CN101303226A - Method for measuring circuit board line width based on largest communication domain - Google Patents
Method for measuring circuit board line width based on largest communication domain Download PDFInfo
- Publication number
- CN101303226A CN101303226A CNA2008101069422A CN200810106942A CN101303226A CN 101303226 A CN101303226 A CN 101303226A CN A2008101069422 A CNA2008101069422 A CN A2008101069422A CN 200810106942 A CN200810106942 A CN 200810106942A CN 101303226 A CN101303226 A CN 101303226A
- Authority
- CN
- China
- Prior art keywords
- straight line
- tested
- wiring board
- line width
- largest connected
- 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)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for measuring line width of a circuit board based on maximum connected domain, which comprises the steps of: 1) capturing the image of a target circuit board; 2) denoising the image and segmenting a target straight line; 3) extracting the straight line by using the maximum connected domain method within a rectangular frame; 4) determining the point sets of both edges of the target straight line by scanning; 5) removing singular edge points; and 6) fitting the two edges of the straight line and performing line width calculation by using the least square method. By introducing maximum connected domain search for acquiring target straight lines, the method of the invention is applicable to line width measurement for not only interior copper plates but also exterior copper plates with small contrast between circuit and substrate. And by employing image denoising and singular point removal, the method achieves accurate acquisition of edges of target straight lines, and as a result, improved precision and stability of line width measurement.
Description
Technical field
The present invention relates to the wiring board detection method, particularly a kind of wiring board line width measuring method based on largest connected territory.
Background technology
The microminiaturization of integrated circuit (IC) chip has proposed the requirements at the higher level of live width densification, number of plies multiple stratification for the making of printed circuit board (PCB) (PCB).The live width of the last intensive parallel lines of PCB, too thick if etching gets, then cause the parallel lines short circuit easily; If it is too thin that etching gets, then cause the transmission of signal undesired easily; If etching gets the local sudden change (chap or attenuate) that has, then be easy to generate the high frequency reflection, form electromagnetic interference (EMI), influence stablizing of electronic system.Accurately measuring automatically of printed circuit board (PCB) cathetus live width is the key of high-quality circuit board making.Usually adopted hundred times of mirrors and general Quadratic Finite Element to measure, hundred times of mirror measurements depend on workman's experience in the past, and measuring speed is slow, precision is low, and general Quadratic Finite Element is a manual measurement, inconvenient operation.
Along with the development of computer image processing technology and the maturation of automatic measuring equipment, measuring automatically by image for the printed-wiring board (PWB) live width provides technology and material base.Existing wiring board line width measuring method based on image, for straight line and the big wiring board of base material contrast, as interior copper coin, can realize automatic measurement, and higher measuring accuracy is arranged, but, be difficult to accurately find automatically the edge of straight line for straight line and the little outer copper coin of base material contrast, can not realize automatic measurement, measure with manual method usually.
Summary of the invention
The purpose of this invention is to provide a kind of wiring board line width measuring method based on largest connected territory, it is to get rid of by the method for seeking largest connected territory to disturb, under measured straight line and the little situation of base material contrast, realize the accurate location of linear edge, and then realized the high precision of straight line live width, measurement automatically.
The present invention is achieved through the following technical solutions, and its method step is as follows:
1. catch the circuit board drawing picture of tested straight line
Image-taking system is made up of two-dimentional moveable platform, ccd video camera, ring lighting device, video frequency collection card and PC.During measurement, printed-wiring board (PWB) is fixed on the two-dimentional moveable platform, adjusts lighting device, make light be uniformly distributed in tested zone, regulate its focal length by the upper-lower position of adjusting camera, obtain test line plate picture signal clearly, send into computing machine and use for measuring.
Printed-wiring board (PWB) manufacturer often by measuring the local live width of printed-wiring board (PWB), checks its fabricating quality, therefore, is obtaining regional area as measured data on the circuit board drawing picture clearly with rectangle frame.
2. image denoising and tested straight line dividing processing
For reducing the influence of noise spot, circuit board drawing is looked like to carry out denoising to measuring accuracy.Because median filter method can keep the edge of image feature well, and wire width measuring is the edge feature that utilizes measured straight line, and therefore, the present invention adopts 3 * 3 template that image is carried out medium filtering.
In rectangle frame, the present invention adopts maximum variance between clusters that tested straight line is split from the base material background, is used for the point set search of follow-up edge.
3. utilize largest connected territory method to extract tested straight line;
According to tested straight line in the rectangle frame is the characteristics in a largest connected territory, and the present invention only keeps tested straight line by largest connected property searching method in rectangle frame, remove other interference.
4. utilize scanning method to determine the two edges point set of tested straight line
The present invention adopts horizontal or vertical scan method to search for the two edges point set of tested straight line, and its key step is as follows:
1) judges it is to adopt horizontal scanning or adopt the vertical scanning mode.The characteristics of wiring board imaging are that the copper cash imaging is brighter, and gray-scale value is bigger than normal, and the base material imaging is darker, and gray-scale value is less than normal.According to this imaging characteristics, the present invention adopts the method for two horizontal linears and two vertical line mean flow rates in the comparison rectangle frame, the way of search of decision edge point set.
2) upper left corner with rectangle frame is starting point, makes a vertical line, calculates two points that itself and tested linear edge intersect.In search procedure, if a certain gray values of pixel points greater than t* (t* is a segmentation threshold), then is a marginal point.
3) in rectangle frame, the present invention makes one group of vertical line with the interval of 5 pixels.Travel through all vertical line from left to right, calculate, can obtain two edge point sets of tested straight line with the method in the 2nd step.
5. remove unusual marginal point
The method that the present invention removes unusual marginal point is, adopt least square method that the initial edge point set is carried out fitting a straight line earlier, calculate the distance of the fitting a straight line of having a few again, after ordering from big to small, remove distance part point farthest by a certain percentage, be singular point.
6. utilize least square fitting two edges straight line and live width to calculate.
Two edge point sets after utilizing least square method to the removal singular point carry out fitting a straight line respectively, obtain two edge lines.
Before measuring live width, carry out camera calibration earlier, scaling method is: under the close-up enlargement factor, the standard light rule is measured the proportionate relationship of determining between the image, i.e. the shared length of unit picture element (unit is mm), computing formula is
Wherein, L is the known length in the standard light rule, and N is the number of pixels of L correspondence in image.The present invention's method by experiment obtains aforementioned proportion and concerns k.
Because two edge lines of tested live width can not be parallel fully, therefore can not calculate live width with range formula between two parallel lines.The present invention calculates coboundary point set after the denoising earlier to the mean distance of lower limb straight line, calculates lower limb point set after the denoising again to the mean distance of coboundary straight line.The number of pixels that on average is tested straight line live width correspondence of above-mentioned two distances multiply by k with it, obtains the live width of tested straight line.
Advantage of the present invention is: the present invention is directed to tested linearity region and the background area gray-scale value differs problem of smaller, adopt the method for seeking largest connected territory to get rid of and disturb, accurately locate linear edge, realized the automatic measurement of live width; Utilize least square method and repeatedly match obtain the two edges straight-line equation of tested straight line, removed unusual marginal point, improved measuring accuracy and stability.
Description of drawings
Fig. 1 is a workflow block scheme of the present invention.
Fig. 2 is the largest connected domain search process flow diagram of the present invention.
Fig. 3 removes process flow diagram for the unusual marginal point of the present invention.
Embodiment
The input image data that the present invention is used to measure derives from two modes: one is with micro-amplifying camera machine, and through the single-frame images that image pick-up card obtains, two is the image file of .BMP and two kinds of forms of .JPEG.Picture format can be 8 gray scales, 24 and 32 rgb images.The video input can be PAL or NTSC video standard signal.
For piece image, this method mainly comprises circuit board drawing picture, image denoising and the tested straight line dividing processing of catching tested straight line, utilizes largest connected territory method to extract tested straight line, utilizes scanning method to determine the two edges point set of tested straight line, removes unusual marginal point, utilizes steps such as least square fitting two edges straight line and live width calculating, workflow of the present invention is specifically implemented as follows as shown in Figure 1:
1. catch the circuit board drawing picture of tested straight line
Image-taking system is made up of two-dimentional moveable platform, ccd video camera, ring lighting device, video frequency collection card and PC.During measurement, printed-wiring board (PWB) is fixed on the two-dimentional moveable platform, adjust lighting device, make light be uniformly distributed in tested zone, under a certain enlargement factor, regulate its focal length by the upper-lower position of adjusting camera, obtain test line plate picture signal clearly, send into computing machine and use for measuring.
Printed-wiring board (PWB) manufacturer often by measuring the local live width of printed-wiring board (PWB), checks its fabricating quality, therefore, is obtaining regional area as measured data on the circuit board drawing picture clearly with rectangle frame.
2. image denoising and tested straight line dividing processing
For reducing the influence of noise spot, circuit board drawing is looked like to carry out denoising to measuring accuracy.Because median filter method can keep the edge of image feature well, and wire width measuring is the edge feature that utilizes tested straight line, and therefore, the present invention adopts 3 * 3 template that image is carried out medium filtering.
In rectangle frame, the present invention adopts maximum variance between clusters that tested straight line is split from the base material background, is used for follow-up edge point set and seeks.
Segmentation threshold calculates principle:
If the image gray levels scope is H={0,1 ..., L}, gray scale is that the pixel count of i is n
i, then total pixel is
Gray scale is that the pixel probability of occurrence of i is p
i=n
i/ N.Has only tested straight line (being target) C in the rectangle frame
0With background C
1Two classes, according to pattern recognition theory, the inter-class variance computing formula of this two class is
σ
2＝p
0(t)p
1(t)[μ
1(t)-μ
0(t)]
2
Wherein, t is C
0And C
1The threshold value of cutting apart; p
0(t) and p
1(t) be respectively C
0And C
1The probability that two classes occur, computing formula is respectively
With
μ
0(t) and μ
1(t) be respectively C
0And C
1The gray average of two classes, computing formula is respectively
With
The optimal threshold of cutting apart is the t value when getting maximal value in the inter-class variance computing formula, is designated as t
*
3. utilize largest connected territory method to extract tested straight line;
According to tested straight line in the rectangle frame is the characteristics in a largest connected territory, and the present invention only keeps tested straight line by largest connected domain search method in rectangle frame, removes and disturbs.
Largest connected domain search method:
The process flow diagram of largest connected domain search method, as shown in Figure 2, key step is as follows:
1) data structure of definition connected component and connection straight line.
2) to image from top to bottom, carry out line scanning,, otherwise carried out for the 4th step if first row carried out for the 3rd step.
3) create connected component according to being communicated with straight line, and to each connected component and connection straight line distribute labels.
4) judge whether to exist the connection straight line,, then carried out for the 6th step if do not exist; If exist, then this is communicated with straight line and compares one by one with the straight line that is communicated with of previous row, judge whether to exist to be communicated with, if do not exist, then create new connected component, and distribute labels, forwarded for the 6th step to, otherwise carried out for the 5th step.
5) judge whether this connection straight line is communicated with straight line for the first time and is communicated with the front, if, then it is joined the end that previous row is communicated with straight line place connected component, and put its mark that previous row is communicated with straight line that is masked as, carried out for the 6th step; Otherwise, the mark that is labeled as this connection straight line that lastrow is communicated with straight line place connected component is set, carried out for the 6th step.
6) all row end of scan whether in the entire image if not, returns the 2nd step scanning next line; If then be to carry out for the 7th step.
7) travel through all different marks, add up the pixel count of each mark correspondence, the pairing connected domain of the mark that number is maximum is largest connected territory.Whole largest connected domain search finishes.
4. utilize scanning method to determine the two edges point set of tested straight line
The present invention adopts horizontal or vertical scan method to search for the two edges point set of tested straight line, and its key step is as follows:
1) judges it is to adopt horizontal scanning or adopt the vertical scanning mode.The characteristics of wiring board imaging are that the copper cash imaging is brighter, and gray-scale value is bigger than normal, and the base material imaging is darker, and gray-scale value is less than normal.According to this imaging characteristics, the present invention adopts the method for two horizontal linears and two vertical line mean flow rates in the comparison rectangle frame, the way of search of decision edge point set.
2) upper left corner with rectangle frame is starting point, makes a vertical line, calculates two points that itself and tested linear edge intersect.In search procedure, if a certain gray values of pixel points is greater than t
*(t
*Be segmentation threshold), then be marginal point.
3) in rectangle frame, the present invention makes one group of vertical line with the interval of 5 pixels.Travel through all vertical line from left to right, calculate, can obtain two edge point sets of tested straight line with the method in the 2nd step.
5. remove unusual marginal point
The method that the present invention removes unusual marginal point is, adopt least square method that the initial edge point set is carried out fitting a straight line earlier, calculate the distance of the fitting a straight line of having a few again, after ordering from big to small, remove distance part point farthest by a certain percentage, be singular point.
The least-square fitting approach principle is as follows:
Suppose that an edge point set has N data point, coordinate is respectively (x
i, y
i), i=0 wherein, 1 ... N adopts least-square fitting approach can get the coboundary straight line, and its equation is
y＝k
1x+b
1
Wherein, k
1And b
1Computing formula be respectively
With
In like manner can obtain the least square fitting straight line of another edge point set, its equation is y=k
2X+b
2
For an edge point set, remove the process flow diagram of unusual marginal point, as shown in Figure 3, its key step is as follows:
1) utilizes least square method that the edge point set is carried out fitting a straight line, obtain edge line.
2) calculate each marginal point that participates in fitting a straight line to the distance between fitting a straight line, these distances are sorted from big to small.
3) concentrate to take out a point by the sequence number order from marginal point, judge this distance of putting fitting a straight line whether belong to farthest 1/3, if, then this marginal point is carried out mark, and removes, carried out for the 4th step, if not, directly carried out for the 4th step.
4) whether the institute that concentrates of marginal point has a few and all travels through, if, then end; Otherwise returned for the 3rd step.
6. utilize least square fitting two edges straight line and live width to calculate
Two edge point sets after utilizing least square method to the removal singular point carry out fitting a straight line respectively, obtain two edge lines.
Before measuring live width, carry out camera calibration earlier, scaling method is: under the close-up enlargement factor, the standard light rule is measured the proportionate relationship of determining between the image, i.e. the shared length of unit picture element (unit is mm), computing formula is
Wherein, L is the known length in the standard light rule, and N is the number of pixels of L correspondence in image.The present invention's method by experiment obtains aforementioned proportion and concerns k.
Because two edge lines of tested live width can not be parallel fully, therefore can not calculate live width with range formula between two parallel lines.The present invention calculates coboundary point set after the denoising earlier to the mean distance of lower limb straight line, calculates lower limb point set after the denoising again to the mean distance of coboundary straight line.The number of pixels that on average is tested straight line live width correspondence of above-mentioned two distances multiply by k with it, obtains the top live width of tested straight line.
Claims (7)
1, a kind of wiring board line width measuring method based on largest connected territory is characterized in that method step is as follows:
1) catches the circuit board drawing picture of tested straight line;
2) image denoising and tested straight line dividing processing;
3) in rectangle frame, utilize largest connected territory method to extract tested straight line;
4) utilize scanning method to determine the two edges point set of tested straight line;
5) remove unusual marginal point;
6) utilize least square fitting two edges straight line and live width to calculate.
2, a kind of wiring board line width measuring method according to claim 1 based on largest connected territory, it is characterized in that, under the specific enlargement factor of video camera, obtain the image of tested straight line in the wiring board, and obtain interested tested regional area with rectangle frame.
