CN106327496A - System and method for detecting defects of blind holes in PCB (Printed Circuit Board) bare board based on AOI (Automated Optical Inspection) - Google Patents
System and method for detecting defects of blind holes in PCB (Printed Circuit Board) bare board based on AOI (Automated Optical Inspection) Download PDFInfo
- Publication number
- CN106327496A CN106327496A CN201610742302.5A CN201610742302A CN106327496A CN 106327496 A CN106327496 A CN 106327496A CN 201610742302 A CN201610742302 A CN 201610742302A CN 106327496 A CN106327496 A CN 106327496A
- Authority
- CN
- China
- Prior art keywords
- bare board
- blind hole
- measured
- scanogram
- pcb bare
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000007689 inspection Methods 0.000 title abstract description 7
- 230000003287 optical effect Effects 0.000 title abstract description 5
- 238000001514 detection method Methods 0.000 claims abstract description 58
- 238000013461 design Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 22
- 238000005520 cutting process Methods 0.000 claims description 14
- 230000002708 enhancing effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000005728 strengthening Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims 1
- 238000003754 machining Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 2
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 238000003466 welding Methods 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a system and a method for detecting defects of blind holes in a PCB (Printed Circuit Board) bare board based on AOI (Automated Optical Inspection). The system and the method are used for solving the technical problem of low detection accuracy of blind holes in dark in the existing detection system and method. The detection system comprises an image acquisition unit, an image preprocessing unit, a file preprocessing unit, a parameter reading unit, a blind hole detection unit and an error calculation unit; and the method comprises the steps of firstly, acquiring a scan image of a PCB bare board to be detected, preprocessing the scan image to obtain a binary image, then reading design file information of a standard PCB bare board, detecting coordinates and radii of all blind holes in the binary image according to the design file information of the standard PCB bare board, and finally calculating errors of all blind holes on the scan image of the PCB bare board to be detected. The detection accuracy in dark is high, the cost of the system is low, and the system and the method can be used for detecting defects of blind holes in circuit board machining environments.
Description
Technical field
The invention belongs to technical field of circuit board detection, relate to graph and image processing technology, be specifically related to a kind of based on AOI
The detecting system of PCB bare board blind hole defect and method, can be used for the detection of blind hole defect in circuit board processing environment.
Background technology
Printed circuit board (PCB, Printed Circuit Board), is the supplier of electronic devices and components electrical connection.It
Being the basis of modern information industry, middle-size and small-size equipment is from accutron, electronic toy to television set, controlling intelligent household appliances, then arrives
The main equipments such as electronics, military weapon system, space shuttle all be unable to do without it, and it is in life, society, traffic, boat
It etc. aspect play significant role.Along with electronics industry and the development of surface mounting technology, printed circuit board (PCB) is just towards highly dense
Degree, light-type direction are developed.Along with PCB volume is more and more less, complexity is more and more higher, brings tired to PCB quality testing simultaneously
Difficulty and challenge.Existing PCB defect inspection method can be divided into two big classes by detection object: one to without attachment circuit components
Bare board detects, and it is the most up to specification etc. that it predominantly detects the conduction of circuit connection, through hole and blind hole;Two is to
The PCB detection of attachment circuit components, predominantly detects the aspects such as circuit welding quality, scolding tin dosage and PCB component placement quality.
The second detects based on PCB bare board, and bare board quality has a strong impact on the quality of mounted board, therefore to PCB bare board quality
Detection has great significance.
Existing PCB bare board blind hole defect inspection method has three kinds: artificial range estimation, detection of electrons and automatic optics inspection
(AOI,Automated Optical Inspection).Artificial range estimation is to be passed through by magnifier or projector by testing staff
Naked eyes detection blind hole whether existing defects;Conventional electronic detecting device mainly has needle bed-type detection and flying needle formula to detect;Automatically
Optical detection is to utilize high resolution camera and special light sources to obtain pcb board image, and through gray processing, two-value processes, feature carries
Take, blind hole defect that feature detection and template matching detect on pcb board automatically, have reliable and stable, in high precision, high efficiency etc.
Advantage, becomes most widely used blind hole defect inspection method.
Such as, Chinese patent application, application publication number is CN105486698A, invention entitled " AOI automatic checkout equipment
And detection method " patent application, disclose a kind of AOI automatic checkout equipment and detection method, AOI automatic checkout equipment is main
Including frame, machine frame inside is provided with transmitting device, and frame top is provided with CCD camera, and the camera lens of CCD camera is towards transmission dress
Putting, be additionally provided with light source cover between CCD camera and transmitting device, CCD camera can be through the through hole of light source cover to transmitting device
On product take a picture, be internally provided with light source at light source cover, also include controlling processor, control processor and CCD camera
Connecting, frame is additionally provided with display, display is connected with controlling processor;AOI automatic testing method, including image acquisition
Module, coordinate analysis module, image processing module, non-defective unit picture storage module, defective region logging modle and display module.
Owing to AOI system uses high resolution camera and special light sources to obtain PCB image, collect under low-light environment
PCB image is of low quality, optical characteristic point is inconspicuous, without brightness enhancing, slant correction operation, directly uses template matching to enter
Row detection, causes the accuracy rate of blind hole detection under low-light environment low.
Summary of the invention
It is an object of the invention to the defect overcoming above-mentioned prior art to exist, the present invention proposes a kind of based on AOI
PCB bare board blind hole defect detecting system and method, be used for solving present in existing detecting system and method under low-light environment
The technical problem that blind hole Detection accuracy is low.
For achieving the above object, the technical scheme that the present invention takes is:
The detecting system of a kind of PCB bare board blind hole defect based on AOI, including the image acquisition units being sequentially connected, figure
As pretreatment unit, file pretreatment unit, parameter read unit, blind hole detector unit and error calculation unit, wherein:
Image acquisition units, is used for obtaining PCB bare board scanogram to be measured;
Image pre-processing unit, for carrying out pretreatment to PCB bare board scanogram to be measured;
File pretreatment unit, is used for coordinate figure representation, the installing hole letter reading in standard PCB bare board design document
Breath and blind hole information;
Parameter reads unit, for the resolution reading scanner and the PCB bare board scanogram blind hole to be measured inputted
Error Calculation mode;
Blind hole detector unit, detects including the feature point detection module being sequentially connected, blind hole area estimation module and blind hole
Module;Feature point detection module, for detecting the home position of installing hole, and as PCB bare board scanogram to be measured
Characteristic point;Blind hole area estimation module, for estimating the region at different blind hole places on PCB bare board scanogram to be measured;Blind hole
Detection module, for detecting the center of circle and the radius of all blind holes;
Error calculation unit, for calculating the mismachining tolerance of all blind holes on PCB bare board scanogram to be measured.
The detecting system of above-mentioned PCB bare board blind hole defect based on AOI, image pre-processing unit, including be sequentially connected
Gray processing module, image enhancement module, slant correction module, cutting module and binarization block;Gray processing module, is used for treating
Survey PCB bare board scanogram and carry out gray processing;Image enhancement module, for carrying out brightness increasing to the scanogram through gray processing
By force;Slant correction module, is corrected for scanogram enhanced to brightness;Cutting module, naked for cutting PCB to be measured
The burr of plate scanogram, to obtain the subimage of PCB bare board scanogram to be measured;Binarization block, for naked to PCB to be measured
The subimage of plate scanogram carries out binaryzation, to obtain the black and white subimage of PCB bare board scanogram to be measured.
The detecting system of above-mentioned PCB bare board blind hole defect based on AOI, PCB bare board scanogram to be measured, save as bitmap
Form.
The detection method of a kind of PCB bare board blind hole defect based on AOI, comprises the steps:
(1) PCB bare board to be measured is scanned, obtains PCB bare board scanogram to be measured;
(2) image pre-processing unit carries out pretreatment to PCB bare board scanogram to be measured, obtains PCB bare board to be measured scanning
The black and white subimage of image, it is achieved step is:
(2a) gray processing module carries out gray processing to PCB bare board scanogram to be measured, obtains gray level image;
(2b) image enhancement module carries out brightness enhancing to gray level image, obtains strengthening image;
(2c) slant correction module carries out slant correction to strengthening image, obtains correction chart picture;
(2d) cutting module carries out cutting to the burr of correction chart picture, obtains the subimage of PCB bare board scanogram to be measured;
(2e) binarization block carries out binaryzation to the subimage of PCB bare board scanogram to be measured, obtains PCB bare board to be measured
The black and white subimage of scanogram;
(3) the coordinate figure representation during file pretreatment unit reads standard PCB bare board design document, the installing hole center of circle
Similar blind hole and the identical first blind hole information of adjacent blind hole spacing on coordinate, blind hole mismachining tolerance scope, same direction, and count
Calculate similar blind hole on same direction and identical last the blind hole central coordinate of circle of adjacent blind hole spacing and any two installing hole
Between distance;
(4) parameter reads unit and reads the resolution of scanner and the PCB bare board scanogram blind hole to be measured that inputted
Error Calculation mode;
(5) the black and white subimage of PCB bare board scanogram to be measured is detected by blind hole detector unit, obtains all blind holes
Central coordinate of circle and radius, it is achieved step is:
