CN102914549A - Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality - Google Patents
Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality Download PDFInfo
- Publication number
- CN102914549A CN102914549A CN2012103321679A CN201210332167A CN102914549A CN 102914549 A CN102914549 A CN 102914549A CN 2012103321679 A CN2012103321679 A CN 2012103321679A CN 201210332167 A CN201210332167 A CN 201210332167A CN 102914549 A CN102914549 A CN 102914549A
- Authority
- CN
- China
- Prior art keywords
- image
- ccd
- under test
- correlation
- element under
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality. The method is that an image is partitioned, a block is taken as a unit for matching detection, the method has good real-time performance, and the online detection requirements can be satisfied. The specific process is that a template image which is suitable for a current element to be measured is searched from a standard database according to the PCB information of the element to be measured; the detection image of the element to be detected is obtained; the template image and the detection image are partitioned; and the relevancy of the two images is judged, and when the relevancy meets the threshold, whether the soldering joints of the image to be detected meet the requirements or not is judged. The partitioning process is carried out on the image on the basis of relevancy matching, so that the method not only has high matching success rate, but also greatly saves the computation time, and the real-time performance is improved; and a partitioning relevancy matching algorithm is simple and efficient and is easy to realize, and the method which is realized on the basis of the algorithm and is used for detecting the satellite-borne PCB soldering joint quality has good practicability.
Description
Technical field
The present invention relates to a kind of optical imagery matching detection method for spaceborne expression type printed circuit board (Printed Circuit Board, PCB) quality of welding spot, belong to quality of welding spot detection technique field.
Background technology
At present, in the electronic equipment, expression type number of welds accounts for more than 80%, detection means mainly is the artificial visually examine's optical detection apparatus of certain enlargement factor (in case of necessity by), the impact of the objective factors such as industrial AOI (Automated Optical Inspection) the examined standard of system is not applied in the production run of space product.The desk checking existence is affected by the human factors such as operator's experience, degree of fatigue and subjective sensation, do not have unified differentiation quantitative criteria, result of determination varies with each individual, and the consistance of criterion is relatively poor, be difficult to guarantee that 100% of solder joint detects, be easy to occur undetected.。
Industry AOI system mainly adopts feature extraction comparison or every pixel interdependence than reciprocity method, such as " the circuit board plate carries the research of components and parts detection system " of the Zhang Jiling of Northwestern Polytechnical University.These algorithm complexity or cycle index are too much, and it is not very high causing real-time, can not be fit to well that needs are online to be detected and test item is many, the demanding space product detection field of detection accuracy.
Summary of the invention
The purpose of this invention is to provide a kind of optical imagery matching detection method for spaceborne expression type PCB quality of welding spot, the method is carried out matching detection by image is carried out piecemeal take piece as the unit, and its real-time is good, can satisfy the needs of online detection.
A kind of optical imagery matching detection method for spaceborne expression type PCB quality of welding spot, concrete step is:
Step 101, from standard database, seek the template image that is fit to current element under test according to the PCB information of element under test;
Step 102, make CCD be positioned at the dead ahead of element under test, and adjust the spacing of CCD and element under test, so that element under test big or small identical on the size of element under test and the template image on the image that CCD gathers; CCD gathers the element under test image, and it is defined as image to be checked;
Step 103, be that w * h, form are that the template image of RGB24 converts 8 constant gray level images of size to size first; Template image is divided into m * n image block, each block size is b * b again, i.e. m=w/b, n=h/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix P of m * n;
Step 104, be that W * H, form are that the image transitions to be checked of RGB24 becomes 8 constant gray level images of size with size; Image to be checked is divided into M * N image block, each block size is b * b again, i.e. M=W/b, N=H/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix Q of M * N;
Step 105, the initial point of two matrixes overlaps when initial, and then order matrix P is in the enterprising line slip of matrix Q, and every slip once calculates the degree of correlation between two matrixes
When the degree of correlation that calculates during less than setting threshold, stop to slide, judge that the solder joint of this image to be checked meets the demands, otherwise continue to slide, when all relative position situations of sliding, the degree of correlation of two matrixes still is not less than setting threshold, judges that then the solder joint of image to be checked does not meet the demands.
When element under test is too large, in the time of all details of element under test can't being represented, gather multiple image by mobile CCD in the piece image that CCD gathers, and multiple image is spliced, obtain image to be checked, the acquisition process of this image to be checked is:
In the whole splicing CCD according to from top to bottom, the image of from left to right acquisition order element under test;
Step 201, first width of cloth (being the image in the element under test lower left corner) that CCD is gathered with the image of seasonal CCD collection the next position, and enter step 202 as the benchmark image of splicing;
Step 202, judge whether the image that CCD gathers is the image of element under test left column, if then enter step 203, otherwise enter step 204;
Step 203, the image that gathers take current C CD is as template image, take its lower images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S mobile minimum degree of correlation that obtains of preset times be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position;
Step 204, the image that gathers take current C CD is as template image, take its left-side images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S the mobile minimum degree of correlation that obtains be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position;
Step 205, judge whether image to be checked is spliced in institute complete, if imperfect, the image of CCD collection the next position then, and return step 202.
Beneficial effect
The present invention has carried out the piecemeal processing to image on the basis of relevant matches, both guaranteed the high success rate of coupling, saves computing time in a large number again, has improved real-time; Piecemeal relevant matches algorithm of the present invention is simply efficient, is easy to realize, the spaceborne PCB quality of welding spot detection method that realizes on its basis has good practicality.
Secondly, the present invention is directed to larger detecting element, use degree of correlation matching method that the element under test image of multi collect is spliced, so that the present invention is used in the detection to the quality of welding spot of larger element.
Description of drawings
Fig. 1 is the process flow diagram of the optical imagery matching detection method of PCB quality of welding spot.
Fig. 2 is the schematic diagram of image to be checked and template image shiding matching.
Embodiment
The present invention is described in detail below in conjunction with the drawings and specific embodiments.
As shown in Figure 1, the present invention is directed to the optical imagery matching detection method of spaceborne expression type PCB quality of welding spot, concrete step is:
Step 101, from standard database, seek the template image that is fit to current element under test according to the PCB information of element under test.
The template image that has various elements on the standard database, and the element on this template image all be the welding good, template image is obtained by a large amount of samplings.Therefore the present invention chooses the template image of element under test from standard database, so that ensuing coupling is used.
Step 102, make CCD be positioned at the dead ahead of element under test, and adjust the spacing of CCD and element under test, so that element under test big or small identical on the size of element under test and the template image on the image that CCD gathers; CCD gathers the element under test image, and it is defined as image to be checked;
The condition that the present invention uses is: light-source brightness is uniform and stable, CCD need demarcate, distance must meet the demands between CCD camera and the PCB, that is: element under test big or small identical on the size of element under test and the template image on the image that gathers of CCD, image to be checked like this and template image just have the value of matching judgment quality of welding spot quality; The present invention determines distance between CCD and the element under test by eye-observation.
Step 103, be that w * h, form are that the template image of RGB24 converts 8 constant gray level images of size to size first; Template image is divided into m * n image block, each block size is b * b again, i.e. m=w/b, n=h/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix P of m * n.W in this process, h, m, n, b are constant.
The present invention carries out piecemeal with image, then carries out follow-up judgement as the unit take image block, and compared with prior art, the present invention can improve the speed of coupling, satisfies the requirement of real-time, can improve the accuracy of coupling simultaneously.
Matrix P of the present invention is retrieved as: with the pixel average of the image block of the first row first row asked for as matrix P position (1,1) value on, with the pixel average of the image block of the first row secondary series asked for as matrix P position (1,2) value on, with the pixel value mean value of the image block of the second row first row of asking for as matrix P position (2,1) value on, and the like.
Step 104, be that W * H, form are that the image transitions to be checked of RGB24 becomes 8 constant gray level images of size with size; Image to be checked is divided into M * N image block, each block size is b * b again, i.e. M=W/b, N=H/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix Q of M * N.W in this process, H, N, M are constant.
Therefore the present invention need to also carry out the conversion the same with template image with image to be checked in order to carry out images match as the unit take image block.
Matrix Q of the present invention is retrieved as: with the pixel average of the image block of the first row first row asked for as matrix Q position (1,1) value on, with the pixel average of the image block of the first row secondary series asked for as matrix Q position (1,2) value on, with the pixel value mean value of the image block of the second row first row of asking for as matrix Q position (2,1) value on, and the like.
Step 105, the initial point of two matrixes overlaps when initial, and then order matrix P is in the enterprising line slip of matrix Q, and every slip once calculates the degree of correlation between two matrixes
When the degree of correlation that calculates during less than setting threshold, stop to slide, judge that the solder joint of this image to be checked meets the demands, otherwise continue to slide, when all relative position situations of sliding, the degree of correlation of two matrixes still is not less than setting threshold, judges that then the solder joint of image to be checked does not meet the demands.
Generally, if element to be checked hour, the image to be checked that gather this moment is usually greater than template image, so the present invention makes image to be checked motionless, makes template image slide at image to be checked, asks for the degree of correlation between two images, as shown in Figure 2.Template image along continuous straight runs and vertical direction slide, and there is multiple relative position situation in the distance of the image block that at every turn slides at two width of cloth images like this.Then to every slip once the degree of correlation and the threshold value of setting compare, wherein threshold value is to draw according to a large amount of tests.The present invention can be better make template image according to from left to right, whether order from top to bottom moves, seek in two width of cloth images to exist the degree of correlation less than the situation of setting threshold.
The present invention when element under test too large, in the time of all details of element under test can't being represented in the piece image that CCD gathers, need to gather multiple image by mobile CCD, and multiple image is spliced, obtain image to be checked, the acquisition process of this image to be checked is:
In the whole splicing CCD according to from top to bottom, the image of from left to right acquisition order element under test; Can guarantee in this order to have correlativity between the two adjacent width of cloth images that CCD gathers.
Step 201, first width of cloth (being the image in the element under test lower left corner) that CCD is gathered with the image of seasonal CCD collection the next position, and enter step 202 as the benchmark image of splicing.
Step 202, judge whether the image that CCD gathers is the image of element under test left column, if then enter step 203, otherwise enter step 204.
The element of a strip when element under test, be that its upper edge and lower edge can be included in piece image, the second width of cloth image of CCD collection is the image of non-element under test left column like this, therefore be to have the zone that overlaps on the right side of the first width of cloth image and the left side of the second width of cloth image, enter step 204 and carry out Image Mosaics this moment.When length and the width of element under test are suitable, namely its upper edge and lower edge can't be included in piece image, and the second width of cloth image of gathering of CCD is the image of element under test left column like this, and need to enter step 203 and carry out Image Mosaics this moment.
Step 203, the image that gathers take current C CD is as template image, take its lower images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S the mobile minimum degree of correlation that obtains be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position.
Step 204, the image that gathers take current C CD is as template image, take its left-side images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S the mobile minimum degree of correlation that obtains be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position.
S is the integer of setting in advance in step 203 and the step 204, in theory, there is the position of accurate coupling certainly in adjacent two width of cloth images that CCD gathers, the match is successful when still not having for mobile S time, then may be because the variation of the adjacent twice collection image-context of CCD is caused, cause such as factors such as blocking of light, this moment CCD Resurvey piece image, until search out till the best stitching position.
Step 205, judge whether image to be checked is spliced in institute complete, if imperfect, the image of CCD collection the next position then, and return step 202.
If this moment splicing is finished, then can enter step 103 pair image to be checked this moment and template image is processed, calculate the degree of correlation, and judge the quality of solder joint.
The method is applied to the Rough Inspection stage that spaceborne PCB quality of welding spot detects, can be to Component Displacement, Short Item, wrong part, many tin, few tin, connect tin, set up a monument, the projects such as breakage, upset detect, higher real-time and reliability are arranged, for the examining stage of utilizing the 3 D stereo microscope to carry out is carried out the basis.
In sum, above is preferred embodiment of the present invention only, is not for limiting protection scope of the present invention.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (2)
1. the optical imagery matching detection method for spaceborne expression type PCB quality of welding spot is characterized in that, concrete step is:
Step 101, from standard database, seek the template image that is fit to current element under test according to the PCB information of element under test;
Step 102, make CCD be positioned at the dead ahead of element under test, and adjust the spacing of CCD and element under test, so that element under test big or small identical on the size of element under test and the template image on the image that CCD gathers; CCD gathers the element under test image, and it is defined as image to be checked;
Step 103, be that w * h, form are that the template image of RGB24 converts 8 constant gray level images of size to size first; Template image is divided into m * n image block, each block size is b * b again, i.e. m=w/b, n=h/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix P of m * n;
Step 104, be that W * H, form are that the image transitions to be checked of RGB24 becomes 8 constant gray level images of size with size; Image to be checked is divided into M * N image block, each block size is b * b again, i.e. M=W/b, N=H/b; Ask the pixel average of each image block, obtain size and be the pixel average matrix Q of M * N;
Step 105, the initial point of two matrixes overlaps when initial, then order matrix P is in the enterprising line slip of matrix Q, every slip once calculates the degree of correlation between two matrixes, when the degree of correlation that calculates during less than setting threshold, stop to slide, the solder joint of judging this image to be checked meets the demands, otherwise continues to slide, when all relative position situations of sliding, the degree of correlation of two matrixes still is not less than setting threshold, judges that then the solder joint of image to be checked does not meet the demands.
2. the optical imagery matching detection method of described quality of welding spot according to claim 1, it is characterized in that, when element under test too large, in the time of all details of element under test can't being represented in the piece image that CCD gathers, need to gather multiple image by mobile CCD, and multiple image spliced, obtaining image to be checked, the acquisition process of this image to be checked is:
In the whole splicing CCD according to from top to bottom, the image of from left to right acquisition order element under test;
Step 201, first width of cloth that CCD is gathered gather the image of the next position, and enter step 202 as the benchmark image of splicing with seasonal CCD;
Step 202, judge whether the image that CCD gathers is the image of element under test left column, if then enter step 203, otherwise enter step 204;
Step 203, the image that gathers take current C CD is as template image, take its lower images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S the mobile minimum degree of correlation that obtains be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position;
Step 204, the image that gathers take current C CD is as template image, take its left-side images as target image, a pixel overlaps with a pixel on the target image on the selected template image, respectively to upper right, the bottom right, upper left, lower-left movable platen image, the degree of correlation of two picture registration positions is once calculated in every movement, judge that whether S the mobile minimum degree of correlation that obtains be less than setting threshold, if, the position relationship of two images is defined as the best stitching position of two width of cloth images during then with the minimum degree of correlation, two width of cloth images are spliced by best stitching position, otherwise again obtain a width of cloth ccd image and calculate the degree of correlation again, until two width of cloth images splice with best stitching position;
Step 205, judge whether image to be checked is spliced in institute complete, if imperfect, the image of CCD collection the next position then, and return step 202.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210332167.9A CN102914549B (en) | 2012-09-10 | 2012-09-10 | Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210332167.9A CN102914549B (en) | 2012-09-10 | 2012-09-10 | Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102914549A true CN102914549A (en) | 2013-02-06 |
| CN102914549B CN102914549B (en) | 2015-03-25 |
Family
ID=47613011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210332167.9A Active CN102914549B (en) | 2012-09-10 | 2012-09-10 | Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102914549B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104535587A (en) * | 2014-12-23 | 2015-04-22 | 安徽科鸣三维科技有限公司 | PCBA solder joint inspection method based on machine vision |
| CN105184793A (en) * | 2015-09-02 | 2015-12-23 | 广东电网有限责任公司汕尾供电局 | Electric energy meter sample appearance and PCB element detection method |
| CN105389818A (en) * | 2015-11-12 | 2016-03-09 | 广州视源电子科技股份有限公司 | Method and system for positioning element |
| CN106651802A (en) * | 2016-12-24 | 2017-05-10 | 大连日佳电子有限公司 | Machine vision tin soldering location detection method |
| WO2017092427A1 (en) * | 2015-12-04 | 2017-06-08 | 广州视源电子科技股份有限公司 | Electronic element positioning method and apparatus |
| CN111369599A (en) * | 2018-12-25 | 2020-07-03 | 阿里巴巴集团控股有限公司 | Image matching method, device and apparatus and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6771807B2 (en) * | 2000-01-18 | 2004-08-03 | Solvision Inc. | Method and system for detecting defects on a printed circuit board |
| CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
| CN101334266A (en) * | 2008-07-18 | 2008-12-31 | 北京优纳科技有限公司 | Circuit board defect off-line checking method based on large-capacity image storage technology |
| JP2010159035A (en) * | 2009-01-09 | 2010-07-22 | Nippon Plast Co Ltd | Cover body of airbag device and airbag device |
| CN101895693A (en) * | 2010-06-07 | 2010-11-24 | 北京高森明晨信息科技有限公司 | Method and device for generating panoramic image |
| CN101901481A (en) * | 2010-08-11 | 2010-12-01 | 深圳市蓝韵实业有限公司 | Image mosaic method |
| JP2011059035A (en) * | 2009-09-14 | 2011-03-24 | Toshiba Corp | Pattern inspection device and method for manufacturing structure having pattern |
| CN201886521U (en) * | 2010-04-16 | 2011-06-29 | 广东工业大学 | Fast image splicing system |
| CN101477066B (en) * | 2009-01-09 | 2012-02-01 | 华南理工大学 | Circuit board element mounting/welding quality detection method and system based on super-resolution image reconstruction |
| CN102486831A (en) * | 2010-12-03 | 2012-06-06 | 江南大学 | Gray level image correlation matching algorithm for digital signal processor |
| CN102486829A (en) * | 2010-12-01 | 2012-06-06 | 鸿富锦精密工业（深圳）有限公司 | Image analysis system and method |
-
2012
- 2012-09-10 CN CN201210332167.9A patent/CN102914549B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6771807B2 (en) * | 2000-01-18 | 2004-08-03 | Solvision Inc. | Method and system for detecting defects on a printed circuit board |
| CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
| CN101334266A (en) * | 2008-07-18 | 2008-12-31 | 北京优纳科技有限公司 | Circuit board defect off-line checking method based on large-capacity image storage technology |
| JP2010159035A (en) * | 2009-01-09 | 2010-07-22 | Nippon Plast Co Ltd | Cover body of airbag device and airbag device |
| CN101477066B (en) * | 2009-01-09 | 2012-02-01 | 华南理工大学 | Circuit board element mounting/welding quality detection method and system based on super-resolution image reconstruction |
| JP2011059035A (en) * | 2009-09-14 | 2011-03-24 | Toshiba Corp | Pattern inspection device and method for manufacturing structure having pattern |
| CN201886521U (en) * | 2010-04-16 | 2011-06-29 | 广东工业大学 | Fast image splicing system |
| CN101895693A (en) * | 2010-06-07 | 2010-11-24 | 北京高森明晨信息科技有限公司 | Method and device for generating panoramic image |
| CN101901481A (en) * | 2010-08-11 | 2010-12-01 | 深圳市蓝韵实业有限公司 | Image mosaic method |
| CN102486829A (en) * | 2010-12-01 | 2012-06-06 | 鸿富锦精密工业（深圳）有限公司 | Image analysis system and method |
| CN102486831A (en) * | 2010-12-03 | 2012-06-06 | 江南大学 | Gray level image correlation matching algorithm for digital signal processor |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104535587A (en) * | 2014-12-23 | 2015-04-22 | 安徽科鸣三维科技有限公司 | PCBA solder joint inspection method based on machine vision |
| CN105184793A (en) * | 2015-09-02 | 2015-12-23 | 广东电网有限责任公司汕尾供电局 | Electric energy meter sample appearance and PCB element detection method |
| CN105184793B (en) * | 2015-09-02 | 2018-01-16 | 广东电网有限责任公司汕尾供电局 | A kind of electric energy meter sample appearance and pcb board element testing method |
| CN105389818A (en) * | 2015-11-12 | 2016-03-09 | 广州视源电子科技股份有限公司 | Method and system for positioning element |
| WO2017080295A1 (en) * | 2015-11-12 | 2017-05-18 | 广州视源电子科技股份有限公司 | Element positioning method and system |
| CN105389818B (en) * | 2015-11-12 | 2018-11-27 | 广州视源电子科技股份有限公司 | The localization method and system of element |
| WO2017092427A1 (en) * | 2015-12-04 | 2017-06-08 | 广州视源电子科技股份有限公司 | Electronic element positioning method and apparatus |
| CN106651802A (en) * | 2016-12-24 | 2017-05-10 | 大连日佳电子有限公司 | Machine vision tin soldering location detection method |
| CN106651802B (en) * | 2016-12-24 | 2019-10-18 | 大连日佳电子有限公司 | Machine vision scolding tin position finding and detection method |
| CN111369599A (en) * | 2018-12-25 | 2020-07-03 | 阿里巴巴集团控股有限公司 | Image matching method, device and apparatus and storage medium |
| CN111369599B (en) * | 2018-12-25 | 2024-04-16 | 阿里巴巴集团控股有限公司 | Image matching method, device, apparatus and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102914549B (en) | 2015-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102914549B (en) | Optical image matching detection method aiming at satellite-borne surface exposed printed circuit board (PCB) soldering joint quality | |
| Di Leo et al. | A vision system for the online quality monitoring of industrial manufacturing | |
| CN105538345B (en) | A kind of puma manipulator and positioning assembly method based on many camera lenses | |
| CN105571502B (en) | The measurement method of weld gap in Friction Stir Welding | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| CN108469437B (en) | Method and device for detecting defects of float glass | |
| DE102014217361B4 (en) | DETERMINING THE SOURCE TRACK OF A MOVING ELEMENT THAT WILL BE MERGED WITH THE DESTINATION TRACK | |
| CN104636760A (en) | Positioning method for welding seam | |
| CN106623493A (en) | Detection method for continuous punching of steel band | |
| CN104198324A (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
| CN104483331A (en) | Three-dimensional detection method, three-dimensional detection device and three-dimensional detection system for connector contact pin | |
| CN106501272A (en) | Machine vision scolding tin position detecting system | |
| CN105139384B (en) | The method and apparatus of defect capsule detection | |
| CN104198325A (en) | Method for measuring ratio of cut stem to cut tobacco based on computer vision | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN102074031A (en) | Standard establishment method for observational check machine of printed circuit board | |
| CN109300125A (en) | Municipal rail train pantograph pan image zooming-out algorithm under a kind of complex environment | |
| CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
| CN206470205U (en) | Machine vision scolding tin assisted detection system | |
| CN111665249B (en) | Light intensity adjusting method and system and optical detection equipment | |
| CN104019752B (en) | The thickness evenness detection method of display screen, Apparatus and system | |
| TWI312705B (en) | ||
| CN105424708B (en) | Plate glass insurance fiber tube fusable links mass defect detection method | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN205620320U (en) | Defect detecting device based on multitube foot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |