CN107633507A - LCD defect inspection methods based on contour detecting and characteristic matching - Google Patents
LCD defect inspection methods based on contour detecting and characteristic matching Download PDFInfo
- Publication number
- CN107633507A CN107633507A CN201710782328.7A CN201710782328A CN107633507A CN 107633507 A CN107633507 A CN 107633507A CN 201710782328 A CN201710782328 A CN 201710782328A CN 107633507 A CN107633507 A CN 107633507A
- Authority
- CN
- China
- Prior art keywords
- mapping
- contour detecting
- characteristic matching
- lcd
- standard
- 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
Abstract
The invention discloses a kind of LCD defect inspection methods based on contour detecting and characteristic matching, step are as follows：The LCD display image of m width standards is gathered first and is averaging and establishes standard gallery, and renewal picture library is resurveyed per 2min；Then LCD display image to be measured is gathered；Then to standard drawing and treat mapping carry out registration, using the method based on contour detecting and characteristic matching；Then to treating that mapping and standard drawing are weighted average fusion after registration, obtain new treating mapping；Afterwards to treating that mapping and standard drawing carry out local auto-adaptive Threshold segmentation respectively after fusion；Last difference shadow method detection defect, and the type by Minimum Enclosing Rectangle method statistical shortcomings and position.Energy real-time high-precision detection LCD defects of the invention.
Description
Technical field
The present invention relates to LCD display defect detection fields, particularly a kind of LCD based on contour detecting and characteristic matching is lacked
Fall into detection method.
Background technology
Liquid crystal display device is widely used in various household electrical appliance and instrument and meter, achieves tremendous development.Display screen by
In production technology it is numerous and diverse, easily by surrounding environment influence, it is easily produced defect, therefore the detection of LCD display defects is to improving
LCD display production technology and improve its product quality and have great significance.Conventional method has artificial vision-based detection, electricity
Parameter detecting, automatic optics inspection are learned, the above two are generally used to detect gross imperfection, can not be detected for microdefect, tradition
Artificial vision detection in human eye resolution ratio it is not high missing inspection flase drop occurs, subjectivity is big, and it is tired that long-term work can produce vision
Labor causes stability not high, and quality testing precision is difficult to ensure card, can not turn into unified examination criteria.Automatic optics inspection is non-with its
The advantages that contact, high-performance, is able to fast development.Many scholars did research to LCD display defect automatic detections, but largely
In method, some does not overcome illumination effect well, and some is sensitive to image rotation, some requirement measurand background letters
Single, what is had can not detect defect information etc., and detect the defects of close with target background without method substantially.
The core of LCD defects detections is image registration, and registration accuracy more high measurement accuracy is higher, mainly have based on region and
Two methods of feature based, the method for being currently based on feature are most universal.Traditional SIFT algorithms are to image rotation and dimensional variation
Robustness is good, but operand is big, time complexity is high.Speed is exchanged for sacrifice precision based on the SIFT SURF algorithms proposed.Afterwards
Carry out many scholars to be improved on the basis of SIFT and SURF, still, the precision of big multi-method image registration is general, and is applicable
Scope compares limitation；It is not high to the antijamming capability of brightness of image change；The anglec of rotation that can be handled is small；It must all use and go
Except error hiding algorithm, time complexity are high；All method registration process all use affine transformation, and affine transformation is transitting probability
A kind of special circumstances, two-dimensional space rotation and translation can only be handled, if three-dimensional state occurs in the micro- distortion of image, affine transformation will
It can malfunction.
The content of the invention
It is an object of the invention to provide a kind of simple, quick, accuracy rate is high LCD defect inspection methods, meet various
Need the demand in LCD detections market.
The technical solution for realizing the object of the invention is：It is a kind of to be examined based on the LCD defects of contour detecting and characteristic matching
Survey method, comprises the following steps：
Step 1, the LCD display image for gathering m width standards are simultaneously averaging, and are obtained standard form figure, are established standard gallery,
Wherein m is positive integer；
Step 2, collection LCD display image to be measured；
Step 3, the standard form figure of step 1 and step 2 treated that mapping carries out registration, using based on contour detecting and spy
The method for levying matching, obtains treating mapping after registration；
What step 4, standard form figure and step 3 to step 1 obtained treats that mapping carries out fusion treatment, after being merged
Treat mapping；
What step 5, respectively the standard form figure to step 1, step 4 obtained treats that mapping carries out Threshold segmentation, obtains two width
Threshold figure；
Step 6, the two width threshold figures obtained using difference shadow method processing step 5, detect defect.
Further, N >=5 described in step 1.
Further, the collection N width standard drawing described in step 1 and it is averaging, the process needs be repeated once per 2min, updates
Standard gallery.
Further, the method based on contour detecting and characteristic matching, detailed process are as follows in step 3：
(1) step 2 is treated that mapping and standard form totem culture prolong expansion, obtains two w × h rectangular image, and w ≠ h,
Wherein, w is width, and h is height；
(2) (1) is prolonged and treats that mapping carries out global threshold segmentation after expanding, obtain binary map；
(3) contour detecting is carried out to the binary map in (2), removes less than 0.5 × l or more than the profile beyond l, leave figure
As the profile of target area, preliminary profile diagram is saved as, wherein l is the girth of rectangle in (1)；
(4) contour detecting by top layer under is carried out again to the preliminary profile diagram in (3), saves as 2D point sets, and establish
The minimum enclosed rectangle of top layer point set；
(5) analysis calculating is carried out to the minimum enclosed rectangle that (4) obtain, determines itself and the anticlockwise rotation of trunnion axis
Angle absolute value theta and four apex coordinates counterclockwise；
(6) anglec of rotation for treating mapping relative standard's Prototype drawing in four apex coordinate discriminating steps 2 that basis (5) obtains
Spend to be positive/negative, afterwards reselection-θ or 90°- θ treats that mapping carries out affine transformation and obtains preliminary registration figure to step 2；
(7) the preliminary registration figure to (6) and standard form figure carry out the matching of distinguished point based, obtain to be measured after registration
Figure.
Further, fusion treatment in step 4, the method specifically merged using weighted average, formula used are：
B'(M, N)=c1A(M,N)+c2B(M,N)
In formula, A is standard drawing, and B is the mapping for the treatment of after registration, and B ' is to treat mapping after merging, and size is M × N,
Weight coefficient：The present invention chooses c1=0.38, c2=0.62.
Further, Threshold segmentation in step 5 is specifically big using local auto-adaptive Threshold segmentation, its sliding window
Small is 9 × 9.
Compared with the conventional method, its remarkable advantage is the present invention：(1) present invention needs 2min to automatically update standard gallery,
Influence of the illumination variation to testing result is avoided to a certain extent, improves accuracy of detection；(2) examined in the present invention based on profile
Survey and the method for registering of characteristic matching is relative to traditional characteristic matching, speed is faster and precision is higher；(3) adding in the present invention
Weight average fusion is capable of detecting when the defects of approximate with background with local auto-adaptive Threshold segmentation, reduces loss.
Brief description of the drawings
Fig. 1 is the LCD defect inspection method flow charts of the invention based on contour detecting and characteristic matching.
Fig. 2 is the flow chart of the registration process based on contour detecting and characteristic matching in the present invention.
Fig. 3 is the implementation illustration of the LCD defect inspection methods of the invention based on contour detecting and characteristic matching, wherein scheming
(a) it is standard form figure, figure (b) is mapping to be checked, and figure (c) is the mapping for the treatment of after merging, and figure (d) (e) is respectively to scheme (a), (c)
Threshold segmentation figure, figure (f) be defects detection result, figure (g) be defect information statistical result.
Embodiment
Below in conjunction with the accompanying drawings and embodiment is described in further detail to the present invention.
A kind of LCD defect inspection methods based on contour detecting and characteristic matching of the present invention, comprise the following steps：
Step 1, the LCD display image for gathering N width standards are simultaneously averaging, and are obtained standard form figure, are established standard gallery,
Wherein N is positive integer；Described N >=5.Described collection N width standard drawing is simultaneously averaging, and the process needs be repeated once per 2min,
Update standard gallery.
Step 2, collection LCD display image to be measured；
Step 3, the standard form figure of step 1 and step 2 treated that mapping carries out registration, using based on contour detecting and spy
The method for levying matching, obtains treating mapping after registration；Detailed process is as follows：
Step 3-1, step 2 is treated that mapping and standard form totem culture prolong expansion, obtains two w × h rectangular image, and
W ≠ h, wherein, w is width, and h is height；
Step 3-2, step 3-1 is prolonged and treats that mapping carries out global threshold segmentation after expanding, obtain binary map；
Step 3-3, contour detecting is carried out to the binary map in step 3-2, removed less than 0.5 × l or more than the wheel beyond l
Exterior feature, the profile of image target area is left, save as preliminary profile diagram, wherein l is the girth of rectangle in step 3-1；
Step 3-4, the contour detecting by top layer under is carried out again to the preliminary profile diagram in step 3-3, saves as 2D points
Collection, and establish the minimum enclosed rectangle of top layer point set；
Step 3-5, analysis calculating is carried out to the minimum enclosed rectangle that step 3-4 is obtained, determines that it is counterclockwise with trunnion axis
The rotation angle absolute value theta in direction and four apex coordinates counterclockwise；
Step 3-6, mapping relative standard's template is treated in the four apex coordinate discriminating steps 2 obtained according to step 3-5
The anglec of rotation of figure is positive/negative, reselection-θ or 90 afterwards°- θ treats that mapping carries out affine transformation acquisition and tentatively matched somebody with somebody to step 2
Quasi- figure；
Step 3-7, the preliminary registration figure to step 3-6 and standard form figure carry out the matching of distinguished point based, are matched somebody with somebody
Mapping is treated after standard.
What step 4, standard form figure and step 3 to step 1 obtained treats that mapping carries out fusion treatment, after being merged
Treat mapping；Fusion treatment, specifically merged using weighted average, formula used is：
B'(M, N)=c1A(M,N)+c2B(M,N)
In formula, A is standard form figure, and for B to treat mapping after registration, size is that M × N, wherein M and N are positive integer,
B ' is to treat mapping, weight coefficient after merging：
Weight coefficient is preferably：c1=0.38, c2=0.62.
What step 5, respectively the standard form figure to step 1, step 4 obtained treats that mapping carries out Threshold segmentation, obtains two width
Threshold figure；Threshold segmentation, specifically using local auto-adaptive Threshold segmentation, its sliding window size is 9 × 9.
Step 6, the two width threshold figures obtained using difference shadow method processing step 5, detect defect.
Weighted average in the present invention merges is capable of detecting when the defects of approximate with background with local auto-adaptive Threshold segmentation,
Reduce loss.
It is described in more detail below.
With reference to Fig. 1, the LCD defect inspection methods of the invention based on contour detecting and characteristic matching, comprise the following steps：
Step 1, the LCD display image for gathering m width standards are simultaneously averaging, and are obtained standard form figure, are established standard gallery,
The process needs to be repeated once per 2min, updates standard gallery, overcomes the influence of illumination variation；
Step 2, collection LCD display image to be measured；
Step 3, the standard form figure of step 1 and step 2 treated that mapping carries out registration, using based on contour detecting and spy
The method for levying matching, detailed process combination Fig. 2, obtains treating mapping after registration；
What step 4, standard form figure and step 3 to step 1 obtained treats that mapping is weighted average fusion treatment, obtains
Mapping is treated after fusion, formula used is：
B'(M, N)=c1A(M,N)+c2B(M,N)
In formula, A is standard drawing, and B is the mapping for the treatment of after registration, and size is M × N, and B ' is the mapping for the treatment of after merging, and is weighted
Coefficient：The present invention chooses c1=0.38, c2=0.62；
Treat that mapping carries out local auto-adaptive threshold value after step 5, the fusion that the standard drawing to step 1, step 4 obtain respectively
Segmentation, its sliding window size are 9 × 9, obtain two width threshold figures；
The two width threshold figures that step 6, difference shadow method processing step 5 obtain, detect defect, and united with Minimum Enclosing Rectangle method
Count type and the position of defect.
Compared with traditional method, not only speed is fast but also accuracy rate is high for detection method of the invention, and accuracy rate can reach
To 98.667%, there is good application prospect.
It is specifically described with reference to embodiment.
Embodiment
With reference to Fig. 3, method is：
(1) gather and standard form figure is obtained after 10 width standard LCD figures are averaging as schemed (a), be stored in standard gallery；
(2) collection treats mapping as schemed (b)；
(3) method based on contour detecting and characteristic matching is used, registration is carried out to figure (a) and (b), and it is flat by weighting
Figure (c) is obtained after merging, fusion can largely overcome the influence of illumination；
(4) local auto-adaptive Threshold segmentation is carried out respectively to figure (a), (c), obtains figure (d) and (e), the Threshold segmentation side
Method can distinguish any defect substantially, reduce loss；
(6) difference shadow method is carried out to figure (d) and figure (e) and detects defect as schemed (f), and counted and lacked with Minimum Enclosing Rectangle method
Sunken type and position are as schemed (g)；
The inventive method is simple, speed is fast, accuracy rate is high, and accuracy rate can reach 98.667%, meets various needs LCD
The demand in defects detection market, there is good application prospect.
Claims (7)
1. a kind of LCD defect inspection methods based on contour detecting and characteristic matching, it is characterised in that comprise the following steps：
Step 1, the LCD display image for gathering N width standards are simultaneously averaging, and are obtained standard form figure, are established standard gallery, wherein
N is positive integer；
Step 2, collection LCD display image to be measured；
Step 3, the standard form figure of step 1 and step 2 treated that mapping carries out registration, using based on contour detecting and feature
The method matched somebody with somebody, obtain treating mapping after registration；
What step 4, standard form figure and step 3 to step 1 obtained treats that mapping carries out fusion treatment, to be measured after being merged
Figure；
What step 5, respectively the standard form figure to step 1, step 4 obtained treats that mapping carries out Threshold segmentation, obtains two width threshold values
Figure；
Step 6, the two width threshold figures obtained using difference shadow method processing step 5, detect defect.
2. the LCD defect inspection methods according to claim 1 based on contour detecting and characteristic matching, it is characterised in that
N >=5 described in step 1.
3. the LCD defect inspection methods according to claim 1 based on contour detecting and characteristic matching, it is characterised in that
Collection N width standard drawing described in step 1 is simultaneously averaging, and the process needs be repeated once per 2min, updates standard gallery.
4. the LCD defect inspection methods according to claim 1 based on contour detecting and characteristic matching, it is characterised in that
The method based on contour detecting and characteristic matching, detailed process are as follows in step 3：
Step 3-1, step 2 is treated that mapping and standard form totem culture prolong expansion, obtains two w × h rectangular image, and w ≠
H, wherein, w is width, and h is height；
Step 3-2, step 3-1 is prolonged and treats that mapping carries out global threshold segmentation after expanding, obtain binary map；
Step 3-3, contour detecting is carried out to the binary map in step 3-2, removed less than 0.5 × l or more than the profile beyond l,
The profile of image target area is left, saves as preliminary profile diagram, wherein l is the girth of rectangle in step 3-1；
Step 3-4, the contour detecting by top layer under is carried out again to the preliminary profile diagram in step 3-3, saves as 2D point sets, and
Establish the minimum enclosed rectangle of top layer point set；
Step 3-5, analysis calculating is carried out to the minimum enclosed rectangle that step 3-4 is obtained, determines it with trunnion axis counterclockwise
Rotation angle absolute value theta and four apex coordinates counterclockwise；
Step 3-6, mapping relative standard's Prototype drawing is treated in the four apex coordinate discriminating steps 2 obtained according to step 3-5
The anglec of rotation is positive/negative, and reselection-θ or 90 ° of-θ treats that mapping carries out affine transformation and obtains preliminary registration figure to step 2 afterwards；
Step 3-7, the preliminary registration figure to step 3-6 and standard form figure carry out the matching of distinguished point based, after obtaining registration
Treat mapping.
5. the LCD defect inspection methods according to claim 1 based on contour detecting and characteristic matching, it is characterised in that
Fusion treatment in step 4, is specifically merged using weighted average, and formula used is：
B'(M, N)=c1A(M,N)+c2B(M,N)
In formula, A is standard form figure, and B is treats mapping after registration, and size is that M × N, wherein M and N are positive integer, and B ' is
Mapping, weight coefficient are treated after fusion：c2=1-c1。
6. the LCD defect inspection methods according to claim 1 based on contour detecting and characteristic matching, it is characterised in that
Threshold segmentation in step 5, specifically using local auto-adaptive Threshold segmentation, its sliding window size is 9 × 9.
7. the LCD defect inspection methods according to claim 5 based on contour detecting and characteristic matching, it is characterised in that
Weight coefficient c1=0.38, c2=0.62.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710782328.7A CN107633507A (en) | 2017-09-02 | 2017-09-02 | LCD defect inspection methods based on contour detecting and characteristic matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710782328.7A CN107633507A (en) | 2017-09-02 | 2017-09-02 | LCD defect inspection methods based on contour detecting and characteristic matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107633507A true CN107633507A (en) | 2018-01-26 |
Family
ID=61099779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710782328.7A Pending CN107633507A (en) | 2017-09-02 | 2017-09-02 | LCD defect inspection methods based on contour detecting and characteristic matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107633507A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724988A (en) * | 2019-02-01 | 2019-05-07 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of pcb board defect positioning method based on multi-template matching |
| CN110211182A (en) * | 2019-05-31 | 2019-09-06 | 东北大学 | A kind of LCD backlight vision positioning method based on Gray-scale Matching and objective contour |
| CN110689527A (en) * | 2019-09-18 | 2020-01-14 | 北京航空航天大学 | Method, device and equipment for detecting installation state of aircraft cable bracket |
| CN110852989A (en) * | 2019-09-30 | 2020-02-28 | 广州利科科技有限公司 | Quality flaw detection of tile photographed picture |
| CN112147147A (en) * | 2019-06-26 | 2020-12-29 | 杭州海康机器人技术有限公司 | Edge defect detection method, edge defect detection device and quality detection equipment |
| CN112364783A (en) * | 2020-11-13 | 2021-02-12 | 诸暨思看科技有限公司 | Part detection method and device and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663725A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | A visible light and SAR image registration method based on linear features and control points |
| CN103499296A (en) * | 2013-10-21 | 2014-01-08 | 东华大学 | Batch part automatic detection system and method based on machine vision |
| CN106017328A (en) * | 2015-12-17 | 2016-10-12 | 广东正业科技股份有限公司 | Method and device for measuring various types of line widths |
| CN107101584A (en) * | 2017-04-27 | 2017-08-29 | 中国科学院长春光学精密机械与物理研究所 | Ohject displacement measuring method based on image recognition, apparatus and system |
-
2017
- 2017-09-02 CN CN201710782328.7A patent/CN107633507A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663725A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | A visible light and SAR image registration method based on linear features and control points |
| CN103499296A (en) * | 2013-10-21 | 2014-01-08 | 东华大学 | Batch part automatic detection system and method based on machine vision |
| CN106017328A (en) * | 2015-12-17 | 2016-10-12 | 广东正业科技股份有限公司 | Method and device for measuring various types of line widths |
| CN107101584A (en) * | 2017-04-27 | 2017-08-29 | 中国科学院长春光学精密机械与物理研究所 | Ohject displacement measuring method based on image recognition, apparatus and system |
Non-Patent Citations (1)
| Title |
|---|
| 朱炳斐 等: "基于傅里叶梅林变换的LCD显示缺陷检测", 《激光与光电子学进展》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724988A (en) * | 2019-02-01 | 2019-05-07 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of pcb board defect positioning method based on multi-template matching |
| CN109724988B (en) * | 2019-02-01 | 2021-05-18 | 佛山市南海区广工大数控装备协同创新研究院 | PCB defect positioning method based on multi-template matching |
| CN110211182A (en) * | 2019-05-31 | 2019-09-06 | 东北大学 | A kind of LCD backlight vision positioning method based on Gray-scale Matching and objective contour |
| CN110211182B (en) * | 2019-05-31 | 2023-03-31 | 东北大学 | Liquid crystal backlight visual positioning method based on gray scale matching and target contour |
| CN112147147A (en) * | 2019-06-26 | 2020-12-29 | 杭州海康机器人技术有限公司 | Edge defect detection method, edge defect detection device and quality detection equipment |
| CN112147147B (en) * | 2019-06-26 | 2023-12-22 | 杭州海康机器人股份有限公司 | Edge defect detection method, edge defect detection device and quality detection equipment |
| CN110689527A (en) * | 2019-09-18 | 2020-01-14 | 北京航空航天大学 | Method, device and equipment for detecting installation state of aircraft cable bracket |
| CN110689527B (en) * | 2019-09-18 | 2021-08-24 | 北京航空航天大学 | Method, device and equipment for detecting installation state of aircraft cable bracket |
| CN110852989A (en) * | 2019-09-30 | 2020-02-28 | 广州利科科技有限公司 | Quality flaw detection of tile photographed picture |
| CN110852989B (en) * | 2019-09-30 | 2022-05-13 | 广州利科科技有限公司 | Quality flaw detection of tile photographed picture |
| CN112364783A (en) * | 2020-11-13 | 2021-02-12 | 诸暨思看科技有限公司 | Part detection method and device and computer readable storage medium |
| CN112364783B (en) * | 2020-11-13 | 2023-07-14 | 黑龙江鸿时数字科技有限公司 | Part detection method and device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633507A (en) | LCD defect inspection methods based on contour detecting and characteristic matching | |
| CN105701820B (en) | A kind of point cloud registration method based on matching area | |
| CN109580630A (en) | A kind of visible detection method of component of machine defect | |
| CN106373124B (en) | Industrial products surface defect visible detection method based on gray level co-occurrence matrixes and RANSAC | |
| CN105740829A (en) | Scanning line processing based automatic reading method for pointer instrument | |
| CN111476246B (en) | Robust and efficient intelligent reading method for pointer instrument applied to complex environment | |
| CN110223355B (en) | Feature mark point matching method based on dual epipolar constraint | |
| CN106897995A (en) | A kind of parts automatic identifying method towards Automatic manual transmission process | |
| CN107561736A (en) | LCD defect inspection methods based on Fourier and Hough transform | |
| WO2022116218A1 (en) | Method for extracting line-structured laser center for complex surface | |
| CN109919960A (en) | A kind of image continuous boundary detection method based on Multiscale Gabor Filters device | |
| CN109359604A (en) | Meter recognition method under shadow interference towards crusing robot | |
| CN112116702A (en) | Human body measurement three-dimensional modeling method and system based on front and side profiles | |
| CN110009019A (en) | Magnetic material crackle intelligent checking system and method | |
| CN111862315A (en) | Human body multi-size measuring method and system based on depth camera | |
| CN103218809A (en) | Image measuring method of pearl length parameter | |
| WO2022252698A1 (en) | Defect detection method and apparatus based on structured light field video stream | |
| CN108205210B (en) | LCD defect detection system and method based on Fourier mellin and feature matching | |
| CN105930793A (en) | Human body detection method based on SAE characteristic visual learning | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN105488798B (en) | SAR image method for measuring similarity based on point set contrast | |
| Dong et al. | Application of machine vision-based NDT technology in ceramic surface defect detection–a review | |
| CN107194916A (en) | A kind of vision measurement system of feature based Point matching | |
| Liu et al. | Improved image matching algorithm based on LK optical flow and grid motion statistics | |
| CN110648312A (en) | Method for identifying wool and cashmere fibers based on scale morphological characteristic analysis |
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: 20180126 |