(5a) feature point detection module is to the center of circle of all installing holes in the black and white subimage of PCB bare board scanogram to be measured
Coordinate detects, and obtains multiple characteristic points of the black and white subimage of PCB bare board scanogram to be measured, and calculates multiple characteristic point
In with the distance between two characteristic points corresponding to any two installing hole spacing calculated in step (3), obtain two spies
Distance between levying a little and the mapping relations of the distance between the middle any two installing hole calculated of step (3);
(5b) blind hole area estimation module, calculates any two installing hole in standard PCB bare board design document and arrives mark respectively
Distance between similar blind hole and the identical first blind hole of adjacent blind hole spacing on same direction in quasi-PCB bare board design document,
Last blind hole central coordinate of circle identical with similar blind hole on the same direction calculated in step (3) and adjacent blind hole spacing
Between distance, obtain four distance values in standard PCB bare board design document, and the mapping relations obtained according to step (5a),
Calculate in the black and white subimage of PCB bare board scanogram to be measured corresponding with four distance values in standard PCB bare board design document
Four distance values, then calculate in the black and white subimage of PCB bare board scanogram to be measured similar on same direction and adjacent blind hole
Multiple image-regions at all blind hole places that spacing is identical;
(5c) the multiple image-regions calculated in step (5b) are detected by blind hole detection module, obtain PCB to be measured naked
The central coordinate of circle of all blind holes and radius in the black and white subimage of plate scanogram, and it is written into file;
(6) error calculation unit is according to the resolution of scanner in step (4) and the PCB bare board scanning figure to be measured that inputted
As the Error Calculation mode of blind hole, calculate the mismachining tolerance of all blind holes in the black and white subimage of PCB bare board scanogram to be measured
Value;
(7) according to the blind hole mismachining tolerance scope in the standard PCB bare board design document read in step (3), to step
(6) in the black and white subimage of the PCB bare board scanogram to be measured calculated, the mismachining tolerance value of all blind holes judges, is treated
Survey the testing result of PCB bare board blind hole.
The present invention compared with prior art, has the advantage that
1. due to the fact that PCB bare board scanogram to be measured through gray processing module, luminance enhancement module, slant correction
Module, cutting module, binarization block and feature point detection module carried out gray processing, brightness enhancing, slant correction, cutting,
Binaryzation and feature point detection operation have obtained the obvious bianry image of characteristic point, and according to characteristic point and blind hole area estimation mould
Block calculates the region at blind hole place, decrease blind hole region exterior to detection blind hole time noise jamming, with prior art phase
Ratio, effectively raises the accuracy rate of blind hole detection under low-light environment.
2. the image acquisition units of the present invention, uses scanner scanning PCB to be measured bare board, generates PCB bare board to be measured scanning
Image, compared with the high resolution camera of prior art employing and special light sources, reduces system cost.
Accompanying drawing explanation
Fig. 1 is the structural representation of detecting system of the present invention;
Fig. 2 be detection method realize FB(flow block).
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described in further detail.
With reference to Fig. 1, image acquisition units that the detecting system of the present invention includes being sequentially connected, image pre-processing unit, literary composition
Part pretreatment unit, parameter read unit, blind hole detector unit and error calculation unit, wherein:
Image acquisition units, is used for obtaining PCB bare board scanogram to be measured;
Image pre-processing unit, for carrying out pretreatment to PCB bare board scanogram to be measured;
File pretreatment unit, is used for coordinate figure representation, the installing hole letter reading in standard PCB bare board design document
Breath and blind hole information;
Parameter reads unit, for the resolution reading scanner and the PCB bare board scanogram blind hole to be measured inputted
Error Calculation mode;
Blind hole detector unit, detects including the feature point detection module being sequentially connected, blind hole area estimation module and blind hole
Module;Feature point detection module, for detecting the home position of installing hole, and as PCB bare board scanogram to be measured
Characteristic point;Blind hole area estimation module, for estimating the region at different blind hole places on PCB bare board scanogram to be measured;Blind hole
Detection module, for detecting the center of circle and the radius of all blind holes;
Error calculation unit, for calculating the mismachining tolerance value of all blind holes on PCB bare board scanogram to be measured.
With reference to Fig. 2, the method for present invention detection comprises the steps:
Step 1, is scanned PCB bare board to be measured, obtains PCB bare board scanogram to be measured, and corner is had by embodiment
Four installing holes, front have the 3 similar blind holes of row and the rectangle PCB bare board of often arranging adjacent blind hole spacing identical to be scanned;
Step 2, image pre-processing unit, PCB bare board scanogram to be measured is carried out pretreatment, obtains PCB bare board to be measured
The black and white subimage of scanogram, it is achieved step is:
Step 2a, gray processing module, PCB bare board scanogram to be measured carries out gray processing, obtains gray level image, embodiment profit
By average gray method, PCB bare board scanogram to be measured is carried out gray processing, Three Channel Color image to be transferred to single channel ash
Degree image, reduces image information;
Step 2b, image enhancement module, gray level image is carried out brightness enhancing, obtains strengthening image, embodiment utilizes ash
Degree pulling method carries out brightness enhancing to gray level image, the illumination impact on picture quality during to remove image acquisition;
Step 2c, slant correction module, carry out slant correction to strengthening image, obtain correction chart picture, embodiment utilizes
The angle of inclination that Hough transform method detects, carries out slant correction, to get rid of tilted image to trimming operation to strengthening image
Interference;
Step 2d, cutting module, the burr of correction chart picture are carried out cutting, obtains the son of PCB bare board scanogram to be measured
Image, embodiment is dismissed the inactive area not comprising circuit board information in correction chart picture, is reduced image information further, gets rid of nothing
The interference in effect region;
Step 2e, binarization block, the subimage of PCB bare board scanogram to be measured is carried out binaryzation, embodiment utilizes
Adaptive Thresholding carries out binaryzation to the subimage of PCB bare board scanogram to be measured, the to be measured PCB bare board few to obtain noise
The black and white subimage of scanogram;
Step 3, file pretreatment unit reads the coordinate figure representation in standard PCB bare board design document, installing hole
Similar blind hole and the identical first blind hole information of adjacent blind hole spacing on central coordinate of circle, blind hole mismachining tolerance scope, same direction,
And calculate similar blind hole on same direction and identical last the blind hole central coordinate of circle of adjacent blind hole spacing and any two peace
Distance between dress hole, embodiment reads the coordinate figure representation in standard PCB bare board design document: 2 represent integer-bit and 5
Position represents decimal place, is positioned at the coordinate of the installing hole of circuit board corner, blind hole mismachining tolerance scope, horizontal direction is often arranged first
The information of blind hole, is calculated in horizontal direction the coordinate often arranging last blind hole, and calculates upper left corner installing hole to bottom right
Distance between the installing hole of angle;
Step 4, parameter reads the resolution that unit reads scanner and the PCB bare board scanogram blind hole to be measured inputted
Error Calculation mode, embodiment read resolution of scanner be 60, Error Calculation mode is absolute error;
Step 5, the black and white subimage of PCB bare board scanogram to be measured is detected, is owned by blind hole detector unit
The central coordinate of circle of blind hole and radius, it is achieved step is:
Step 5a, feature point detection module utilizes the connected domain detection method black and white to PCB bare board scanogram to be measured
In image, the central coordinate of circle of all installing holes detects, and obtains black and white subimage multiple of PCB bare board scanogram to be measured
Characteristic point, and calculate two characteristic points corresponding with any two installing hole spacing calculated in step 3 in multiple characteristic point
Between distance, obtain the reflecting of distance between any two installing hole calculated in the distance between two characteristic points and step 3
Penetrating relation, embodiment utilizes connected domain detection algorithm to detect the installing hole of corner, obtains the testing result of sub-pixel,
Calculate error to reduce, calculate upper left corner installing hole in the black and white subimage of PCB bare board scanogram to be measured and install to the lower right corner
Distance between hole, according to the distance between upper left corner installing hole in step 3 to lower right corner installing hole, obtains distance mapping relations;
Step 5b, blind hole area estimation module, calculate any two installing hole in standard PCB bare board design document and arrive respectively
In standard PCB bare board design document on same direction between similar blind hole and the identical first blind hole of adjacent blind hole spacing away from
From, last blind hole center of circle identical with similar blind hole on the same direction calculated in step 3 and adjacent blind hole spacing is sat
Distance between mark, obtains four distance values in standard PCB bare board design document, and the mapping relations obtained according to step 5a,
Calculate in the black and white subimage of PCB bare board scanogram to be measured corresponding with four distance values in standard PCB bare board design document
Four distance values, then calculate in the black and white subimage of PCB bare board scanogram to be measured similar on same direction and adjacent blind hole
Multiple image-regions at all blind hole places that spacing is identical, embodiment calculates two installing holes of left end on standard PCB bare board and arrives
Often arranging two distances between first blind hole, two installing holes of right-hand member are to often arranging two distances of last blind hole, according to step
Four distances are converted to left end two peace on the black and white subimage of PCB bare board scanogram to be measured by the mapping relations that 5a obtains
Dress hole to two distances often arranged between first blind hole, two installing holes of right-hand member to often arranging two distances of last blind hole, root
According to two circle intersect formula of intersection points, calculate often arrange on the black and white subimage of PCB bare board scanogram to be measured first and last
The coordinate of individual blind hole, thus often arranged the image-region at blind hole place;
Step 5c, the multiple image-regions calculated in step 5b are detected, obtain PCB to be measured naked by blind hole detection module
The central coordinate of circle of all blind holes and radius in the black and white subimage of plate scanogram, and it is written into file;
Step 6, error calculation unit scans according to resolution and the PCB bare board to be measured inputted of scanner in step 4
The Error Calculation mode of image blind hole, calculates the processing of all blind holes in the black and white subimage of PCB bare board scanogram to be measured by mistake
Difference;
Step 7, according to the blind hole mismachining tolerance scope in the standard PCB bare board design document read in step 3, to step
In the black and white subimage of the 6 PCB bare board scanograms to be measured calculated, the mismachining tolerance value of all blind holes judges, obtains to be measured
The testing result of PCB bare board blind hole.
The detection method of above-mentioned PCB bare board blind hole defect based on AOI, PCB bare board to be measured is swept described in step 2e
The black and white subimage of tracing picture carries out binaryzation, uses adaptive threshold method to realize, and adaptive threshold method can be according to every width
The optimal threshold of the gray scale dynamic calculation each image of image, obtains the bianry image that noise is few.
The detection method of above-mentioned PCB bare board blind hole defect based on AOI, multiple image-regions are entered described in step 5c
Row detection, uses connected domain detection method to realize, and connected domain detection method can detect all of white pixel on bianry image
Region, can ignore the deformation of blind hole simultaneously, obtain the testing result of sub-pixel.
The detection method of above-mentioned PCB bare board blind hole defect based on AOI, PCB bare board to be measured is swept described in step 5a
In the black and white subimage of tracing picture, the central coordinate of circle of all installing holes detects, and same employing connected domain detection method realizes.
Above description is only example of the present invention, it is clear that for those skilled in the art, is understanding
After present disclosure and principle, all may carry out form and details in the case of without departing substantially from the principle of the present invention, structure
On various corrections and change, but these corrections based on inventive concept and change still the present invention claim protect
Within the scope of.
Claims (7)
1. the detecting system of a PCB bare board blind hole defect based on AOI, it is characterised in that: include that the image being sequentially connected is adopted
Collection unit (1), image pre-processing unit (2), file pretreatment unit (3), parameter read unit (4), blind hole detector unit (5)
With error calculation unit (6), wherein:
Described image acquisition units (1), is used for obtaining PCB bare board scanogram to be measured;
Described image pre-processing unit (2), for carrying out pretreatment to PCB bare board scanogram to be measured;
Described file pretreatment unit (3), is used for coordinate figure representation, the installation reading in standard PCB bare board design document
Hole information and blind hole information;
Described parameter reads unit (4), blind for resolution and the PCB bare board scanogram to be measured inputted reading scanner
The Error Calculation mode in hole;
Described blind hole detector unit (5), including the feature point detection module (51) being sequentially connected, blind hole area estimation module (52)
With blind hole detection module (53);Described feature point detection module (51), for detecting the home position of installing hole, and as
The characteristic point of PCB bare board scanogram to be measured;Described blind hole area estimation module (52), is used for estimating that PCB bare board to be measured scans
The region at different blind hole places on image;Described blind hole detection module (53) is for detecting the center of circle and the radius of all blind holes;
Described error calculation unit (6), for calculating the mismachining tolerance value of all blind holes on PCB bare board scanogram to be measured.
The detecting system of PCB bare board blind hole defect based on AOI the most according to claim 1, it is characterised in that described figure
As pretreatment unit (2), including the gray processing module (21) being sequentially connected, image enhancement module (22), slant correction module
(23), cutting module (24) and binarization block (25);Described gray processing module (21), for PCB bare board to be measured scanning figure
As carrying out gray processing;Described image enhancement module (22), for carrying out brightness enhancing to the scanogram through gray processing;Described
Slant correction module (23), is corrected for scanogram enhanced to brightness;Described cutting module (24), for cutting
The burr of PCB bare board scanogram to be measured, to obtain the subimage of PCB bare board scanogram to be measured;Described binarization block
(25), for the subimage of PCB bare board scanogram to be measured is carried out binaryzation, to obtain PCB bare board scanogram to be measured
Black and white subimage.
The detecting system of PCB bare board blind hole defect based on AOI the most according to claim 1, it is characterised in that described in treat
Survey PCB bare board scanogram, save as bitmap format.
4. a detection method for PCB bare board blind hole defect based on AOI, comprises the steps:
(1) PCB bare board to be measured is scanned, obtains PCB bare board scanogram to be measured;
(2) image pre-processing unit, carries out pretreatment to PCB bare board scanogram to be measured, obtains PCB bare board scanogram to be measured
Black and white subimage, it is achieved step is:
(2a) gray processing module, carries out gray processing to PCB bare board scanogram to be measured, obtains gray level image;
(2b) image enhancement module, carries out brightness enhancing to gray level image, obtains strengthening image;
(2c) slant correction module, carries out slant correction to strengthening image, obtains correction chart picture;
(2d) burr of correction chart picture are carried out cutting by cutting module, obtain the subimage of PCB bare board scanogram to be measured;
(2e) binarization block, carries out binaryzation to the subimage of PCB bare board scanogram to be measured, obtains PCB bare board to be measured and sweeps
The black and white subimage of tracing picture;
(3) file pretreatment unit, reads the coordinate figure representation in standard PCB bare board design document, installing hole center of circle seat
Similar blind hole and the identical first blind hole information of adjacent blind hole spacing on mark, blind hole mismachining tolerance scope, same direction, and calculate
On same direction between similar blind hole and identical last blind hole central coordinate of circle and any two installing hole of adjacent blind hole spacing
Distance;
(4) parameter reads unit, the resolution reading scanner and the error of the PCB bare board scanogram blind hole to be measured inputted
Calculation;
(5) blind hole detector unit, detects the black and white subimage of PCB bare board scanogram to be measured, obtains all blind holes
Central coordinate of circle and radius, it is achieved step is:
(5a) feature point detection module, sits the center of circle of all installing holes in the black and white subimage of PCB bare board scanogram to be measured
Mark detects, and obtains multiple characteristic points of the black and white subimage of PCB bare board scanogram to be measured, and calculates in multiple characteristic point
The distance two characteristic points between corresponding with any two installing hole spacing calculated in step (3), obtains two features
Distance between point and the mapping relations of the distance between the middle any two installing hole calculated of step (3);
(5b) blind hole area estimation module, calculates any two installing hole in standard PCB bare board design document and arrives standard PCB respectively
Distance between similar blind hole and the identical first blind hole of adjacent blind hole spacing on same direction in bare board design document, and arrive
On the same direction calculated in step (3) between similar blind hole and identical last the blind hole central coordinate of circle of adjacent blind hole spacing
Distance, obtain four distance values in standard PCB bare board design document, and the mapping relations obtained according to step (5a), calculate
Corresponding with four distance values in standard PCB bare board design document in the black and white subimage of PCB bare board scanogram to be measured four
Distance value, then calculates in the black and white subimage of PCB bare board scanogram to be measured similar on same direction and adjacent blind hole spacing
Multiple image-regions at identical all blind hole places;
(5c) the multiple image-regions calculated in step (5b) are detected by blind hole detection module, obtain PCB bare board to be measured and sweep
The central coordinate of circle of all blind holes and radius in the black and white subimage of tracing picture, and it is written into file;
(6) error calculation unit is blind according to resolution and the PCB bare board scanogram to be measured inputted of scanner in step (4)
The Error Calculation mode in hole, calculates the mismachining tolerance value of all blind holes in the black and white subimage of PCB bare board scanogram to be measured;
(7) according to the blind hole mismachining tolerance scope in the standard PCB bare board design document read in step (3), step (6) is counted
In the black and white subimage of the PCB bare board scanogram to be measured calculated, the mismachining tolerance value of all blind holes judges, obtains PCB to be measured
The testing result of bare board blind hole.
The detection method of PCB bare board blind hole defect based on AOI the most according to claim 4, it is characterised in that step
(2e) the black and white subimage to PCB bare board scanogram to be measured described in carries out binaryzation, uses adaptive threshold method real
Existing.
The detection method of PCB bare board blind hole defect based on AOI the most according to claim 4, it is characterised in that step
(5c) detecting multiple image-regions described in, uses connected domain detection method to realize.
The detection method of PCB bare board blind hole defect based on AOI the most according to claim 4, it is characterised in that step
(5a) in the black and white subimage to PCB bare board scanogram to be measured described in, the central coordinate of circle of all installing holes detects,
Connected domain detection method is used to realize.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610742302.5A CN106327496B (en) | 2016-08-26 | 2016-08-26 | The detection system and method for PCB bare board blind hole defect based on AOI |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610742302.5A CN106327496B (en) | 2016-08-26 | 2016-08-26 | The detection system and method for PCB bare board blind hole defect based on AOI |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106327496A true CN106327496A (en) | 2017-01-11 |
CN106327496B CN106327496B (en) | 2019-04-23 |
Family
ID=57791810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610742302.5A Active CN106327496B (en) | 2016-08-26 | 2016-08-26 | The detection system and method for PCB bare board blind hole defect based on AOI |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106327496B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107093174A (en) * | 2017-04-05 | 2017-08-25 | 湖北工业大学 | A kind of PCB design defect inspection method |
CN107464236A (en) * | 2017-07-28 | 2017-12-12 | 武汉华星光电半导体显示技术有限公司 | A kind of flexible display substrates defect estimation method based on AOI |
CN108550142A (en) * | 2018-03-30 | 2018-09-18 | 深圳大学 | A kind of tooth hole inspection method and hole inspection and device |
CN108572307A (en) * | 2017-03-07 | 2018-09-25 | 惠州中京电子科技有限公司 | A kind of multi-layer H DI printed circuits board blind hole inspection method |
CN109253702A (en) * | 2018-11-08 | 2019-01-22 | 东莞职业技术学院 | A kind of PCB drilling Quick overhaul method and apparatus |
CN111310402A (en) * | 2020-01-21 | 2020-06-19 | 西安工程大学 | Method for detecting defects of bare printed circuit board based on surface-to-surface parallelism |
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 |
CN112200164A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Integrated circuit metal round hole automatic identification method and system based on electron microscope image |
CN113808067A (en) * | 2020-06-11 | 2021-12-17 | 广东美的白色家电技术创新中心有限公司 | Circuit board detection method, visual detection equipment and device with storage function |
CN113870242A (en) * | 2021-10-12 | 2021-12-31 | 京东方(河北)移动显示技术有限公司 | Method and equipment for detecting blind hole |
CN113933309A (en) * | 2021-10-28 | 2022-01-14 | 赣州市同兴达电子科技有限公司 | Method for retesting defects in blind hole by AOI machine |
CN114782436A (en) * | 2022-06-20 | 2022-07-22 | 苏州康代智能科技股份有限公司 | PCB defect detection method, circuit board metering measurement method and manufacturing method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5907628A (en) * | 1992-07-27 | 1999-05-25 | Orbot Instruments Ltd. | Apparatus and method for comparing and aligning two digital representations of an image |
CN1401107A (en) * | 2000-01-18 | 2003-03-05 | 索威森公司 | Method and system for detecting defects on a printed circuit board |
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 |
CN104764712A (en) * | 2015-04-29 | 2015-07-08 | 浙江工业大学 | Method for detecting quality of inner wall of via hole of PCB |
CN104777165A (en) * | 2014-01-13 | 2015-07-15 | 牧德科技股份有限公司 | Detection equipment, detection system and detection method for defects in blind holes of circuit board |
CN105631846A (en) * | 2014-10-31 | 2016-06-01 | 陕西高华知本化工科技有限公司 | Detection method for circular figure |
-
2016
- 2016-08-26 CN CN201610742302.5A patent/CN106327496B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5907628A (en) * | 1992-07-27 | 1999-05-25 | Orbot Instruments Ltd. | Apparatus and method for comparing and aligning two digital representations of an image |
CN1401107A (en) * | 2000-01-18 | 2003-03-05 | 索威森公司 | Method and system for detecting defects on a printed circuit board |
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 |
CN104777165A (en) * | 2014-01-13 | 2015-07-15 | 牧德科技股份有限公司 | Detection equipment, detection system and detection method for defects in blind holes of circuit board |
CN105631846A (en) * | 2014-10-31 | 2016-06-01 | 陕西高华知本化工科技有限公司 | Detection method for circular figure |
CN104764712A (en) * | 2015-04-29 | 2015-07-08 | 浙江工业大学 | Method for detecting quality of inner wall of via hole of PCB |
Non-Patent Citations (5)
Title |
---|
MUKESH KUMAR等: ""A novel approach of standard data base generation for defect detection in bare PCB"", 《INTERNATIONAL CONFERENCE ON COMPUTING COMMUNICATION AND AUTOMATIC》 * |
周明: ""PCB光学孔位(孔径)检测设备设计与研究"", 《机电信息》 * |
李正明等: ""基于数字图像处理的印刷电路板缺陷检测"", 《仪表技术与传感器》 * |
杨霞等: ""基于AOI的PCB孔缺陷检测法"", 《工业控制计算机》 * |
熊超有: ""PCB孔位检测系统研究与实现"", 《中国优秀硕士学位论文数据库 信息科技辑》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108572307A (en) * | 2017-03-07 | 2018-09-25 | 惠州中京电子科技有限公司 | A kind of multi-layer H DI printed circuits board blind hole inspection method |
CN107093174A (en) * | 2017-04-05 | 2017-08-25 | 湖北工业大学 | A kind of PCB design defect inspection method |
CN107464236A (en) * | 2017-07-28 | 2017-12-12 | 武汉华星光电半导体显示技术有限公司 | A kind of flexible display substrates defect estimation method based on AOI |
CN107464236B (en) * | 2017-07-28 | 2020-05-05 | 武汉华星光电半导体显示技术有限公司 | Flexible display substrate defect discrimination method based on AOI |
CN108550142A (en) * | 2018-03-30 | 2018-09-18 | 深圳大学 | A kind of tooth hole inspection method and hole inspection and device |
WO2019184094A1 (en) * | 2018-03-30 | 2019-10-03 | 深圳大学 | Threaded hole detecting method and device |
CN109253702A (en) * | 2018-11-08 | 2019-01-22 | 东莞职业技术学院 | A kind of PCB drilling Quick overhaul method and apparatus |
CN109253702B (en) * | 2018-11-08 | 2023-07-28 | 东莞职业技术学院 | PCB drilling quick overhaul method and equipment |
CN111310402B (en) * | 2020-01-21 | 2023-04-14 | 西安工程大学 | Method for detecting defects of bare printed circuit board based on surface-to-surface parallelism |
CN111310402A (en) * | 2020-01-21 | 2020-06-19 | 西安工程大学 | Method for detecting defects of bare printed circuit board based on surface-to-surface parallelism |
CN113808067A (en) * | 2020-06-11 | 2021-12-17 | 广东美的白色家电技术创新中心有限公司 | Circuit board detection method, visual detection equipment and device with storage function |
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 |
CN112200164A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Integrated circuit metal round hole automatic identification method and system based on electron microscope image |
CN113870242A (en) * | 2021-10-12 | 2021-12-31 | 京东方(河北)移动显示技术有限公司 | Method and equipment for detecting blind hole |
CN113933309A (en) * | 2021-10-28 | 2022-01-14 | 赣州市同兴达电子科技有限公司 | Method for retesting defects in blind hole by AOI machine |
CN113933309B (en) * | 2021-10-28 | 2023-10-20 | 赣州市同兴达电子科技有限公司 | Method for retesting blind hole Kong Nabu of AOI machine |
CN114782436A (en) * | 2022-06-20 | 2022-07-22 | 苏州康代智能科技股份有限公司 | PCB defect detection method, circuit board metering measurement method and manufacturing method |
Also Published As
Publication number | Publication date |
---|---|
CN106327496B (en) | 2019-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106327496A (en) | System and method for detecting defects of blind holes in PCB (Printed Circuit Board) bare board based on AOI (Automated Optical Inspection) | |
CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
CN110497187B (en) | Sun flower pattern assembly system based on visual guidance | |
EP0467149B1 (en) | Method of and device for inspecting pattern of printed circuit board | |
EP3989542A1 (en) | Method and apparatus for evaluating image acquisition accuracy, and electronic device and storage medium | |
CN107345789B (en) | PCB hole position detection device and method | |
EP1580691A2 (en) | Automatic adjustment of acquisition of inspection image | |
EP0466013B1 (en) | Method of and device for inspecting pattern of printed circuit board | |
CN110473165A (en) | A kind of welding quality of circuit board detection method and device | |
CN1977145A (en) | Measuring apparatus and method for range inspection | |
JP2019100917A (en) | Inspection program generation system, generation method of inspection program and generation program of inspection program | |
CN107155094B (en) | Using the vision inspections method of multiple video cameras | |
Guo et al. | Research of the machine vision based PCB defect inspection system | |
CN109696240A (en) | Detection method, device and the readable storage medium storing program for executing of the semiconductor laser overall situation uniformity | |
US10853935B2 (en) | Image processing system, computer readable recording medium, and image processing method | |
CN116818785B (en) | Defect detection method, system and medium based on machine vision | |
CN109612408B (en) | Method and device for testing emission angle of semiconductor laser and readable storage medium | |
CN114964032B (en) | Blind hole depth measurement method and device based on machine vision | |
CN109580174A (en) | Detection method, device and the readable storage medium storing program for executing of semiconductor laser local uniformity | |
CN115479891A (en) | Automatic detection system and method for circuit board mounted components based on image recognition | |
Wu et al. | A visual inspection system for surface mounted components based on color features | |
CN209877890U (en) | Semi-automatic line width detection device | |
WO2022250584A1 (en) | A method and an electronic device for analysing an image | |
CN206638404U (en) | Detector lens light box | |
JP2596158B2 (en) | Component recognition device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |