CN101216438A - Printed circuit boards coarse defect image detection method based on FPGA - Google Patents
Printed circuit boards coarse defect image detection method based on FPGA Download PDFInfo
- Publication number
- CN101216438A CN101216438A CNA2008103001316A CN200810300131A CN101216438A CN 101216438 A CN101216438 A CN 101216438A CN A2008103001316 A CNA2008103001316 A CN A2008103001316A CN 200810300131 A CN200810300131 A CN 200810300131A CN 101216438 A CN101216438 A CN 101216438A
- Authority
- CN
- China
- Prior art keywords
- image data
- data
- printed circuit
- template
- grid
- 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
A method for detecting crude defect image of a printed circuit board based on FPGA comprises the following steps of: subjecting preprocessed template image data and the image data of the scanned printed circuit board to be detected to information extraction at the same proportion by using a field programmable gate array collection card; comparing the two image data after information extraction to obtain the difference, subjecting the difference image data and the template image data to binary morphologic operation corrosion, dividing grids, and removing fine characteristics of image data and keeping the larger characteristics; counting foreground pixels in each grid and respectively outputting data streams larger than, equal to and small than the template image data; and determining the desired characteristics and coordinates according to the output result, reducing the original coordinates of the large characteristics and determining large defect characteristics and coordinates of the printed circuit board. The invention can rapidly detect large defects of the printed circuit board in real time.
Description
(1) technical field
The present invention relates to a kind of optics automatic testing method of printed circuit board (PCB).
(2) background technology
In automated optical detection equipment and other machine vision equipments, need the defective that causes in the fast detecting P.e.c. board production technology.At present, known detection method is based on the simple logic computings such as adding, subtract of image, and is fairly simple to the analysis of operation result, be difficult to determine the difference between the image and determine its defect type, detection speed is slower, is difficult to realize the real-time processing to images acquired, influences detection efficiency.
(3) summary of the invention
The purpose of this invention is to provide a kind of printed circuit boards coarse defect image detection method, solve the technical matters that detects the big defective of printed circuit board (PCB) real-time based on FPGA.
For achieving the above object, the present invention adopts following technical scheme:
A kind of printed circuit boards coarse defect image detection method based on FPGA, applied optics capture, imaging device and analysis of image data disposal system, analysis of image data disposal system site of deployment programmable gate array capture card is characterized in that:
(1), with pretreated template image data with scan printed circuit board image data to be checked and carry out in proportion information extraction;
(2), two view data after extracting are compared, find out two differences between the view data, output template view data and differential image data synchronously, the differential image data comprise loses view data and unnecessary view data;
(3), differential image data and template image data are carried out the corrosion of two-value morphological operations;
(4), differential image data and template image data are carried out grid dividing, feature trickle on the view data is removed, kept bigger feature;
(5), with the grid be unit, add up the number of foreground pixel in each grid, and in comparing difference view data and the template image data in the corresponding grid through the foreground pixel data after the linear transformation, export greater than template image data respectively, equal template image data and less than the data stream of template image data;
(6), the result of the output feature and the coordinate thereof that determine to need, be negligible feature less than the data stream of template image data, reduce the original coordinates of big feature, and deliver in the report gatherer;
(7), make the big defect image examining report of printed circuit board (PCB), definite big defect characteristic of printed circuit board (PCB) and coordinate of detecting
In above-mentioned (1), elder generation imports through pretreated scan image, and the template image of angle that input process is again rotated and scan image is consistent carries out 4 * 4 sampling operation with scan-data and template data respectively again.
In above-mentioned (2), data stream through a capable Postponement module, make each data stream keep synchronously.
In above-mentioned (3), it is 5 * 5 two-value morphological operations that kernel is adopted in the corrosion of output stream;
In above-mentioned (4), grid dividing is that output stream is carried out the Mesh grid operations, they is divided into 10 * 10 grid and output.
In above-mentioned (5), the computing formula that above-mentioned view data relatively adopts is as follows:
Compare?Type0 Compare?Type1
S
0D
0+O
0＜S
1D
1+O
1 S
1D
1+O
1＜S
0D
0+O
0
S
0D
0+O
0＝S
1D
1+O
1 S
1D
1+O
1＝S
0D
0+O
0
S
0D
0+O
0＞S
1D
1+O
1 S
1D
1+O
1＞S
0D
0+O
0
Wherein Dx is the value of the number of pixels of input, and Sx is a zoom factor, and Ox is an off-set value.
A kind of printed circuit boards coarse defect image detecting system based on FPGA, comprise optical image-taking, imaging device and analysis of image data disposal system, it is characterized in that: the analysis of image data disposal system comprises a field programmable gate array capture card that contains configurable logic block, storer, digital dock administration module, interface module and interconnected wiring, wherein, there is template image data in the storer; Configurable logic block comprises connection in turn: data extract processor module, comparator module, row delay output module, pictorial data binarization block, grid dividing module, calculator modules and characteristic processing device module in proportion.
Compared with prior art the present invention has following characteristics and beneficial effect:
Site of deployment programmable gate array of the present invention (FPGA), FPGA are based on the programmable semiconductor capture card of configurable logic block (CLB) matrix by interconnected connection able to programme.The present invention uses FPGA that data are carried out fast parallel processing, discharges effective software resource, for main frame provides more wide resource space, thereby increases work efficiency greatly.The Gross algorithm of this image operation provided by the invention by using the grid skill, carries out the otherwise effective technique analysis to variance data, realized the accurate judgement of characteristic type, has reduced the erroneous judgement in the testing process and fails to judge.
(4) description of drawings
The present invention will be further described in detail below in conjunction with accompanying drawing.
Fig. 1 is the embodiment synoptic diagram after printed circuit board (PCB) area image to be measured extracts.
Fig. 2 is the synoptic diagram that the image after extracting carries out grid dividing embodiment;
Fig. 3 is a FPGA design flow diagram of the present invention.
Fig. 4 is a grid dividing embodiment synoptic diagram.
Fig. 5 is the FPGA design drawing of comparison module.
(5) embodiment
Embodiment: the present invention downloads to the FPGA programmable gate array by the description of use Hardware Description Language VHDL implementation algorithm, adopts and based on gridding technique image is analyzed fast and effectively, handled, and the effective fast and result's of assurance algorithm is accurate.
Fig. 6 is the process flow diagram of the novel Gross algorithm based on FPGA provided by the invention, and this method may further comprise the steps:
Step 1: as shown in Figure 1, in comparison module, input traffic and parameter, input through pretreated scan image data and with the be consistent template image data of angle of scan image, wait pending.
Step 2: as shown in Figure 2, respectively scan-data and template data are carried out 4 * 4 sampling operation, so algorithm mainly detects big defective, can ignore,, reduce data volume, raise the efficiency so image is sampled for fine feature.
Step 3: view data and template image data after will sampling are done logical operation, compare roughly, obtain the difference of two view data, synchronous output template data GC and differential image data, variance data comprises disappearance view data GM and unnecessary view data GA.
Step 4: template data and differential image data postpone to keep synchronously through space.Data stream makes each data stream keep synchronously through a capable Postponement module of Row Delay.
Step 5: template data and differential image data are carried out the corrosion of two-value morphological operations.Three output streams are corroded, and the employing kernel is 5 * 5 two-value morphological operations, and feature trickle on the view data is removed, and keeps bigger feature.
Step 6: template data and differential image data are carried out grid dividing.As shown in Figure 4, use Mesh grid generator, above-mentioned three data streams are carried out the operation of Mesh grid dividing, they are divided into 10 * 10 grid and output, the size of grid can change according to actual needs.
Among Fig. 3, GM-lacks view data, GC-template data, the unnecessary view data of GA-, row postpones: in FPGA, data stream is a stream, has only data line, needs 5 row to handle together when still handling, so before handling, need to go delay, early the data that arrive stay for some time in this module, when 5 row all arrive, carry out single treatment.
Step 7: as shown in Figure 5, be unit, compare the processing of Compare module with the grid.For two view data to be compared, add up the number of pixels Dx of prospect in each grid respectively, parameter S eale0, Seale1, offset0 and offset1 according to input, Dx carries out linear transformation, data after the more corresponding grid inner conversion, export comparative result respectively: greater than, equal, less than data stream.The grid dividing technology of Fig. 4: hypothetical trellis is of a size of 10 pixels * 10 pixels, and then the image of 30 pixels * 30 pixels is done above-mentioned division, and each grid is 10 pixels * 10 pixels, and each grid is handled as a unit.
Compare?Type0 Compare?Type?1
S
0D
0+O
0＜S
1D
1+O
1 S
1D
1+O
1＜S
0D
0+O
0
S
0D
0+O
0＝S
1D
1+O
1 S
1D
1+O
1＝S
0D
0+O
0
S
0D
0+O
0＞S
1D
1+O
1 S
1D
1+O
1＞S
0D
0+O
0
Wherein Dx is the value of the number of pixels of input, and Sx is a zoom factor, and Ox is an off-set value.
Step 8: data stream is compared, relatively lack feature and redundant character.Export greater than type respectively, equal type and less than the data stream of type.According to output stream, greater than with equal output stream and be defined as big feature, be negligible feature less than output stream.
Step 9: reduce the original coordinates of big feature, deliver in the report gatherer and generate examining report.
Claims (7)
1. printed circuit boards coarse defect image detection method based on FPGA, applied optics capture, imaging device and analysis of image data disposal system, analysis of image data disposal system site of deployment programmable gate array capture card is characterized in that:
(1), with pretreated template image data with scan printed circuit board image data to be checked and carry out in proportion information extraction;
(2), two view data after extracting are compared, find out two differences between the view data, output template view data and differential image data synchronously, the differential image data comprise loses view data and unnecessary view data;
(3), differential image data and template image data are carried out the corrosion of two-value morphological operations;
(4), differential image data and template image data are carried out grid dividing, feature trickle on the view data is removed, kept bigger feature;
(5), with the grid be unit, add up the number of foreground pixel in each grid, and in comparing difference view data and the template image data in the corresponding grid through the foreground pixel data after the linear transformation, export greater than template image data respectively, equal template image data and less than the data stream of template image data;
(6), the result of the output feature and the coordinate thereof that determine to need, be negligible feature less than the data stream of template image data, reduce the original coordinates of big feature, and deliver in the report gatherer;
(7), make the big defect image examining report of printed circuit board (PCB), definite big defect characteristic of printed circuit board (PCB) and coordinate of detecting
2. the printed circuit boards coarse defect image detection method based on FPGA according to claim 1, it is characterized in that: in above-mentioned (1), input is through pretreated scan image earlier, the template image of angle that input process is again rotated and scan image is consistent carries out 4 * 4 sampling operation with scan-data and template data respectively again.
3. the printed circuit boards coarse defect image detection method based on FPGA according to claim 1 is characterized in that: in above-mentioned (2), data stream through a capable Postponement module, make each data stream keep synchronously.
4. the printed circuit boards coarse defect image detection method based on FPGA according to claim 1 is characterized in that: in above-mentioned (3), it is 5 * 5 two-value morphological operations that kernel is adopted in the corrosion of output stream.
5. the printed circuit boards coarse defect image detection method based on FPGA according to claim 1 is characterized in that: in above-mentioned (4), grid dividing is that output stream is carried out the Mesh grid operations, they is divided into 10 * 10 grid and output.
6. the printed circuit boards coarse defect image detection method based on FPGA according to claim 1 is characterized in that: in above-mentioned (5), the computing formula that above-mentioned view data relatively adopts is as follows:
Compare?Type0 Compare?Type?1
S0D0+O0＜S1D1+01?S1D1+O1＜S0D0+00
S0D0+O0＝S1D1+01?S1D1+O1＝S0D0+00
S0D0+O0＞S1D1+01?S1D1+O1＞S0D0+00
Wherein Dx is the value of the number of pixels of input, and Sx is a zoom factor, and Ox is an off-set value.
7. printed circuit boards coarse defect image detecting system based on FPGA, comprise optical image-taking, imaging device and analysis of image data disposal system, it is characterized in that: the analysis of image data disposal system comprises a field programmable gate array capture card that contains configurable logic block, storer, digital dock administration module, interface module and interconnected wiring, wherein, there is template image data in the storer; Configurable logic block comprises connection in turn: data extract processor module, comparator module, row delay output module, pictorial data binarization block, grid dividing module, calculator modules and characteristic processing device module in proportion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008103001316A CN101216438B (en) | 2008-01-16 | 2008-01-16 | Printed circuit boards coarse defect image detection method based on FPGA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008103001316A CN101216438B (en) | 2008-01-16 | 2008-01-16 | Printed circuit boards coarse defect image detection method based on FPGA |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101216438A true CN101216438A (en) | 2008-07-09 |
| CN101216438B CN101216438B (en) | 2010-09-08 |
Family
ID=39622916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008103001316A Expired - Fee Related CN101216438B (en) | 2008-01-16 | 2008-01-16 | Printed circuit boards coarse defect image detection method based on FPGA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101216438B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565073A (en) * | 2011-12-31 | 2012-07-11 | 北京航空航天大学 | Portable FPGA (Field Programmable Gate Array)-based rapid detection device of circuit board defects |
| CN103106663A (en) * | 2013-02-19 | 2013-05-15 | 公安部第三研究所 | Method for detecting defect of subscriber identity module (SIM) card based on image processing in computer system |
| CN103543151A (en) * | 2013-09-29 | 2014-01-29 | 广东工业大学 | Measurement method of PCB (printed circuit board) based on microsection binary image |
| CN104422832A (en) * | 2013-08-28 | 2015-03-18 | 深圳麦逊电子有限公司 | Network analysis method of PCB |
| CN106778879A (en) * | 2015-09-23 | 2017-05-31 | 英特美克技术公司 | Evaluation image |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN111443096A (en) * | 2020-04-03 | 2020-07-24 | 联觉(深圳)科技有限公司 | Method and system for detecting defects of printed circuit board, electronic device and storage medium |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
| CN116228746A (en) * | 2022-12-29 | 2023-06-06 | 摩尔线程智能科技(北京)有限责任公司 | Defect detection method, device, electronic apparatus, storage medium, and program product |
-
2008
- 2008-01-16 CN CN2008103001316A patent/CN101216438B/en not_active Expired - Fee Related
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565073A (en) * | 2011-12-31 | 2012-07-11 | 北京航空航天大学 | Portable FPGA (Field Programmable Gate Array)-based rapid detection device of circuit board defects |
| CN102565073B (en) * | 2011-12-31 | 2013-08-28 | 北京航空航天大学 | Portable FPGA (Field Programmable Gate Array)-based rapid detection device of circuit board defects |
| CN103106663A (en) * | 2013-02-19 | 2013-05-15 | 公安部第三研究所 | Method for detecting defect of subscriber identity module (SIM) card based on image processing in computer system |
| CN103106663B (en) * | 2013-02-19 | 2015-12-09 | 公安部第三研究所 | Realize the method for SIM card defects detection based on image procossing in computer system |
| 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 |
| CN103543151A (en) * | 2013-09-29 | 2014-01-29 | 广东工业大学 | Measurement method of PCB (printed circuit board) based on microsection binary image |
| CN103543151B (en) * | 2013-09-29 | 2017-04-05 | 广东工业大学 | A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image |
| CN106778879A (en) * | 2015-09-23 | 2017-05-31 | 英特美克技术公司 | Evaluation image |
| CN106778879B (en) * | 2015-09-23 | 2022-06-03 | 英特美克技术公司 | Evaluating images |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN109376770B (en) * | 2018-09-26 | 2020-10-20 | 凌云光技术集团有限责任公司 | Grid area identification method and device applied to negative film inspection machine |
| CN111443096A (en) * | 2020-04-03 | 2020-07-24 | 联觉(深圳)科技有限公司 | Method and system for detecting defects of printed circuit board, electronic device and storage medium |
| CN111443096B (en) * | 2020-04-03 | 2023-05-30 | 联觉(深圳)科技有限公司 | Method, system, electronic device and storage medium for detecting defect of printed circuit board |
| CN116228746A (en) * | 2022-12-29 | 2023-06-06 | 摩尔线程智能科技(北京)有限责任公司 | Defect detection method, device, electronic apparatus, storage medium, and program product |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101216438B (en) | 2010-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101216438B (en) | Printed circuit boards coarse defect image detection method based on FPGA | |
| CN102044071A (en) | Single-pixel margin detection method based on FPGA | |
| CN101216522A (en) | FPGA based printed circuit board rapid image feature value extraction detection method | |
| CN105160654A (en) | Towel label defect detecting method based on feature point extraction | |
| CN101912847B (en) | Fruit grading system and method based on DSP machine vision | |
| CN204924967U (en) | Image acquisition mechanism of full -automatic AOI complete machine | |
| CN100390530C (en) | Image type online flaws detection equipment in line array for surface of strip steel, and detection method | |
| CN112651966A (en) | Printed circuit board micro-defect detection method based on ACYOLOV4_ CSP | |
| WO2022017197A1 (en) | Intelligent product quality inspection method and apparatus | |
| CN1815489A (en) | Intelligent image counting method | |
| CN101221439A (en) | Embedded system for high speed parallel duplex digital image capturing and processing | |
| CN202444572U (en) | Non-reference video monitoring image blurring quality detection device | |
| CN111695493A (en) | Method and system for detecting hidden danger of power transmission line | |
| CN115249237A (en) | Defect detection method, defect detection apparatus, and computer-readable storage medium | |
| Zhang et al. | Gesture recognition system based on improved YOLO v3 | |
| CN109657682B (en) | Electric energy representation number identification method based on deep neural network and multi-threshold soft segmentation | |
| CN113506281A (en) | Bridge crack detection method based on deep learning framework | |
| Demirci et al. | Defective PV cell detection using deep transfer learning and EL imaging | |
| CN206891989U (en) | Paper defects data acquisition device and the real-time detection using the device and reponse system | |
| CN113487570A (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
| CN101221135B (en) | Printed circuit board image skeletonization method based on FPGA | |
| CN112116600A (en) | Photovoltaic panel counting method based on image processing | |
| CN105548210A (en) | Detection method for American-standard power source extension wire based on machine vision | |
| CN112903701A (en) | Automatic detection system for surface defects of solar cell panel |
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 | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100908 Termination date: 20140116 |