3, a kind of wiring board line width measuring method based on largest connected territory according to claim 1 is characterized in that described image de-noising method is to adopt edge feature to keep filtering method preferably.
4, a kind of wiring board line width measuring method based on largest connected territory according to claim 1 is characterized in that, is to utilize largest connected domain search method to obtain measured straight line in rectangle frame.
5, according to the described a kind of wiring board line width measuring method of claim 1, it is characterized in that based on largest connected territory, from rectangle frame up and down or about scan two edge point sets that obtain tested straight line every certain pixel separation to tested straight line respectively.
6, according to the described a kind of wiring board line width measuring method of claim 1 based on largest connected territory, it is characterized in that the unusual marginal point of described removal, comprise and adopt least square method that the initial edge point set is carried out fitting a straight line earlier, calculate the distance of the fitting a straight line of having a few again, and by after the ordering from big to small, remove distance part point farthest in proportion, be unusual marginal point.
7, require described a kind of wiring board line width measuring method according to right 1 based on largest connected territory, it is characterized in that, tested straight line live width is going up behind the singular point (or left side) edge point set to the mean distance of (or right) edge line down, and down (or right) edge point set to both average again of the mean distance of last (or left side) edge line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008101069422A CN101303226A (en) | 2008-06-25 | 2008-06-25 | Method for measuring circuit board line width based on largest communication domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008101069422A CN101303226A (en) | 2008-06-25 | 2008-06-25 | Method for measuring circuit board line width based on largest communication domain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101303226A true CN101303226A (en) | 2008-11-12 |
Family
ID=40113238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2008101069422A Pending CN101303226A (en) | 2008-06-25 | 2008-06-25 | Method for measuring circuit board line width based on largest communication domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101303226A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183206A (en) * | 2011-03-16 | 2011-09-14 | 昆山市正业电子有限公司 | Line width measuring method for line on printed circuit board (PCB) |
| CN102496136A (en) * | 2011-12-08 | 2012-06-13 | 中国人民解放军国防科学技术大学 | Phase-grouping line extraction method based on image processing unit |
| CN102589461A (en) * | 2012-01-17 | 2012-07-18 | 华中科技大学 | Image-based snow depth measuring method |
| CN103185560A (en) * | 2011-12-29 | 2013-07-03 | 鸿富锦精密工业（深圳）有限公司 | System and method for detecting circuit width of printed circuit board (PCB) |
| CN103512501A (en) * | 2013-09-22 | 2014-01-15 | 电子科技大学 | Method for detecting manufacturing error of line width of microstrip line circuit on surface of ceramic substrate |
| CN103954223A (en) * | 2014-05-04 | 2014-07-30 | 杭州电子科技大学 | Outlet silk width measuring method based on double-camera millimeter level biology 3D printer |
| CN104422832A (en) * | 2013-08-28 | 2015-03-18 | 深圳麦逊电子有限公司 | Network analysis method of PCB |
| 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 |
| CN107588731A (en) * | 2017-09-30 | 2018-01-16 | 江西景旺精密电路有限公司 | A kind of pcb board line width measuring method and system |
| CN107917686A (en) * | 2017-12-18 | 2018-04-17 | 广州兴森快捷电路科技有限公司 | The method for detecting abnormality and device of printed wiring board |
| CN109215075A (en) * | 2017-06-30 | 2019-01-15 | 沈阳新松机器人自动化股份有限公司 | The positioning identification system and method for workpiece in the crawl of industrial robot material |
