CN106327496B - The detection system and method for PCB bare board blind hole defect based on AOI - Google Patents
The detection system and method for PCB bare board blind hole defect based on AOI Download PDFInfo
- Publication number
- CN106327496B CN106327496B CN201610742302.5A CN201610742302A CN106327496B CN 106327496 B CN106327496 B CN 106327496B CN 201610742302 A CN201610742302 A CN 201610742302A CN 106327496 B CN106327496 B CN 106327496B
- Authority
- CN
- China
- Prior art keywords
- bare board
- blind hole
- measured
- pcb bare
- image
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000007547 defect Effects 0.000 title claims abstract description 23
- 238000013461 design Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000012937 correction Methods 0.000 claims description 19
- 230000002708 enhancing effect Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 8
- 238000003754 machining Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification 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
- 239000011521 glass Substances 0.000 description 1
- 238000005286 illumination Methods 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)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention proposes a kind of PCB bare board blind hole defect detecting system and method based on AOI, for solving the technical problem that blind hole Detection accuracy is low under low-light environment present in existing detection system and method, detection system includes the image acquisition units being sequentially connected, image pre-processing unit, file pretreatment unit, parameter reading unit, blind hole detection unit and error calculation unit;The system acquires the scan image of PCB bare board to be measured first, bianry image is obtained by pretreatment, then the design document information of standard PCB bare board is read, according to the design document information of standard PCB bare board, the coordinate and radius for detecting all blind holes in bianry image, finally calculate the error of all blind holes on PCB bare board scan image to be measured.Detection accuracy of the present invention under low-light environment is high, and system cost is low, can be used for the detection of blind hole defect in circuit board processing environment.
Description
Technical field
The invention belongs to technical field of circuit board detection, are related to graph and image processing technology, and in particular to one kind is based on AOI
PCB bare board blind hole defect detection system and method, can be used for the detection of blind hole defect in circuit board processing environment.
Background technique
Printed circuit board (PCB, Printed Circuit Board) is the supplier of electronic component electrical connection.It
It is the basis of modern information industry, middle-size and small-size equipment is from electronic watch, electronic toy to television set, controlling intelligent household appliances, then arrives
The large scale equipments such as electronics, military weapon system, space shuttle all be unable to do without it, it is in life, society, traffic, boat
It etc. plays significant role.With the development of electronics industry and surface mounting technology, printed circuit board is just towards highly dense
Degree, light-type direction are developed.As PCB volume is smaller and smaller, complexity is higher and higher, while bringing to PCB quality testing tired
Difficult and challenge.Existing PCB defect inspection method can be divided into two major classes by test object: first is that without attachment circuit components
Bare board is detected, and whether conduction, through-hole and the blind hole that it predominantly detects circuit connection are up to specification etc.;Second is that
The PCB detection for mounting circuit components, predominantly detects circuit welding quality, scolding tin dosage and PCB component placement quality etc..
Based on PCB bare board, bare board quality seriously affects the quality of mounted board for second of detection, therefore to PCB bare board quality
Detection has great significance.
There are three types of existing PCB bare board blind hole defect inspection methods: artificial range estimation, detection of electrons and automatic optics inspection
(AOI,Automated Optical Inspection).Artificial range estimation is to be passed through by testing staff by magnifying glass or projector
Naked eyes detection blind hole whether there is defect;Common electronic detecting device mainly has needle bed-type detection and the detection of flying needle formula;Automatically
Optical detection is to obtain pcb board image using high resolution camera and special light sources, is mentioned by gray processing, two-value processing, feature
Take, feature detection and template matching to detect blind hole defect on pcb board automatically, there is reliable and stable, high-precision, high efficiency etc.
Advantage becomes most widely used blind hole defect inspection method.
For example, Chinese patent application, application publication number CN105486698A, 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 be main
Including rack, machine frame inside is provided with transmitting device, and frame top is provided with CCD camera, and the camera lens of CCD camera is filled towards transmission
It sets, light source cover is additionally provided between CCD camera and transmitting device, CCD camera can pass through the through-hole of light source cover to transmitting device
On product take a picture, be internally provided with light source in light source cover, further include control processor, control processor and CCD camera
It connects, is additionally provided with display in rack, display is connect with control 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.
It is collected under low-light environment since AOI system obtains PCB image using high resolution camera and special light sources
PCB image is of low quality, optical characteristic point is unobvious, without brightness enhancing, slant correction operate, directly use template matching into
Row detection, causes the accuracy rate that blind hole detects under low-light environment low.
Summary of the invention
It is an object of the invention to overcome the problems of the above-mentioned prior art, the invention proposes a kind of based on AOI's
PCB bare board blind hole defect detecting system and method, for solving under low-light environment present in existing detection system and method
The low technical problem of blind hole Detection accuracy.
To achieve the above object, the technical scheme adopted by the invention is as follows:
A kind of detection system of the PCB bare board blind hole defect based on AOI, including be sequentially connected image acquisition units, figure
As pretreatment unit, file pretreatment unit, parameter reading unit, blind hole detection unit and error calculation unit, in which:
Image acquisition units, for obtaining PCB bare board scan image to be measured;
Image pre-processing unit, for being pre-processed to PCB bare board scan image to be measured;
File pretreatment unit, for reading the coordinate value representation in standard PCB bare board design document, mounting hole letter
Breath and blind hole information;
Parameter reading unit, the PCB bare board scan image blind hole to be measured for reading the resolution ratio of scanner and having inputted
Error calculation mode;
Blind hole detection unit, including characteristic point detection module, blind hole area estimation module and the blind hole detection being sequentially connected
Module;Characteristic point detection module, for detecting the center location of mounting hole, and as PCB bare board scan image to be measured
Characteristic point;Blind hole area estimation module, for estimating the region on PCB bare board scan image to be measured where different blind holes;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 scan image to be measured.
The detection system of the above-mentioned PCB bare board blind hole defect based on AOI, image pre-processing unit, including what is be sequentially connected
Gray processing module, slant correction module, cuts module and binarization block at image enhancement module;Gray processing module, for treating
It surveys PCB bare board scan image and carries out gray processing;Image enhancement module, for carrying out brightness increasing to by the scan image of gray processing
By force;Slant correction module, for being corrected to the enhanced scan image of brightness;Module is cut, it is naked for cutting PCB to be measured
The flash of plate scan image, to obtain the subgraph of PCB bare board scan image to be measured;Binarization block, for naked to PCB to be measured
The subgraph of plate scan image carries out binaryzation, to obtain the black and white subgraph of PCB bare board scan image to be measured.
The detection system of the above-mentioned PCB bare board blind hole defect based on AOI, PCB bare board scan image to be measured save as bitmap
Format.
A kind of detection method of the PCB bare board blind hole defect based on AOI, includes the following steps:
(1) PCB bare board to be measured is scanned, obtains PCB bare board scan image to be measured;
(2) image pre-processing unit pre-processes PCB bare board scan image to be measured, obtains PCB bare board scanning to be measured
The black and white subgraph of image realizes step are as follows:
(2a) gray processing module carries out gray processing to PCB bare board scan image to be measured, obtains gray level image;
(2b) image enhancement module carries out brightness enhancing to gray level image, obtains enhancing image;
(2c) slant correction module carries out slant correction to enhancing image, obtains correction image;
(2d) cuts module and cuts to the flash of correction image, obtains the subgraph of PCB bare board scan image to be measured;
(2e) binarization block carries out binaryzation to the subgraph of PCB bare board scan image to be measured, obtains PCB bare board to be measured
The black and white subgraph of scan image;
(3) the coordinate value representation in file pretreatment unit reading standard PCB bare board design document, the mounting hole center of circle
Coordinate, blind hole machining error range, similar blind hole and the identical first blind hole information of adjacent blind hole spacing in same direction, and count
Calculate similar blind hole and the last one identical blind hole central coordinate of circle of adjacent blind hole spacing and any two mounting hole in same direction
Between distance;
(4) parameter reading unit reads the resolution ratio of scanner and the PCB bare board scan image blind hole to be measured that has inputted
Error calculation mode;
(5) blind hole detection unit detects the black and white subgraph of PCB bare board scan image to be measured, obtains all blind holes
Central coordinate of circle and radius, realize step are as follows:
The center of circle of (5a) the characteristic point detection module to all mounting holes in the black and white subgraph of PCB bare board scan image to be measured
Coordinate is detected, and obtains multiple characteristic points of the black and white subgraph of PCB bare board scan image to be measured, and calculate multiple characteristic points
In with the distance between corresponding two characteristic points of any two installation distance between borehole that are calculated in step (3), obtain two spies
Sign point the distance between with step (3) in calculate any two mounting hole between at a distance from mapping relations;
(5b) blind hole area estimation module calculates any two mounting hole in standard PCB bare board design document and arrives mark respectively
The distance between similar blind hole and the identical first blind hole of adjacent blind hole spacing in same direction in quasi- PCB bare board design document,
With similar blind hole and the last one identical blind hole central coordinate of circle of adjacent blind hole spacing in same direction to step (3) middle calculating
The distance between, four distance values in standard PCB bare board design document, and the mapping relations obtained according to step (5a) are obtained,
It calculates corresponding with four distance values in standard PCB bare board design document in the black and white subgraph of PCB bare board scan image to be measured
Then four distance values calculate in the black and white subgraph of PCB bare board scan image to be measured similar and adjacent blind hole in same direction
Multiple images region where the identical all blind holes of spacing;
(5c) blind hole detection module detects the multiple images region calculated in step (5b), and it is naked to obtain PCB to be measured
The central coordinate of circle and radius of all blind holes in the black and white subgraph of plate scan image, and it is written into file;
(6) error calculation unit is according to the resolution ratio of scanner in step (4) and the PCB bare board scanning figure to be measured inputted
As the error calculation mode of blind hole, the mismachining tolerance of all blind holes in the black and white subgraph of PCB bare board scan image to be measured is calculated
Value;
(7) according to the blind hole machining error range in the standard PCB bare board design document read in step (3), to step
(6) the mismachining tolerance values of all blind holes is determined in the black and white subgraph of the PCB bare board scan image to be measured calculated, obtain to
Survey the testing result of PCB bare board blind hole.
Compared with the prior art, the invention has the following advantages:
1. the present invention is due to passing through gray processing module, luminance enhancement module, slant correction to PCB bare board scan image to be measured
Module, cut module, binarization block and characteristic point detection module have carried out gray processing, brightness enhancing, slant correction, cutting,
Binaryzation and characteristic point detection operation have obtained the apparent bianry image of characteristic point, and according to characteristic point and blind hole area estimation mould
Block calculates the region where blind hole, reduces noise jamming of the blind hole region exterior to detection blind hole when, with prior art phase
Than effectively raising the accuracy rate that blind hole detects under low-light environment.
2. image acquisition units of the invention generate PCB bare board scanning to be measured using scanner scanning PCB bare board to be measured
Image reduces system cost compared with high resolution camera and special light sources that the prior art uses.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of detection system of the present invention;
Fig. 2 is the implementation process block diagram of detection method.
Specific embodiment
Below in conjunction with drawings and examples, invention is further described in detail.
Referring to Fig.1, detection system of the invention includes the image acquisition units being sequentially connected, image pre-processing unit, text
Part pretreatment unit, parameter reading unit, blind hole detection unit and error calculation unit, in which:
Image acquisition units, for obtaining PCB bare board scan image to be measured;
Image pre-processing unit, for being pre-processed to PCB bare board scan image to be measured;
File pretreatment unit, for reading the coordinate value representation in standard PCB bare board design document, mounting hole letter
Breath and blind hole information;
Parameter reading unit, the PCB bare board scan image blind hole to be measured for reading the resolution ratio of scanner and having inputted
Error calculation mode;
Blind hole detection unit, including characteristic point detection module, blind hole area estimation module and the blind hole detection being sequentially connected
Module;Characteristic point detection module, for detecting the center location of mounting hole, and as PCB bare board scan image to be measured
Characteristic point;Blind hole area estimation module, for estimating the region on PCB bare board scan image to be measured where different blind holes;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 scan image to be measured.
Referring to Fig. 2, the method that the present invention detects includes the following steps:
Step 1, PCB bare board to be measured is scanned, obtains PCB bare board scan image to be measured, embodiment has quadrangle
Four mounting holes, front have the similar blind hole of 3 rows and the identical rectangle PCB bare board of the adjacent blind hole spacing of every row is scanned;
Step 2, image pre-processing unit pre-processes PCB bare board scan image to be measured, obtains PCB bare board to be measured
The black and white subgraph of scan image realizes step are as follows:
Step 2a, gray processing module, PCB bare board scan image to be measured carry out gray processing, obtain gray level image, embodiment benefit
Gray processing is carried out to PCB bare board scan image to be measured with average gray method, Three Channel Color image is switched into single channel ash
Image is spent, image information is reduced;
Step 2b, image enhancement module carry out brightness enhancing to gray level image, obtain enhancing image, and embodiment utilizes ash
It spends pulling method and brightness enhancing, influence of the illumination to picture quality when removing Image Acquisition is carried out to gray level image;
Step 2c, slant correction module carry out slant correction to enhancing image, obtain correction image, and embodiment utilizes
The tilt angle that Hough transform method detects carries out slant correction to enhancing image, to exclude tilted image to trimming operation
Interference;
Step 2d cuts module, cuts to the flash of correction image, obtains the son of PCB bare board scan image to be measured
Image, embodiment dismiss the inactive area for not including circuit board information in correction image, are further reduced image information, exclude nothing
Imitate the interference in region;
Step 2e, binarization block carry out binaryzation to the subgraph of PCB bare board scan image to be measured, and embodiment utilizes
Adaptive Thresholding carries out binaryzation to the subgraph of PCB bare board scan image to be measured, to obtain the few PCB bare board to be measured of noise
The black and white subgraph of scan image;
Step 3, file pretreatment unit reads coordinate value representation, mounting hole in standard PCB bare board design document
Central coordinate of circle, blind hole machining error range, similar blind hole and the identical first blind hole information of adjacent blind hole spacing in same direction,
And calculate similar blind hole and the last one identical blind hole central coordinate of circle of adjacent blind hole spacing and any two peace in same direction
The distance between hole is filled, embodiment reads the coordinate value representation in standard PCB bare board design document: 2 expression integer-bits and 5
Position indicates decimal place, and positioned at the coordinate of the mounting hole of circuit board quadrangle, blind hole machining error range, every row is first in horizontal direction
The information of blind hole, is calculated the coordinate of every the last one blind hole of row in horizontal direction, and calculates upper left corner mounting hole to bottom right
Distance between the mounting hole of angle;
Step 4, the PCB bare board scan image blind hole to be measured that parameter reading unit reads the resolution ratio of scanner and inputted
Error calculation mode, embodiment read resolution of scanner be 60, error calculation mode be absolute error;
Step 5, blind hole detection unit detects the black and white subgraph of PCB bare board scan image to be measured, is owned
The central coordinate of circle and radius of blind hole realize step are as follows:
Step 5a, characteristic point detection module treat black and white for surveying PCB bare board scan image using connection area detecting method
The central coordinate of circle of all mounting holes is detected in image, obtains the multiple of the black and white subgraph of PCB bare board scan image to be measured
Characteristic point, and calculate two characteristic points corresponding with any two installation distance between borehole calculated in step 3 in multiple characteristic points
The distance between, obtain the distance between two characteristic points between any two mounting hole calculated in step 3 at a distance from reflect
Relationship is penetrated, embodiment is detected using mounting hole of the connected domain detection algorithm to quadrangle, the testing result of sub-pixel is obtained,
Error is calculated to reduce, upper left corner mounting hole in the black and white subgraph of PCB bare board scan image to be measured is calculated and is installed to the lower right corner
Distance between hole is obtained to the distance between the mounting hole of the lower right corner apart from mapping relations according to upper left corner mounting hole in step 3;
Step 5b, blind hole area estimation module calculate any two mounting hole in standard PCB bare board design document and arrive respectively
In standard PCB bare board design document in same direction between similar blind hole and the identical first blind hole of adjacent blind hole spacing away from
From, and similar blind hole and the last one identical blind hole center of circle of adjacent blind hole spacing is sat in the same direction that is calculated into step 3
The distance between mark, obtains four distance values in standard PCB bare board design document, and the mapping relations obtained according to step 5a,
It calculates corresponding with four distance values in standard PCB bare board design document in the black and white subgraph of PCB bare board scan image to be measured
Then four distance values calculate in the black and white subgraph of PCB bare board scan image to be measured similar and adjacent blind hole in same direction
Multiple images region where the identical all blind holes of spacing, embodiment calculate the mounting hole of left end two on standard PCB bare board and arrive
Two distances between every first blind hole of row, two distances of two mounting holes of right end to every the last one blind hole of row, according to step
Four distances are converted to the peace of left end two on the black and white subgraph of PCB bare board scan image to be measured by the mapping relations that 5a is obtained
Hole is filled to two distances between the first blind hole of every row, two distances of two mounting holes of right end to every the last one blind hole of row, root
According to two circle intersection formula of intersection point, calculate every row on the black and white subgraph of PCB bare board scan image to be measured it is first and last
The coordinate of a blind hole, to obtain the image-region where every row's blind hole;
Step 5c, blind hole detection module detect the multiple images region calculated in step 5b, and it is naked to obtain PCB to be measured
The central coordinate of circle and radius of all blind holes in the black and white subgraph of plate scan image, and it is written into file;
Step 6, error calculation unit is scanned according to the resolution ratio of scanner in step 4 and the PCB bare board to be measured inputted
The error calculation mode of image blind hole, the processing for calculating all blind holes in the black and white subgraph of PCB bare board scan image to be measured miss
Difference;
Step 7, according to the blind hole machining error range in the standard PCB bare board design document read in step 3, to step
The mismachining tolerance value of all blind holes is determined in the black and white subgraph of the 6 PCB bare board scan images to be measured calculated, is obtained to be measured
The testing result of PCB bare board blind hole.
The detection method of the above-mentioned PCB bare board blind hole defect based on AOI, sweeps PCB bare board to be measured described in step 2e
The black and white subgraph of tracing picture carries out binaryzation, realizes that adaptive threshold method can be according to every width using adaptive threshold method
The gray scale dynamic of image calculates the optimal threshold of each image, obtains the few bianry image of noise.
The detection method of the above-mentioned PCB bare board blind hole defect based on AOI, described in step 5c to multiple images region into
Row detection realizes that connection area detecting method can detecte white pixel all on bianry image using connection area detecting method
Region, while the deformation of blind hole can be ignored, obtain the testing result of sub-pixel.
The detection method of the above-mentioned PCB bare board blind hole defect based on AOI, sweeps PCB bare board to be measured described in step 5a
The central coordinate of circle of all mounting holes is detected in the black and white subgraph of tracing picture, same to be realized using connection area detecting method.
Above description is only example of the present invention, it is clear that for those skilled in the art, is being understood
After the contents of the present invention and principle, all form and details may be carried out without departing substantially from the principle of the present invention, structure
On various modifications and variations, but these modifications and variations based on inventive concept are still protected in claim of the invention
Within the scope of.
Claims (4)
1. a kind of detection method of the PCB bare board blind hole defect based on AOI is by including the Image Acquisition list being sequentially connected
The inspection of member, image pre-processing unit, file pretreatment unit, parameter reading unit, blind hole detection unit and error calculation unit
What examining system was realized, include the following steps:
(1) PCB bare board to be measured is scanned, obtains PCB bare board scan image to be measured;
(2) image pre-processing unit pre-processes PCB bare board scan image to be measured, obtains PCB bare board scan image to be measured
Black and white subgraph, realize step are as follows:
(2a) gray processing module carries out gray processing to PCB bare board scan image to be measured, obtains gray level image;
(2b) image enhancement module carries out brightness enhancing to gray level image, obtains enhancing image;
(2c) slant correction module carries out slant correction to enhancing image, obtains correction image;
(2d) cuts module, cuts to the flash of correction image, obtains the subgraph of PCB bare board scan image to be measured;
(2e) binarization block carries out binaryzation to the subgraph of PCB bare board scan image to be measured, obtains PCB bare board to be measured and sweep
The black and white subgraph of tracing picture;
(3) file pretreatment unit reads the coordinate value representation in standard PCB bare board design document, the mounting hole center of circle is sat
Similar blind hole and the identical first blind hole information of adjacent blind hole spacing on mark, blind hole machining error range, same direction, and calculate
In same direction between similar blind hole and the last one identical blind hole central coordinate of circle of adjacent blind hole spacing and any two mounting hole
Distance;
(4) parameter reading unit, the error of PCB bare board scan image blind hole to be measured for reading the resolution ratio of scanner and having inputted
Calculation;
(5) blind hole detection unit detects the black and white subgraph of PCB bare board scan image to be measured, obtains all blind holes
Central coordinate of circle and radius realize step are as follows:
(5a) characteristic point detection module sits the center of circle of all mounting holes in the black and white subgraph of PCB bare board scan image to be measured
Mark is detected, and obtains multiple characteristic points of the black and white subgraph of PCB bare board scan image to be measured, and calculate in multiple characteristic points
The distance between two characteristic points corresponding with any two installation distance between borehole calculated in step (3), obtain two features
Point the distance between with step (3) in calculate any two mounting hole between at a distance from mapping relations;
(5b) blind hole area estimation module calculates any two mounting hole in standard PCB bare board design document and arrives standard PCB respectively
The distance between similar blind hole and the identical first blind hole of adjacent blind hole spacing in same direction in bare board design document, and in addition
Any two mounting hole arrives similar blind hole in the same direction calculated in step (3) respectively and adjacent blind hole spacing is identical last
The distance between one blind hole central coordinate of circle obtains four distance values in standard PCB bare board design document, and according to step (5a)
Obtained mapping relations calculate in the black and white subgraph of PCB bare board scan image to be measured in standard PCB bare board design document four
Corresponding four distance values of a distance value, then calculate in the black and white subgraph of PCB bare board scan image to be measured in same direction
Multiple images region where the identical all blind holes of similar and adjacent blind hole spacing;
(5c) blind hole detection module detects the multiple images region calculated in step (5b), obtains PCB bare board to be measured and sweeps
The central coordinate of circle and radius of all blind holes in the black and white subgraph of tracing picture, and it is written into file;
(6) error calculation unit is blind according to the resolution ratio of scanner in step (4) and the PCB bare board scan image to be measured inputted
The error calculation mode in hole calculates the mismachining tolerance value of all blind holes in the black and white subgraph of PCB bare board scan image to be measured;
(7) according to the blind hole machining error range in the standard PCB bare board design document read in step (3), step (6) are counted
The mismachining tolerance value of all blind holes is determined in the black and white subgraph for the PCB bare board scan image to be measured calculated, and obtains PCB to be measured
The testing result of bare board blind hole.
2. the detection method of the PCB bare board blind hole defect according to claim 1 based on AOI, which is characterized in that step
Binaryzation is carried out to the black and white subgraph of PCB bare board scan image to be measured described in (2e), it is real using adaptive threshold method
It is existing.
3. the detection method of the PCB bare board blind hole defect according to claim 1 based on AOI, which is characterized in that step
Multiple images region is detected described in (5c), is realized using connection area detecting method.
4. the detection method of the PCB bare board blind hole defect according to claim 1 based on AOI, which is characterized in that step
The central coordinate of circle of all mounting holes in the black and white subgraph of PCB bare board scan image to be measured is detected described in (5a),
It is realized using connection area detecting method.
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 CN106327496A (en) | 2017-01-11 |
CN106327496B true 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) |
Families Citing this family (12)
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 |
CN107093174B (en) * | 2017-04-05 | 2018-03-27 | 湖北工业大学 | A kind of PCB design defect inspection method |
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 |
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 |
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 |
CN112200164B (en) * | 2020-12-03 | 2021-02-23 | 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 |
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 |
CN114782436B (en) * | 2022-06-20 | 2023-03-24 | 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 (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IL102659A (en) * | 1992-07-27 | 1997-07-13 | Orbot Instr Ltd | Apparatus and method for comparing and aligning two digital representations of an image |
-
2016
- 2016-08-26 CN CN201610742302.5A patent/CN106327496B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
---|
"A novel approach of standard data base generation for defect detection in bare PCB";Mukesh Kumar等;《International Conference on Computing Communication and Automatic》;20150706;第11-15页 |
"PCB光学孔位(孔径)检测设备设计与研究";周明;《机电信息》;20160712(第18期);第78-79页和第81页 |
"PCB孔位检测系统研究与实现";熊超有;《中国优秀硕士学位论文数据库 信息科技辑》;20160615(第06期);正文第19页第1段、第28-29页、第41页和第52页 |
"基于AOI的PCB孔缺陷检测法";杨霞等;《工业控制计算机》;20140311;第27卷(第1期);第21-22页 |
"基于数字图像处理的印刷电路板缺陷检测";李正明等;《仪表技术与传感器》;20121231(第8期);第87-89页 |
Also Published As
Publication number | Publication date |
---|---|
CN106327496A (en) | 2017-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106327496B (en) | The detection system and method for PCB bare board blind hole defect based on AOI | |
CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
US10366485B2 (en) | Positioning method, visual inspection apparatus, program, computer readable recording medium, and visual inspection method | |
EP0467149B1 (en) | Method of and device for inspecting pattern of printed circuit board | |
CN103675588B (en) | The machine vision detection method of printed component part polarity and equipment | |
CN107345789B (en) | PCB hole position detection device and method | |
EP3989542A1 (en) | Method and apparatus for evaluating image acquisition accuracy, and electronic device and storage medium | |
JP7122524B2 (en) | Inspection program generation system, inspection program generation method, and inspection program generation program | |
JP4309927B2 (en) | Eyelid detection device and program | |
CN110473165A (en) | A kind of welding quality of circuit board detection method and device | |
CN104484659A (en) | Method for automatically identifying and calibrating medical color images and medical gray scale images | |
EP0466013B1 (en) | Method of and device for inspecting pattern of printed circuit board | |
CN109785294A (en) | A kind of pcb board defective locations detection system and method | |
Guo et al. | Research of the machine vision based PCB defect inspection system | |
CN109905700A (en) | Virtual display device and its detection method, device, computer readable storage medium | |
CN108072664B (en) | Appearance detection system and method | |
CN109949725A (en) | A kind of AOI system image grayscale standardized method and system | |
CN107003255B (en) | Method for inspecting terminal of component formed on substrate and substrate inspection apparatus | |
CN116818785B (en) | Defect detection method, system and medium based on machine vision | |
JP2005128016A (en) | Inspection system and method | |
CN104359925A (en) | System for realizing automatic detection of electronic glass defects | |
KR101757240B1 (en) | Method for generating reference pattern of 3D shape measuring device | |
CN109612408B (en) | Method and device for testing emission angle of semiconductor laser and readable storage medium | |
CN109580174A (en) | Detection method, device and the readable storage medium storing program for executing of semiconductor laser local uniformity | |
Wu et al. | A visual inspection system for surface mounted components based on color features |
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 |