection method for light guide plate | |
| JP5929238B2 (en) | Image inspection method and image inspection apparatus | |
| CN107369176B (en) | System and method for detecting oxidation area of flexible IC substrate | |
| CN109001213A (en) | A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method | |
| CN115082451B (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN109685760A (en) | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| CN113034474A (en) | Test method for wafer map of OLED display | |
| CN105741244A (en) | Method for removing shadows and halos under weak light through indoor polling robot | |
| JP2009259036A (en) | Image processing device, image processing method, image processing program, recording medium, and image processing system | |
| CN116109637B (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
| CN116503388A (en) | Defect detection method, device and storage medium | |
| CN114417993A (en) | Scratch detection method based on deep convolutional neural network and image segmentation | |
| CN113609984A (en) | Pointer instrument reading identification method and device and electronic equipment | |
| Ma et al. | An automatic detection method of Mura defects for liquid crystal display | |
| CN114037682A (en) | Two-dimensional automatic detection method for optical element surface defects | |
| CN115100104A (en) | Defect detection method, device and equipment for glass ink area and readable storage medium | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN110349129B (en) | Appearance defect detection method for high-density flexible IC 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |