CN102938077A - Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation - Google Patents
Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation Download PDFInfo
- Publication number
- CN102938077A CN102938077A CN2012104122899A CN201210412289A CN102938077A CN 102938077 A CN102938077 A CN 102938077A CN 2012104122899 A CN2012104122899 A CN 2012104122899A CN 201210412289 A CN201210412289 A CN 201210412289A CN 102938077 A CN102938077 A CN 102938077A
- Authority
- CN
- China
- Prior art keywords
- image
- threshold
- search
- template image
- method based
- 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
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides an online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation. The online AOI image retrieval method comprises the following steps: S1, acquiring a position image of a standard PCB (Printed Circuit Board); S2, carrying out grey processing on the position image to acquire a grey template image; S3, carrying out double-threshold binaryzation treatment on the grey template image to acquire a template image; S4, acquiring a position image of a PCB to be detected, and acquiring a search region image corresponding to the template image according to the double thresholds set in the step S3; and S5, matching the search region image with the template image to search out a position point which is has the biggest matching degree with the template image. The double-threshold binaryzation treatment is adopted to reduce a grey level of the position image, so that the target area of an electronic component is more protruded; moreover, calculation can be effectively reduced, and calculation speed can be improved, so that a rate of missing report and a misstatement rate are reduced when the AOI software identifies an image.
Description
Technical field
The present invention relates to the SMT technical field, relate in particular to a kind of online AOI image search method based on the dual threshold binaryzation.
Background technology
Automated optical detects (Automatic Optic Inspection, AOI), is based on the method that optical principle comes welding runs in producing to pcb board common deficiency to detect.It is a kind of SMT detection technique of rising in recent years.
Along with developing rapidly of SMT industry, just towards microminiaturized, intensive future development, the defective of element seems unable to do what one wishes to the components and parts size on pcb board so that artificial visually examine's mode detects for this, and is lower by manually removing detection efficiency, and wastes time and energy.Some traditional detection techniques can not adapt to the requirement of SMT development such as the on-line testing instrument.So the AOI technology is to produce for the requirement that adapts to the SMT development.
Present existing AOI software all exists when detecting object component to be failed to report and the wrong report problem, causes this reason to relate to the problem of two aspects: the detection algorithm that adopts in the light source that adopts when gathering image and the software.
The existing problem in first aspect is along with the appearance of high-resolution, high resolution CCD and scanning device, most of AOI manufacturer has begun to make corresponding improvement according to the actual conditions of self, as adopts the CCD of 300 ~ 5,000,000 pixels can collect the picture rich in detail of existing minimum package dimension 01005 element.
Second Problem is AOI software detection algorithm, and the algorithm that adopts owing to each manufacturer is not quite similar, so also to some extent difference of the effect that detects.Most AOI algorithm principle has following several: image ratio is to principle, weights image-forming principle, image statistics study, similarity analysis, images match, vector analysis, color distance analysis, character recognition, gray scale operation.And adopt which kind of algorithm all can when element testing, produce the wrong report and fail to report problem, in order to reduce rate of failing to report and rate of false alarm, only seek more accurate location and image recognition mode at algorithm.
In view of this, be necessary AOI image search method of the prior art is improved, to address the above problem.
Summary of the invention
The object of the present invention is to provide the lower a kind of AOI image search method of rate of false alarm and rate of failing to report.
For achieving the above object, the invention provides a kind of online AOI image search method based on the dual threshold binaryzation, may further comprise the steps:
S1, obtain the location drawing picture of standard pcb board;
S2, the position image is carried out gray processing process, obtain the gray scale template image;
S3, the gray scale template image is carried out the dual threshold binary conversion treatment, obtain template image;
S4, obtain the location drawing picture of pcb board to be detected, and obtain the corresponding region of search of described template image image according to the dual threshold of setting among the step S3;
S5, region of search image and template image are mated, to search out the location point with template image matching degree maximum.
As a further improvement on the present invention, described step S1 is specially: the location drawing picture that obtains at least one electronic component on the standard pcb board by image collecting device and/or image editing apparatus.
As a further improvement on the present invention, described step S2 is specially: the described location drawing is looked like to carry out 256 grades of gray processings process, obtain the gray scale template image of gray level in 0 to 255 scope.
As a further improvement on the present invention, described step S3 is specially: the gray scale template image is carried out the dual threshold binary conversion treatment, capping threshold value Ta and lower threshold Tb obtaining the corresponding region of search of described template image image, and are saved in the database.
As a further improvement on the present invention, the threshold range of described upper limit threshold Ta is 0 to 250, and the threshold range of described lower threshold Tb is 0 to 100.
As a further improvement on the present invention, described step S3 further comprises deviation threshold Tc and left-right deviation threshold value Td about the position image setting of obtaining pcb board to be detected.
As a further improvement on the present invention, described step S3 further comprises obtaining the position image setting similarity threshold Te of pcb board to be detected.
As a further improvement on the present invention, described similarity threshold Te is set to 85%.
As a further improvement on the present invention, described step S5 is specially: obtain the corresponding region of search of described template image image, then the region of search image being carried out 256 grades of gray processings processes, and from database, call upper limit threshold Ta and lower threshold Tb, process to carry out the normalized crosscorrelation template matches, in order to region of search image and template image are mated, to obtain position coefficient R (x, y), and according to similarity threshold Te, search out the location point with template image matching degree maximum.
As a further improvement on the present invention, if position coefficient R (x, y) is greater than or equal to described similarity threshold Te, show that then the position of electronic component on the described pcb board to be detected meets the requirements; If position coefficient R (x, y), shows then that the position of electronic component on the described pcb board to be detected is undesirable less than described similarity threshold Te.
Compared with prior art, the invention has the beneficial effects as follows: by the dual threshold binary conversion treatment, the gray-scale value of image can dip, the target area at electronic component place is protruded more, and computation reduction effectively, improve arithmetic speed, thereby reduced rate of failing to report and the rate of false alarm of AOI software when image recognition.
Description of drawings
Fig. 1 is the schematic flow sheet that the present invention is based on the online AOI image search method of dual threshold binaryzation.
Embodiment
The present invention is described in detail below in conjunction with each embodiment shown in the drawings; but should be noted that; these embodiments are not limitation of the present invention; those of ordinary skills all belong within protection scope of the present invention according to these embodiment institute work energy, method or structural equivalent transformation or alternative.
Shown in please refer to the drawing 1, Fig. 1 is the schematic flow sheet that the present invention is based in the embodiment of online AOI image search method of dual threshold binaryzation.
In the present embodiment, the online AOI image search method based on the dual threshold binaryzation may further comprise the steps:
S1, obtain the location drawing picture of standard pcb board.
This step S1 is specially: the location drawing picture that obtains at least one electronic component on the standard pcb board by image collecting device and/or image editing apparatus.
In the present embodiment, can obtain local or whole location drawing picture on the standard pcb board by double bidirectional scan type CCD image collecting device.Comprise at least one electronic component in this location drawing picture.Certainly also can pass through image editing apparatus, for example: the scanner of tape editing function or pcb board plotting apparatus or mapping software obtain the local or whole location drawing picture on the accurate pcb board of label taking.
S2, the position image is carried out gray processing process, obtain the gray scale template image.
This step S2 is specially: the described location drawing is looked like to carry out 256 grades of gray processings process, obtain the gray scale template image of gray level in 0 to 255 scope.Because the original location drawing similarly is colored, so in the data handling procedure in later stage, the operand of computing machine is huge.Process and the position image is carried out 256 grades of gray processings, computation reduction improves arithmetic speed effectively.
S3, the gray scale template image is carried out the dual threshold binary conversion treatment, obtain template image.
Described step S3 is specially: the gray scale template image is carried out the dual threshold binary conversion treatment, and capping threshold value Ta and lower threshold Tb obtaining the corresponding region of search of described template image image, and are saved in the database.The threshold range of described upper limit threshold Ta is 0 to 250, and the threshold range of described lower threshold Tb is 0 to 100.Described step S3 further comprises deviation threshold Tc and left-right deviation threshold value Td about the position image setting of obtaining pcb board to be detected.Described step S3 further comprises obtaining the position image setting similarity threshold Te of pcb board to be detected.Concrete, this similarity threshold Te is set to 85%.
S4, obtain the location drawing picture of pcb board to be detected, and obtain the corresponding region of search of described template image image according to the dual threshold of setting among the step S3.
S5, region of search image and template image are mated, to search out the location point with template image matching degree maximum.
Described step S5 is specially: obtain the corresponding region of search of described template image image, then the region of search image being carried out 256 grades of gray processings processes, and from database, call upper limit threshold Ta and lower threshold Tb, process to carry out the normalized crosscorrelation template matches, in order to region of search image and template image are mated, to obtain position coefficient R (x, y), and according to similarity threshold Te, search out the location point with template image matching degree maximum.
In the present embodiment, the algorithm model of this normalized crosscorrelation template matches processing is as follows.
If region of search image
Size be
, template image
Size be
(wherein
), with template image
Overlay the region of search image
Upper translation is weighed template image with the square error sum
With the region of search image
Difference between the coated region, square error and being defined as shown in the formula (1).
Formula (1) is launched can be as the formula (2).
In the formula (2): first expression region of search image
In with template image
The energy of corresponding region, it and location of pixels
Relevant.But with location of pixels
Variation and slowly change.A middle expression template image
With the region of search image
The cross-correlation coefficient of coated region, it is with location of pixels
Variation and change, work as template image
With the region of search image
When coated region was complementary, cross-correlation coefficient was got maximal value.Last is constant, the expression template image
Gross energy, it and image pixel positions
Irrelevant.
Can be with the related coefficient after the following normalization as position coefficient R (x, y), its computing formula is as the formula (3).
Suppose the region of search image
And template image
Initial point all in the upper left corner, to any one
In
, can calculate to get one according to following formula
When x and y variation,
At the region of search image
Move in the zone and draw
All values.
Maximal value represent template image
The optimum position of coupling is if begin at the region of search image from this position
Middle taking-up and template image
The zone that size is identical just can obtain matching image.This matching image be exactly search out and template image
The location point of matching degree maximum.
Search time when mating in order to be reduced in, we have adopted the convergent-divergent algorithm to control the region of search images of different sizes in design
, according to the big or small region of search of difference image
Adjust the scaling coefficient.This has reduced search time to a great extent.Interpolation arithmetics all in Image Zooming Algorithm all adopt the cubic polynomial interpolation, have so just guaranteed the region of search image
The precision of convergent-divergent.
In the present embodiment, if position coefficient R (x, y) is greater than or equal to described similarity threshold Te, show that then the position of electronic component on the described pcb board to be detected meets the requirements; If position coefficient R (x, y), shows then that the position of electronic component on the described pcb board to be detected is undesirable less than described similarity threshold Te.
Above listed a series of detailed description only is specifying for feasibility embodiment of the present invention; they are not to limit protection scope of the present invention, allly do not break away from equivalent embodiment or the change that skill spirit of the present invention does and all should be included within protection scope of the present invention.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned example embodiment, and in the situation that does not deviate from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore, no matter from which point, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims rather than above-mentioned explanation, therefore is intended to include in the present invention dropping on the implication that is equal to important document of claim and all changes in the scope.Any Reference numeral in the claim should be considered as limit related claim.
In addition, be to be understood that, although this instructions is described according to embodiment, but be not that each embodiment only comprises an independently technical scheme, this narrating mode of instructions only is for clarity sake, those skilled in the art should make instructions as a whole, and the technical scheme among each embodiment also can through appropriate combination, form other embodiments that it will be appreciated by those skilled in the art that.
Claims (10)
1. based on the online AOI image search method of dual threshold binaryzation, it is characterized in that, may further comprise the steps:
S1, obtain the location drawing picture of standard pcb board;
S2, the position image is carried out gray processing process, obtain the gray scale template image;
S3, the gray scale template image is carried out the dual threshold binary conversion treatment, obtain template image;
S4, obtain the location drawing picture of pcb board to be detected, and obtain the corresponding region of search of described template image image according to the dual threshold of setting among the step S3;
S5, region of search image and template image are mated, to search out the location point with template image matching degree maximum.
2. the online AOI image search method based on the dual threshold binaryzation according to claim 1, it is characterized in that described step S1 is specially: the location drawing picture that obtains at least one electronic component on the standard pcb board by image collecting device and/or image editing apparatus.
3. the online AOI image search method based on the dual threshold binaryzation according to claim 1, it is characterized in that, described step S2 is specially: the described location drawing is looked like to carry out 256 grades of gray processings process, obtain the gray scale template image of gray level in 0 to 255 scope.
4. the online AOI image search method based on the dual threshold binaryzation according to claim 1, it is characterized in that, described step S3 is specially: the gray scale template image is carried out the dual threshold binary conversion treatment, capping threshold value Ta and lower threshold Tb, obtaining the corresponding region of search of described template image image, and be saved in the database.
5. the online AOI image search method based on the dual threshold binaryzation according to claim 4 is characterized in that the threshold range of described upper limit threshold Ta is 0 to 250, and the threshold range of described lower threshold Tb is 0 to 100.
6. the online AOI image search method based on the dual threshold binaryzation according to claim 1 is characterized in that, described step S3 further comprises deviation threshold Tc and left-right deviation threshold value Td about the position image setting of obtaining pcb board to be detected.
7. the online AOI image search method based on the dual threshold binaryzation according to claim 1 is characterized in that, described step S3 further comprises obtaining the position image setting similarity threshold Te of pcb board to be detected.
8. the online AOI image search method based on the dual threshold binaryzation according to claim 7 is characterized in that described similarity threshold Te is set to 85%.
9. according to claim 1 or 4 described online AOI image search methods based on the dual threshold binaryzation, it is characterized in that, described step S5 is specially: obtain the corresponding region of search of described template image image, then the region of search image being carried out 256 grades of gray processings processes, and from database, call upper limit threshold Ta and lower threshold Tb, process to carry out the normalized crosscorrelation template matches, in order to region of search image and template image are mated, to obtain position coefficient R (x, y), and according to similarity threshold Te, search out the location point with template image matching degree maximum.
10. the online AOI image search method based on the dual threshold binaryzation according to claim 9, it is characterized in that, if position coefficient R (x, y) is greater than or equal to described similarity threshold Te, show that then the position of electronic component on the described pcb board to be detected meets the requirements; If position coefficient R (x, y), shows then that the position of electronic component on the described pcb board to be detected is undesirable less than described similarity threshold Te.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104122899A CN102938077A (en) | 2012-10-25 | 2012-10-25 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104122899A CN102938077A (en) | 2012-10-25 | 2012-10-25 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102938077A true CN102938077A (en) | 2013-02-20 |
Family
ID=47696972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104122899A Pending CN102938077A (en) | 2012-10-25 | 2012-10-25 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102938077A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104677914A (en) * | 2015-03-10 | 2015-06-03 | 华中科技大学 | Method for identifying crystal stock defect of chip |
| CN104700085A (en) * | 2015-03-10 | 2015-06-10 | 华中科技大学 | Template matching-based chip positioning method |
| CN105136818A (en) * | 2015-09-18 | 2015-12-09 | 联策科技股份有限公司 | Printing substrate image detecting method |
| CN106023182A (en) * | 2016-05-13 | 2016-10-12 | 广州视源电子科技股份有限公司 | PCB image matching method and system |
| CN106228546A (en) * | 2016-07-13 | 2016-12-14 | 广州视源电子科技股份有限公司 | The detection method of a kind of board and device |
| CN106327462A (en) * | 2015-06-16 | 2017-01-11 | 征图新视（江苏）科技有限公司 | Printed image positioning core extraction method and extraction device |
| CN106570858A (en) * | 2016-10-17 | 2017-04-19 | 浙江理工大学 | AOI component detection frame automatic generation method based on PCB coordinate transformation |
| CN106886989A (en) * | 2015-12-11 | 2017-06-23 | 东莞东聚电子电讯制品有限公司 | The automatic optical detection method of keyboard |
| WO2017107533A1 (en) * | 2015-12-22 | 2017-06-29 | 广州视源电子科技股份有限公司 | Electronic component sample labeling method and device |
| CN107480672A (en) * | 2016-06-08 | 2017-12-15 | 广州康昕瑞基因健康科技有限公司 | Image-recognizing method and system and autofocus control method and system |
| CN107665350A (en) * | 2016-07-29 | 2018-02-06 | 广州康昕瑞基因健康科技有限公司 | Image-recognizing method and system and autofocus control method and system |
| CN107764192A (en) * | 2017-11-30 | 2018-03-06 | 中国地质调查局水文地质环境地质调查中心 | One kind landslide multi-point displacement intelligent monitoring device and monitoring method |
| CN107784645A (en) * | 2016-08-26 | 2018-03-09 | 广州康昕瑞基因健康科技有限公司 | Measurement for Digital Image Definition and system, auto focusing method |
| CN108355987A (en) * | 2018-01-08 | 2018-08-03 | 西安交通大学 | A kind of screen printing of battery quality determining method based on piecemeal template matches |
| CN108414193A (en) * | 2018-03-28 | 2018-08-17 | 京东方科技集团股份有限公司 | The detection zone localization method and device of display screen |
| CN108615253A (en) * | 2018-04-12 | 2018-10-02 | 广东数相智能科技有限公司 | Image generating method, device and computer readable storage medium |
| CN108941918A (en) * | 2018-03-29 | 2018-12-07 | 江苏新时代造船有限公司 | One kind founding part method based on networking intelligent recognition multirobot automatic welding ship group |
| CN109509165A (en) * | 2017-09-11 | 2019-03-22 | 凌云光技术集团有限责任公司 | Framing region choosing method and device |
| CN109870117A (en) * | 2017-12-05 | 2019-06-11 | 英业达科技有限公司 | Binaryzation outline detection system and its method |
| CN112634227A (en) * | 2020-12-21 | 2021-04-09 | 广州镭晨智能科技有限公司 | Detection and identification method and device for PCB jointed board, electronic equipment and storage medium |
| TWI738295B (en) * | 2020-04-15 | 2021-09-01 | 明基材料股份有限公司 | Aoi apparatus for product manufactured roll-to-roll process and aoi method by using the same |
| CN115359047A (en) * | 2022-10-19 | 2022-11-18 | 元能微电子科技南通有限公司 | Abnormal defect detection method for intelligent welding of PCB (printed circuit board) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0206709A2 (en) * | 1985-06-17 | 1986-12-30 | Visionetics Corporation | Automatic optical inspection of printed circuit boards |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN102507008A (en) * | 2011-10-26 | 2012-06-20 | 惠州市德赛西威汽车电子有限公司 | Multi-template automatic optical color detection method |
-
2012
- 2012-10-25 CN CN2012104122899A patent/CN102938077A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0206709A2 (en) * | 1985-06-17 | 1986-12-30 | Visionetics Corporation | Automatic optical inspection of printed circuit boards |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN102507008A (en) * | 2011-10-26 | 2012-06-20 | 惠州市德赛西威汽车电子有限公司 | Multi-template automatic optical color detection method |
Non-Patent Citations (2)
| Title |
|---|
| 王雁玲: "自动光学检测系统中图像处理技术研究", 《中国优秀硕士学位论文全文数据库》 * |
| 苟中魁 等: "一种Otsu阈值法的推广——Otsu双阈值法", 《机械》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700085B (en) * | 2015-03-10 | 2018-02-27 | 华中科技大学 | A kind of chip positioning method based on template matches |
| CN104700085A (en) * | 2015-03-10 | 2015-06-10 | 华中科技大学 | Template matching-based chip positioning method |
| CN104677914B (en) * | 2015-03-10 | 2017-03-08 | 华中科技大学 | A kind of chip crystal stock defect identification method |
| CN104677914A (en) * | 2015-03-10 | 2015-06-03 | 华中科技大学 | Method for identifying crystal stock defect of chip |
| CN106327462B (en) * | 2015-06-16 | 2019-06-21 | 征图新视（江苏）科技有限公司 | Print the positioning core extracting method and extraction element of image |
| CN106327462A (en) * | 2015-06-16 | 2017-01-11 | 征图新视（江苏）科技有限公司 | Printed image positioning core extraction method and extraction device |
| CN105136818A (en) * | 2015-09-18 | 2015-12-09 | 联策科技股份有限公司 | Printing substrate image detecting method |
| CN105136818B (en) * | 2015-09-18 | 2018-03-09 | 联策科技股份有限公司 | The image detection method of printed base plate |
| CN106886989A (en) * | 2015-12-11 | 2017-06-23 | 东莞东聚电子电讯制品有限公司 | The automatic optical detection method of keyboard |
| WO2017107533A1 (en) * | 2015-12-22 | 2017-06-29 | 广州视源电子科技股份有限公司 | Electronic component sample labeling method and device |
| CN106023182A (en) * | 2016-05-13 | 2016-10-12 | 广州视源电子科技股份有限公司 | PCB image matching method and system |
| CN107480672A (en) * | 2016-06-08 | 2017-12-15 | 广州康昕瑞基因健康科技有限公司 | Image-recognizing method and system and autofocus control method and system |
| CN106228546B (en) * | 2016-07-13 | 2019-01-29 | 广州视源电子科技股份有限公司 | A kind of detection method and device of board |
| CN106228546A (en) * | 2016-07-13 | 2016-12-14 | 广州视源电子科技股份有限公司 | The detection method of a kind of board and device |
| CN107665350A (en) * | 2016-07-29 | 2018-02-06 | 广州康昕瑞基因健康科技有限公司 | Image-recognizing method and system and autofocus control method and system |
| CN107784645A (en) * | 2016-08-26 | 2018-03-09 | 广州康昕瑞基因健康科技有限公司 | Measurement for Digital Image Definition and system, auto focusing method |
| CN106570858A (en) * | 2016-10-17 | 2017-04-19 | 浙江理工大学 | AOI component detection frame automatic generation method based on PCB coordinate transformation |
| CN106570858B (en) * | 2016-10-17 | 2019-05-07 | 浙江理工大学 | AOI component detection block method is automatically generated based on PCB coordinate transform |
| CN109509165A (en) * | 2017-09-11 | 2019-03-22 | 凌云光技术集团有限责任公司 | Framing region choosing method and device |
| CN109509165B (en) * | 2017-09-11 | 2021-01-29 | 凌云光技术股份有限公司 | Image positioning area selection method and device |
| CN107764192A (en) * | 2017-11-30 | 2018-03-06 | 中国地质调查局水文地质环境地质调查中心 | One kind landslide multi-point displacement intelligent monitoring device and monitoring method |
| CN109870117A (en) * | 2017-12-05 | 2019-06-11 | 英业达科技有限公司 | Binaryzation outline detection system and its method |
| CN108355987A (en) * | 2018-01-08 | 2018-08-03 | 西安交通大学 | A kind of screen printing of battery quality determining method based on piecemeal template matches |
| CN108414193A (en) * | 2018-03-28 | 2018-08-17 | 京东方科技集团股份有限公司 | The detection zone localization method and device of display screen |
| CN108941918A (en) * | 2018-03-29 | 2018-12-07 | 江苏新时代造船有限公司 | One kind founding part method based on networking intelligent recognition multirobot automatic welding ship group |
| CN108615253A (en) * | 2018-04-12 | 2018-10-02 | 广东数相智能科技有限公司 | Image generating method, device and computer readable storage medium |
| TWI738295B (en) * | 2020-04-15 | 2021-09-01 | 明基材料股份有限公司 | Aoi apparatus for product manufactured roll-to-roll process and aoi method by using the same |
| CN112634227A (en) * | 2020-12-21 | 2021-04-09 | 广州镭晨智能科技有限公司 | Detection and identification method and device for PCB jointed board, electronic equipment and storage medium |
| CN115359047A (en) * | 2022-10-19 | 2022-11-18 | 元能微电子科技南通有限公司 | Abnormal defect detection method for intelligent welding of PCB (printed circuit board) |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102938077A (en) | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation | |
| Romero-Ramirez et al. | Speeded up detection of squared fiducial markers | |
| EP3033875B1 (en) | Image processing apparatus, image processing system, image processing method, and computer program | |
| JP5699788B2 (en) | Screen area detection method and system | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN109752392B (en) | PCB defect type detection system and method | |
| US20080205769A1 (en) | Apparatus, method and program product for matching with a template | |
| CN111833303A (en) | Product detection method and device, electronic equipment and storage medium | |
| CN106651802B (en) | Machine vision scolding tin position finding and detection method | |
| WO2014045508A1 (en) | Inspection device, inspection method, and inspection program | |
| CN106501272A (en) | Machine vision scolding tin position detecting system | |
| CN105354816B (en) | A kind of electronic units fix method and device | |
| CN115249237A (en) | Defect detection method, defect detection apparatus, and computer-readable storage medium | |
| JP6197340B2 (en) | Image processing apparatus, image processing method, and program | |
| Mukhopadhyay et al. | PCB inspection in the context of smart manufacturing | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| JP2022009474A (en) | System and method for detecting lines in vision system | |
| Abbas | Recovering homography from camera captured documents using convolutional neural networks | |
| CN117761060A (en) | Visual detection system and detection method thereof | |
| CN115984197A (en) | Defect detection method based on standard PCB image and related device | |
| CN105469085B (en) | Board image acquiring method and system | |
| CN114418951A (en) | Pad detection method and device, computer equipment and storage medium | |
| JP2008185395A (en) | Mounting substrate visual inspection method | |
| KR20150096128A (en) | Auto Calibration Method for Virtual Camera based on Mobile Platform | |
| CN103630547B (en) | There is flaw detection method and the pick-up unit thereof of the optical thin film of periodic structure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130220 |