| CN109255795A (en) * | 2018-09-11 | 2019-01-22 | 中国计量大学 | A kind of tomato plant edge sort algorithm |
| CN109349774A (en) * | 2018-10-29 | 2019-02-19 | 徐悦 | A kind of automatic manicure method and apparatus |
| CN109580652A (en) * | 2018-10-30 | 2019-04-05 | 广州超音速自动化科技股份有限公司 | A kind of quality of battery pole piece detection method, electronic equipment and storage medium |
| CN110553581A (en) * | 2018-06-01 | 2019-12-10 | 华邦电子股份有限公司 | critical dimension measuring method and image processing device for measuring critical dimension |
| CN112541910A (en) * | 2020-12-23 | 2021-03-23 | 中国工程物理研究院机械制造工艺研究所 | End face gap detection method, device, equipment and medium based on deep learning |
| US11037287B2 (en) | 2018-05-09 | 2021-06-15 | Winbond Electronics Corp. | Method for measuring critical dimension and image-processing apparatus for measuring critical dimension |
| CN113533785A (en) * | 2021-07-22 | 2021-10-22 | 中国计量科学研究院 | Scanning electron microscope-based nano line width self-adaptive measurement method and system |
| CN114646265A (en) * | 2022-05-24 | 2022-06-21 | 四川英创力电子科技股份有限公司 | Detection device and method for precisely detecting line width on circuit board |
-
2008
- 2008-06-25 CN CNA2008101069422A patent/CN101303226A/en active Pending
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183206A (en) * | 2011-03-16 | 2011-09-14 | 昆山市正业电子有限公司 | Line width measuring method for line on printed circuit board (PCB) |
| CN102496136A (en) * | 2011-12-08 | 2012-06-13 | 中国人民解放军国防科学技术大学 | Phase-grouping line extraction method based on image processing unit |
| CN102496136B (en) * | 2011-12-08 | 2013-04-17 | 中国人民解放军国防科学技术大学 | Phase-grouping line extraction method based on image processing unit |
| CN103185560A (en) * | 2011-12-29 | 2013-07-03 | 鸿富锦精密工业（深圳）有限公司 | System and method for detecting circuit width of printed circuit board (PCB) |
| CN102589461A (en) * | 2012-01-17 | 2012-07-18 | 华中科技大学 | Image-based snow depth measuring method |
| CN104422832A (en) * | 2013-08-28 | 2015-03-18 | 深圳麦逊电子有限公司 | Network analysis method of PCB |
| CN104422832B (en) * | 2013-08-28 | 2017-04-19 | 深圳麦逊电子有限公司 | Network analysis method of PCB |
| CN103512501A (en) * | 2013-09-22 | 2014-01-15 | 电子科技大学 | Method for detecting manufacturing error of line width of microstrip line circuit on surface of ceramic substrate |
| CN103954223B (en) * | 2014-05-04 | 2017-01-11 | 杭州电子科技大学 | Outlet silk width measuring method based on double-camera millimeter level biology 3D printer |
| CN103954223A (en) * | 2014-05-04 | 2014-07-30 | 杭州电子科技大学 | Outlet silk width measuring method based on double-camera millimeter level biology 3D printer |
| CN106017328B (en) * | 2015-12-17 | 2019-03-05 | 广东正业科技股份有限公司 | A kind of polymorphic type line width measuring method and device |
| 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 |
| CN109215075B (en) * | 2017-06-30 | 2021-07-09 | 沈阳新松机器人自动化股份有限公司 | Positioning and identifying system and method for workpiece in material grabbing of industrial robot |
| CN109215075A (en) * | 2017-06-30 | 2019-01-15 | 沈阳新松机器人自动化股份有限公司 | The positioning identification system and method for workpiece in the crawl of industrial robot material |
| CN107588731A (en) * | 2017-09-30 | 2018-01-16 | 江西景旺精密电路有限公司 | A kind of pcb board line width measuring method and system |
| CN107588731B (en) * | 2017-09-30 | 2019-11-22 | 江西景旺精密电路有限公司 | A kind of pcb board line width measuring method and system |
| CN107917686A (en) * | 2017-12-18 | 2018-04-17 | 广州兴森快捷电路科技有限公司 | The method for detecting abnormality and device of printed wiring board |
| CN107917686B (en) * | 2017-12-18 | 2020-04-14 | 广州兴森快捷电路科技有限公司 | Method and device for detecting abnormality of printed wiring board |
| US11037287B2 (en) | 2018-05-09 | 2021-06-15 | Winbond Electronics Corp. | Method for measuring critical dimension and image-processing apparatus for measuring critical dimension |
| CN110553581B (en) * | 2018-06-01 | 2022-01-14 | 华邦电子股份有限公司 | Critical dimension measuring method and image processing device for measuring critical dimension |
| CN110553581A (en) * | 2018-06-01 | 2019-12-10 | 华邦电子股份有限公司 | critical dimension measuring method and image processing device for measuring critical dimension |
| CN109255795A (en) * | 2018-09-11 | 2019-01-22 | 中国计量大学 | A kind of tomato plant edge sort algorithm |
| CN109255795B (en) * | 2018-09-11 | 2021-04-06 | 中国计量大学 | Tomato plant edge sorting method |
| CN109349774A (en) * | 2018-10-29 | 2019-02-19 | 徐悦 | A kind of automatic manicure method and apparatus |
| CN109580652A (en) * | 2018-10-30 | 2019-04-05 | 广州超音速自动化科技股份有限公司 | A kind of quality of battery pole piece detection method, electronic equipment and storage medium |
| CN112541910A (en) * | 2020-12-23 | 2021-03-23 | 中国工程物理研究院机械制造工艺研究所 | End face gap detection method, device, equipment and medium based on deep learning |
| CN112541910B (en) * | 2020-12-23 | 2023-07-11 | 中国工程物理研究院机械制造工艺研究所 | End face gap detection method, device, equipment and medium based on deep learning |
| CN113533785A (en) * | 2021-07-22 | 2021-10-22 | 中国计量科学研究院 | Scanning electron microscope-based nano line width self-adaptive measurement method and system |
| CN114646265A (en) * | 2022-05-24 | 2022-06-21 | 四川英创力电子科技股份有限公司 | Detection device and method for precisely detecting line width on circuit board |
| CN114646265B (en) * | 2022-05-24 | 2022-07-22 | 四川英创力电子科技股份有限公司 | Detection device and method for precisely detecting line width on circuit board |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101303226A (en) | Method for measuring circuit board line width based on largest communication domain | |
| CN103091331B (en) | System and method for visual inspection on burrs and stain defects of radio frequency identification (RFID) antennae | |
| CN108982512A (en) | A kind of circuit board detecting system and method based on machine vision | |
| CN106127746A (en) | Circuit board element missing part detection method and system | |
| CN110473165A (en) | A kind of welding quality of circuit board detection method and device | |
| CN107392890B (en) | FPC copper wire surface oxidation defect detection method and detection system thereof | |
| CN110929720B (en) | Component detection method based on LOGO matching and OCR | |
| CN102988052B (en) | Method and system for measuring foot length | |
| CN109813727A (en) | A kind of pcb board weld defects detection method based on depth information | |
| CN110047063B (en) | Material drop detection method, device, equipment and storage medium | |
| CN115797359B (en) | Detection method, equipment and storage medium based on solder paste on circuit board | |
| JP2002039962A (en) | Method for inspecting electronic substrate and apparatus using the same | |
| CN104331695A (en) | Robust round identifier shape quality detection method | |
| CN106017328B (en) | A kind of polymorphic type line width measuring method and device | |
| CN111861980B (en) | Imaging detection method, electronic equipment and computer readable storage medium | |
| CN107369176A (en) | A kind of flexible IC substrates oxidation area detection system and method | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN102183206B (en) | Line width measuring method for line on printed circuit board (PCB) | |
| CN116337869A (en) | Machine vision-based detection system for production of double-sided circuit board | |
| CN110909735A (en) | Intelligent electric energy meter chip visual identification comparison system and method based on convolutional neural network | |
| CN101266135B (en) | Circuit board etching edge detection and etching factor measurement method | |
| CN113674260A (en) | SMT welding spot defect detection method | |
| CN111310402A (en) | Method for detecting defects of bare printed circuit board based on surface-to-surface parallelism | |
| CN110579184A (en) | Product appearance online detection device and use method thereof | |
| CN116310263A (en) | Pointer type aviation horizon instrument indication automatic reading implementation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20081112 |