CN106651849A - Area-array camera-based PCB bare board defect detection method - Google Patents
Area-array camera-based PCB bare board defect detection method Download PDFInfo
- Publication number
- CN106651849A CN106651849A CN201611227887.3A CN201611227887A CN106651849A CN 106651849 A CN106651849 A CN 106651849A CN 201611227887 A CN201611227887 A CN 201611227887A CN 106651849 A CN106651849 A CN 106651849A
- Authority
- CN
- China
- Prior art keywords
- image
- pcb
- template
- camera
- defect
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 89
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims abstract description 5
- 238000003860 storage Methods 0.000 claims abstract description 4
- 238000003709 image segmentation Methods 0.000 claims abstract description 3
- 238000012360 testing method Methods 0.000 claims description 43
- 238000007689 inspection Methods 0.000 claims description 30
- 230000009466 transformation Effects 0.000 claims description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 206010054949 Metaplasia Diseases 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000015689 metaplastic ossification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G06T3/147—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Abstract
The invention discloses an area-array camera-based PCB bare board defect detection method. The method comprises the following steps of 1, storing to-be-detected PCB parameters, wherein the to-be-detected PCB parameters include a PCB size; 2, determining a lowest shooting frequency according to the PCB size and a camera visual field; 3, loading a CAD template image used for detecting PCB bare board defects, and performing image segmentation processing and template corner point detection on a CAD template; 4, acquiring a to-be-detected image by a camera, and performing communication with a PLC; moving the carried camera when the to-be-detected image is acquired, and performing image acquisition on a whole PCB by regions; 5, performing registration on the CAD template image and the corresponding to-be-detected image; 6, performing image defect detection and extraction; and 7, when the defects are detected, outputting an alarm signal, recording the defects, and performing storage and display. The method has the characteristics of high detection precision and good real-time property, and the manpower cost is effectively reduced.
Description
Technical field
The invention belongs to Intelligent Measurement field, more particularly to a kind of PCB bare board defect inspection methods based on area array cameras.
Background technology
At present, PCB print quality inspections rely primarily on traditional manual detection mode, with the development of PCB industries, PCB
Plate printed circuit becomes increasingly complex, and artificial plus survey difficulty is big, and time-consuming, and subjectivity is big, it is difficult to meets growing PCB industries
Growth requirement.
Thus prior art could be improved and improve.
The content of the invention
It is an object of the invention to provide for the deficiency of manual detection traditional in PCB production processes, there is provided Yi Zhongji
In the PCB bare board defect inspection methods of machine vision, PCB bare board defect automatic detections are realized, greatly solve traditional PCB inspection
Survey complexity high, difficulty is big, detect time-consuming problem, save human cost, improve production efficiency.
In order to achieve the above object, this invention takes technical scheme below:
A kind of PCB bare board defect inspection methods based on area array cameras, it comprises the steps:
Step 1, storage pcb board parameter to be measured, the pcb board parameter to be measured includes pcb board size;
Step 2, according to the pcb board size, and camera fields of view, it is determined that at least shooting number of times;
Step 3, CAD template images for detecting PCB bare board defects are loaded, and the CAD templates are carried out at image segmentation
Manage, and template angle point adds survey;
Step 4, gathered by camera testing image, and communicated with PLC;Camera movement is carried when row altimetric image is gathered, point
Region carries out IMAQ to whole pcb board;
Step 5, CAD template images carry out registering with corresponding testing image;
Step 6, image deflects Detection and Extraction;
Step 7, when defect is detected, output alarm signal, record defect is simultaneously preserved and shown.
In the described PCB bare board defect inspection methods based on area array cameras, the step 1 includes:
The size of pcb board to be detected is measured, and parameter setting is carried out in software man-machine interactively interface.
In the described PCB bare board defect inspection methods based on area array cameras, the step 2 includes:
The size in the visual field is shot according to the size and camera of pcb board to be detected, it is determined that the scheme of taking pictures of optimum;The optimum bat
Take pictures scheme by optimum of the minimum shooting number of times of whole pcb board to be measured according to scheme.
In the described PCB bare board defect inspection methods based on area array cameras, the step 3 includes:
Step 31, initialization process is loaded and made to CAD template images, according to the optimum photographic schemes, to whole CAD
Template image carries out corresponding region cutting, is subsequently registering with the testing image that subregion shoots preparing;
Step 32, in order to ensure subsequent defective detection real-time, load CAD template images when feature is carried out to template image
Point is extracted, and specially extracts the angle point of each segmentation figure picture as characteristic point.
In the described PCB bare board defect inspection methods based on area array cameras, the step 4 includes:
Step 41, pcb board IMAQ mode to be measured adopt high-resolution face battle array black and white camera subregion multi collect;
It is in communication with each other with camera and PLC in step 42, gatherer process, according to shooting number of times, photographed scene size, and pcb board
Size determine PLC moving step lengths horizontally and vertically, after the completion of PLC movements, triggering camera is captured;
Step 43, the PLC that communicates after the completion of camera is captured be moved to it is next capture position, until completing whole process shooting.
In the described PCB bare board defect inspection methods based on area array cameras, the step 5 includes:
Step 51, according to the angle point of each cut zone of CAD template images, it is ROI areas to choose certain limit inner region around angle point
Domain, and choose the ROI region image of CAD template images;
Step 52, in testing image, scanning for matching with the range of template ROI region corresponding region, according to optimal
With result, corresponding angle point in testing image is determined;
Step 53, the matching process to all angle point execution steps 52 of extraction in step 3, obtain being corresponded therewith in template
Angle point;
Step 54, the transformation matrix between template and testing image is obtained using angle point, and it is affine to carry out image to template image
Conversion.
In the described PCB bare board defect inspection methods based on area array cameras, image deflects are extracted in step 6 includes extracting
Circuit fracture defect and circuit connect defect by mistake.
In the described PCB bare board defect inspection methods based on area array cameras, when circuit fracture defect is extracted, the step
Rapid 6 include:
Step 61, testing image test0 and template image model0 is made to negate image for binaryzation;
Step 62, Refinement operation is carried out to template image model0, specially travel through model0 image pixels, if (model0(x,
y)=0)Reset (test0 (x, y)=0), obtain Resttest0;
Step 63, model0 and Resttest0 are made the difference, obtain the defects detection result that ruptures.
In the described PCB bare board defect inspection methods based on area array cameras, when circuit connects defect by mistake, the step 6
Include:
Step 61 ', make testing image test1 and template image model1 negate image for binaryzation;
Step 62 ', expansive working is carried out to model1, travel through model1 pixels, if (model1(x,y)=255)Reset (test1
(x, y)=255), obtain Resttest1;
Step 63 ', model1 and Resttest1 are made the difference, obtain circuit and connect defects detection result by mistake.
In the described PCB bare board defect inspection methods based on area array cameras, the step 7 includes:
To detecting that defect is reported to the police, and the defect result for detecting is shown, historical record is preserved.
Compared to prior art, the remarkable result of the present invention is to whole PCB using the battle array black and white industry of high-resolution face
Plate image carries out subregion multi collect, and equipment is simple.Camera is using the CAD image of standard as template image, it is to avoid use
The template image error caused because of dust etc. during collected by camera template image, generates link and extracts in advance in template loading
Template angle point, reduces follow-up defects detection in real time and takes, and is matched according to the angle point region extracted, in obtaining testing image
Corresponding angle point, using multipair angle point grid template and the transformation matrix of testing image, carries out affine transformation, and analysis circuit is disconnected
Defect characteristic is split and connected by mistake, is extracted respectively, accuracy of detection is high, real-time is good, effectively saves human cost.
Description of the drawings
Fig. 1 is the flow chart of the PCB bare board defect inspection methods based on area array cameras of the present invention.
Fig. 2 is that template image treats mapping with corresponding in the PCB bare board defect inspection methods based on area array cameras of the invention
As the flow chart of matching.
Fig. 3 is defect in the PCB bare board defect inspection methods based on area array cameras of the invention(Fracture, connects by mistake)Detection
Flow chart.
Specific embodiment
What the present invention was provided can realize that PCB bare boards print based on the PCB bare board defect automatic checkout systems of machine vision
Defect automatic detection, it is high using high-resolution face battle array black and white camera and image processing algorithm accuracy of detection, can realize that PCB gives birth to
Detect completely into all the period of time, detection efficiency is greatly promoted, while the PCB product quality to producing realizes statistical management, meet existing
For the demand that metaplasia is produced.
To make the purpose of the present invention, technical scheme and effect clearer, clear and definite, develop simultaneously referring to the drawings embodiment pair
The present invention is further described.It should be appreciated that specific embodiment described herein is not used to only to explain the present invention
Limit the present invention.
Fig. 1 is the flow chart of the PCB bare board defect inspection methods based on area array cameras of the present invention.The present invention based on face
The PCB bare board defect inspection methods of array camera include:
Step 1, storage pcb board parameter to be measured, the pcb board parameter to be measured includes pcb board size.For the PCB of different size
Plate, by manual measurement mode the size of pcb board to be detected is determined, and carries out parameter setting in software man-machine interactively interface.
Step 2, according to the pcb board size, and camera fields of view, it is determined that at least shooting number of times.It is determined that shooting number of times
When, the size in the visual field is shot according to the size and camera of pcb board to be detected, it is determined that the scheme of taking pictures of optimum;The optimum bat
Take pictures scheme by optimum of the minimum shooting number of times of whole pcb board to be measured according to scheme.
Step 3, CAD template images for detecting PCB bare board defects are loaded, and image point is carried out to the CAD templates
Process is cut, and template angle point adds survey.It is specifically included:
Step 31, initialization process is loaded and made to CAD template images, according to the optimum photographic schemes, to whole CAD
Template image carries out corresponding region cutting, is subsequently registering with the testing image that subregion shoots preparing;
Step 32, in order to ensure subsequent defective detection real-time, load CAD template images when feature is carried out to template image
Point is extracted, and specially extracts the angle point of each segmentation figure picture as characteristic point.
Step 4, gathered by camera testing image, and communicated with PLC;Carry camera when row altimetric image is gathered to move
Dynamic, subregion carries out IMAQ to whole pcb board.It is specifically included:
Step 41, pcb board IMAQ mode to be measured adopt high-resolution face battle array black and white camera subregion multi collect;Rapid 42,
It is in communication with each other with PLC with camera in gatherer process, is determined according to the size for shooting number of times, photographed scene size, and pcb board
PLC moving step lengths horizontally and vertically, after the completion of PLC movements, triggering camera is captured;Rapid 43, captured in camera
Next candid photograph position is moved to into rear communication PLC, until completing whole process shooting.
Step 5, CAD template images carry out registering with corresponding testing image;It is specifically included:
Step 51, according to the angle point of each cut zone of CAD template images, it is ROI areas to choose certain limit inner region around angle point
Domain, and choose the ROI region image of CAD template images;
Step 52, in testing image, scanning for matching with the range of template ROI region corresponding region, according to optimal
With result, corresponding angle point in testing image is determined;
Step 53, the matching process to all angle point execution steps 52 of extraction in step 3, obtain being corresponded therewith in template
Angle point;
Step 54, the transformation matrix between template and testing image is obtained using angle point, and it is affine to carry out image to template image
Conversion.
Step 6, image deflects Detection and Extraction;Described image defect is extracted includes that extract circuit fracture defect and circuit connects by mistake
Defect.
For circuit ruptures defects detection, CAD template images are refined, because template adopts CAD image, therefore with reality
Whether the testing image circuit that border shoots has differences, and is to ensure that fracture defects detection result prepares, using detection circuit framework
There is fracture as defects detection foundation, therefore need first to carry out original Prototype drawing circuit connection when fracture defects detection is carried out
Refinement.When circuit fracture defect is extracted, the step 6 includes:
Step 61, testing image test0 and template image model0 is made to negate image for binaryzation;
Step 62, Refinement operation is carried out to template image model0, specially travel through model0 image pixels, if (model0(x,
y)=0)Reset (test0 (x, y)=0), obtain Resttest0;
Step 63, model0 and Resttest0 are made the difference, obtain the defects detection result that ruptures.
When circuit connects defect by mistake, the step 6 includes:
Step 61 ', make testing image test1 and template image model1 negate image for binaryzation;
Step 62 ', expansive working is carried out to model1, travel through model1 pixels, if (model1(x,y)=255)Reset (test1
(x, y)=255), obtain Resttest1;
Step 63 ', model1 and Resttest1 are made the difference, obtain circuit and connect defects detection result by mistake.
Step 7, when defect is detected, output alarm signal, record defect is simultaneously preserved and shown.Specially:To detection
Defect is reported to the police, and the defect result for detecting is shown, historical record is preserved
The present invention is used as template image using standard CAD image, shoots the visual field to enter according to pcb board size to be detected, camera
Row shoots number of times setting, and by setting PLC moving parameters, to control, camera moves horizontally distance and pcb board microscope carrier is vertically moved
Distance, realizes that the quick subregion to monoblock pcb board shoots.
Connect camera automatically in the software initialization stage, obtain camera parameter, realize standard the back(ing) board stage is added
CAD template images read internal memory, and according to the shooting number of times for determining, shoot visual field size and realize to whole plate CAD template image
Region divide automatically and read, it is time-consuming in order to save, after the CAD template images for extracting regional, carry out Corner Detection,
Corner Detection is carried out using Shi-tomasi methods in this invention.
When template loading link is completed, trigger triggering PLC automatically controls PCB microscope carrier automatic feeds(Convey to be measured
Pcb board), camera starts to capture, and triggers after the pre-determined step-length of PLC carrying camera microscope carrier horizontal direction movements, triggers phase
Machine is taken pictures, until horizontal direction completes predetermined shooting number of times, is carried pcb board microscope carrier and is continued vertical direction one fixed step size of movement, directly
Follow shots to whole PCB are realized to all shooting number of times are completed.
In shooting process, detect that thread synchronization is performed, start the testing image and corresponding template image to collecting
Configured, carried out defects detection.
Further, Fig. 2 is referred to, Fig. 2 is the flow chart that the template of the present invention is matched with corresponding testing image.Carry out
When template is matched with corresponding testing image, because the CAD templates of standard are black white image, lack gradation of image information, thus it is special
Levy a detection and registration is realized using angle point grid.Specially:
Carry out angle point grid to template image first, concrete grammar adopts Shi-tomasi methods, finally gives zones of different mould
The angle point of plate image;Then centered on angle point, the corresponding ROI region of each angle point is determined in template image, and treated
Region subject to registration is chosen in corresponding position in altimetric image(Due to there is displacement between template and testing image, for follow-up mould
The corresponding ROI region of plate angle point can obtain more accurate template matching results in testing image, correspondence in testing image
Region subject to registration need to be more than corresponding ROI region in template image);Afterwards, in template image, corresponding ROI region with
Correspondence position carries out traversal template matches in testing image, obtains accurate matched position, so as to obtain testing image in correspondence
Corner location, the angle point of all templates to extracting is repeated in said process, obtains one-to-one template and treat mapping
Corners Matching pair as in, so as to obtain the affine transformation matrix of template and testing image, realizes the affine change to template image
Change.
Fig. 3 is the defect of the present invention(Fracture, connects by mistake)The flow chart of detection.The step 6 is according to the affine transformation for obtaining
Matrix, realizes that the image to template image is converted, and to the template image model after conversion binaryzation inversion operation is carried out, and is used for
Carry out circuit fracture and circuit connects defects detection by mistake.
As shown in figure 3, for circuit fracture defects detection, test0 and model0 negates image for binaryzation, to model0
Refinement operation is carried out, according in order to avoid the impact of other factors, model0 image pixels, if (model0 is traveled through(x,y)=0)
Reset (test0 (x, y)=0);Resttest0 is obtained, model0 and Resttest0 are made the difference, the defect that ruptures is obtained according to difference
When testing result, such as difference are 0, testing result be then without defect, not for 0 when, then there is circuit fracture defect.
For circuit connects defects detection by mistake, test1 and model1 negate image for binaryzation, and to model1 expansion behaviour is carried out
Make, travel through model1 pixels, if (model1(x,y)=255)Reset (test1 (x, y)=255), obtain Resttest1, it is right
Model1 and Resttest1 make the difference, and testing result is connected by mistake.
Also, for the circuit fracture defects detection results different with connecting two kinds by mistake, respectively with not in former testing image
Indicated with color, recorded testing result.
In sum, to carry out subregion to whole pcb board image using the industry of high-resolution face battle array black and white multiple for the present invention
Collection, equipment is simple.Camera is using the CAD image of standard as template image, it is to avoid use collected by camera template image process
In because the template image error that causes such as dust, generates link and extracts template angle point in advance in template loading, reduce follow-up real
When defects detection take, and according to extract angle point region matched, corresponding angle point in testing image is obtained, using multipair
Angle point grid template and the transformation matrix of testing image, carry out radiation conversion, and analysis circuit ruptures and connects defect characteristic by mistake, point
Do not extracted, accuracy of detection is high, real-time is good, effectively saves human cost.
It is understood that for those of ordinary skills, with technology according to the present invention scheme and its can send out
Bright design in addition equivalent or change, and all these changes or replace the guarantor that should all belong to appended claims of the invention
Shield scope.
Claims (10)
1. a kind of PCB bare board defect inspection methods based on area array cameras, it is characterised in that comprise the steps:
Step 1, storage pcb board parameter to be measured, the pcb board parameter to be measured includes pcb board size;
Step 2, according to the pcb board size, and camera fields of view, it is determined that at least shooting number of times;
Step 3, CAD template images for detecting PCB bare board defects are loaded, and the CAD templates are carried out at image segmentation
Manage, and template angle point adds survey;
Step 4, gathered by camera testing image, and communicated with PLC;Camera movement is carried when row altimetric image is gathered, point
Region carries out IMAQ to whole pcb board;
Step 5, CAD template images carry out registering with corresponding testing image;
Step 6, image deflects Detection and Extraction;
Step 7, when defect is detected, output alarm signal, record defect is simultaneously preserved and shown.
2. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that the step
Rapid 1 includes:
The size of pcb board to be detected is measured, and parameter setting is carried out in software man-machine interactively interface.
3. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that the step
Rapid 2 include:
The size in the visual field is shot according to the size and camera of pcb board to be detected, it is determined that the scheme of taking pictures of optimum;The optimum bat
Take pictures scheme by optimum of the minimum shooting number of times of whole pcb board to be measured according to scheme.
4. PCB bare board defect inspection methods based on area array cameras according to claim 3, it is characterised in that the step
Rapid 3 include:
Step 31, initialization process is loaded and made to CAD template images, according to the optimum photographic schemes, to whole CAD
Template image carries out corresponding region cutting, is subsequently registering with the testing image that subregion shoots preparing;
Step 32, in order to ensure subsequent defective detection real-time, load CAD template images when feature is carried out to template image
Point is extracted, and specially extracts the angle point of each segmentation figure picture as characteristic point.
5. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that the step
Rapid 4 include:
Step 41, pcb board IMAQ mode to be measured adopt high-resolution face battle array black and white camera subregion multi collect;
It is in communication with each other with camera and PLC in step 42, gatherer process, according to shooting number of times, photographed scene size, and pcb board
Size determine PLC moving step lengths horizontally and vertically, after the completion of PLC movements, triggering camera is captured;
Step 43, the PLC that communicates after the completion of camera is captured be moved to it is next capture position, until completing whole process shooting.
6. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that the step
Rapid 5 include:
Step 51, according to the angle point of each cut zone of CAD template images, it is ROI areas to choose certain limit inner region around angle point
Domain, and choose the ROI region image of CAD template images;
Step 52, in testing image, scanning for matching with the range of template ROI region corresponding region, according to optimal
With result, corresponding angle point in testing image is determined;
Step 53, the matching process to all angle point execution steps 52 of extraction in step 3, obtain being corresponded therewith in template
Angle point;
Step 54, the transformation matrix between template and testing image is obtained using angle point, and it is affine to carry out image to template image
Conversion.
7. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that in step 6
Image deflects are extracted includes that extract circuit fracture defect and circuit connects defect by mistake.
8. PCB bare board defect inspection methods based on area array cameras according to claim 7, it is characterised in that extracting
During circuit fracture defect, the step 6 includes:
Step 61, testing image test0 and template image model0 is made to negate image for binaryzation;
Step 62, Refinement operation is carried out to template image model0, specially travel through model0 image pixels, if (model0(x,
y)=0)Reset (test0 (x, y)=0), obtain Resttest0;
Step 63, model0 and Resttest0 are made the difference, obtain the defects detection result that ruptures.
9. PCB bare board defect inspection methods based on area array cameras according to claim 7, it is characterised in that in circuit
When connecting defect by mistake, the step 6 includes:
Step 61 ', make testing image test1 and template image model1 negate image for binaryzation;
Step 62 ', expansive working is carried out to model1, travel through model1 pixels, if (model1(x,y)=255)Reset (test1
(x, y)=255), obtain Resttest1;
Step 63 ', model1 and Resttest1 are made the difference, obtain circuit and connect defects detection result by mistake.
10. PCB bare board defect inspection methods based on area array cameras according to claim 1, it is characterised in that the step
Rapid 7 include:
To detecting that defect is reported to the police, and the defect result for detecting is shown, historical record is preserved.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611227887.3A CN106651849A (en) | 2016-12-27 | 2016-12-27 | Area-array camera-based PCB bare board defect detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611227887.3A CN106651849A (en) | 2016-12-27 | 2016-12-27 | Area-array camera-based PCB bare board defect detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106651849A true CN106651849A (en) | 2017-05-10 |
Family
ID=58831729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611227887.3A Pending CN106651849A (en) | 2016-12-27 | 2016-12-27 | Area-array camera-based PCB bare board defect detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106651849A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107367514A (en) * | 2017-08-28 | 2017-11-21 | 广东工业大学 | A kind of POS defect inspection method based on machine vision |
CN107767379A (en) * | 2017-11-16 | 2018-03-06 | 桂林电子科技大学 | Pcb board marks print quality inspection method |
CN108254380A (en) * | 2018-01-03 | 2018-07-06 | 浙江涵普电力科技有限公司 | PCB circuit board template matching method based on Digital Image Processing |
CN110363737A (en) * | 2018-04-08 | 2019-10-22 | 深圳技术大学(筹) | A kind of image to be detected acquisition methods and image to be detected obtain system |
CN111798443A (en) * | 2020-07-16 | 2020-10-20 | 佛山市南海区广工大数控装备协同创新研究院 | Method for positioning and visualizing defects by utilizing PCB defect detection system |
CN113466261A (en) * | 2021-07-26 | 2021-10-01 | 鸿安(福建)机械有限公司 | PCB board automatic checkout device |
CN113777109A (en) * | 2021-08-25 | 2021-12-10 | 深圳市青虹激光科技有限公司 | Workpiece detection method, system, equipment and storage medium |
CN116593479A (en) * | 2023-07-19 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101793843A (en) * | 2010-03-12 | 2010-08-04 | 华东理工大学 | Connection table based automatic optical detection algorithm of printed circuit board |
CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
CN105957082A (en) * | 2016-05-04 | 2016-09-21 | 广东锐视智能检测有限公司 | Printing quality on-line monitoring method based on area-array camera |
-
2016
- 2016-12-27 CN CN201611227887.3A patent/CN106651849A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101793843A (en) * | 2010-03-12 | 2010-08-04 | 华东理工大学 | Connection table based automatic optical detection algorithm of printed circuit board |
CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
CN105957082A (en) * | 2016-05-04 | 2016-09-21 | 广东锐视智能检测有限公司 | Printing quality on-line monitoring method based on area-array camera |
Non-Patent Citations (5)
Title |
---|
A. ANU,MARGRET ANOUNCIA,L. RAJAJI: ""Automatic Visual Inspection of PCB using CAD Information"", 《2012 INTERNATIONAL CONFERENCE ON RADAR, COMMUNICATION AND COMPUTING》 * |
刘百芬等: ""基于机器视觉PCB裸板缺陷自动检测研究"", 《工业控制计算机》 * |
周建军,崔麦会等: "《海战场侦察技术概论》", 31 January 2013 * |
毕国玲等: ""基于角点和局部特征描述子的快速匹配算法"", 《光电工程》 * |
王艳卫: ""基于计算机视觉的线路板缺陷检测技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107367514A (en) * | 2017-08-28 | 2017-11-21 | 广东工业大学 | A kind of POS defect inspection method based on machine vision |
CN107767379A (en) * | 2017-11-16 | 2018-03-06 | 桂林电子科技大学 | Pcb board marks print quality inspection method |
CN107767379B (en) * | 2017-11-16 | 2021-02-12 | 桂林电子科技大学 | PCB label printing quality detection method |
CN108254380A (en) * | 2018-01-03 | 2018-07-06 | 浙江涵普电力科技有限公司 | PCB circuit board template matching method based on Digital Image Processing |
CN108254380B (en) * | 2018-01-03 | 2023-02-10 | 浙江涵普电力科技有限公司 | PCB template comparison method based on digital image processing |
CN110363737A (en) * | 2018-04-08 | 2019-10-22 | 深圳技术大学(筹) | A kind of image to be detected acquisition methods and image to be detected obtain system |
CN110363737B (en) * | 2018-04-08 | 2022-07-26 | 深圳技术大学(筹) | Method and system for acquiring image to be detected |
CN111798443A (en) * | 2020-07-16 | 2020-10-20 | 佛山市南海区广工大数控装备协同创新研究院 | Method for positioning and visualizing defects by utilizing PCB defect detection system |
CN113466261A (en) * | 2021-07-26 | 2021-10-01 | 鸿安(福建)机械有限公司 | PCB board automatic checkout device |
CN113777109A (en) * | 2021-08-25 | 2021-12-10 | 深圳市青虹激光科技有限公司 | Workpiece detection method, system, equipment and storage medium |
CN116593479A (en) * | 2023-07-19 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
CN116593479B (en) * | 2023-07-19 | 2024-02-06 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106651849A (en) | Area-array camera-based PCB bare board defect detection method | |
CN104749184B (en) | Automatic optical detection method and system | |
CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
CN111161404A (en) | Three-dimensional reconstruction method, device and system for annular scanning morphology | |
CN106228546A (en) | The detection method of a kind of board and device | |
CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
CN113723325B (en) | Frock defect detecting system of prefabricated component of assembled | |
CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
CN202649127U (en) | Automatic optical detection system | |
CN114049557A (en) | Garbage sorting robot visual identification method based on deep learning | |
CN104749801B (en) | High Precision Automatic optical detecting method and system | |
CN108445010A (en) | Automatic optical detection method and device | |
CN111624203A (en) | Relay contact alignment non-contact measurement method based on machine vision | |
CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
CN113688817A (en) | Instrument identification method and system for automatic inspection | |
CN114820439A (en) | PCB bare board defect detection system and method based on AOI | |
CN114518526A (en) | Automatic testing machine control system suitable for PCB board ICT | |
CN104614372B (en) | Detection method of solar silicon wafer | |
CN115937218B (en) | Surface defect detection method and system for cold stamping part | |
CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
CN101980299B (en) | Chessboard calibration-based camera mapping method | |
CN113723841B (en) | On-line detection method for tool missing in assembled prefabricated part | |
CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
CN111738257B (en) | Deep learning-based accurate reasoning system and method for cascading targets of different network models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
RJ01 | Rejection of invention patent application after publication |