CN103543151B - A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image - Google Patents
A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image Download PDFInfo
- Publication number
- CN103543151B CN103543151B CN201310461359.4A CN201310461359A CN103543151B CN 103543151 B CN103543151 B CN 103543151B CN 201310461359 A CN201310461359 A CN 201310461359A CN 103543151 B CN103543151 B CN 103543151B
- Authority
- CN
- China
- Prior art keywords
- pcb
- image
- thickness
- pixel
- images
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000004020 conductor Substances 0.000 claims abstract description 84
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000000205 computational method Methods 0.000 claims abstract description 6
- 230000003321 amplification Effects 0.000 claims description 16
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 16
- 206010008190 Cerebrovascular accident Diseases 0.000 claims description 3
- 208000006011 Stroke Diseases 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims 1
- 239000010931 gold Substances 0.000 claims 1
- 229910052737 gold Inorganic materials 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 10
- 238000001514 detection method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The present invention is a kind of measuring method of the printed circuit board (PCB) based on microsection bianry image.Bitmap images of the present invention for the bianry image of the microsection in certain hole in infput sheet, that is PCB image, hole is divided into the white portion of PCB image the feature of upper and lower two simply connected regions, proposes first to calculate the upper half area printed circuit board (PCB) number of plies of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor；Then the PCB image to being input into carries out flip vertical, obtains the flip vertical image of input picture；Then the flip vertical image of input picture is calculated with the computational methods for calculating upper half area before again, obtains the lower half region PCB layer number of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor；The result of calculation in last comprehensive upper and lower two regions obtains the PCB layer number in whole hole, outer layer conductor thickness, the measurement result of the thickness of every inner conductor.The present invention can significantly improve certainty of measurement and efficiency.
Description
Technical field
The invention belongs to quality of printed circuits detection technique, and in particular to a kind of to be used to detect printed circuit intralaminar part matter
Printed circuit board (PCB) (Printed Circuit Board, the PCB) number of plies based on microsection bianry image and conductor thickness of amount
Measuring method.Belong to the innovative technology of the measuring method of printed circuit board (PCB) based on microsection bianry image.
Background technology
Received more and more attention based on the PCB product quality determining method of image processing techniquess.It is existing based on figure
As the PCB quality testings for the treatment of technology be concentrated mainly on PCB surface components and parts detection with identification (Su Mingming. circuit board element
Detection with identification [D]. Dalian University of Technology, 2005；Zhu Yan. the electric circuit inspection based on machine vision technique and realization [D]. west
Northern polytechnical university, 2007) and PCB surface defect context of detection (Zheng Wei. image method detection defect of printed circuit board [D]. Xi'an
Polytechnics, 2002).PCB internal soundnesses detection based on microsection image mainly adopts artificial observation method at present, related
Patent and research report are little.Artificial observation method efficiency is low, and observed result stability is poor, precision cannot be guaranteed.
The content of the invention
It is an object of the invention to consider the problems referred to above and provide it is a kind of can significantly improve certainty of measurement and efficiency based on
The measuring method of the printed circuit board (PCB) of microsection bianry image.
Measuring method of the present invention based on the printed circuit board (PCB) of microsection bianry image, including having the following steps：
1) in infput sheet the bianry image of the microsection in certain hole bitmap images, i.e. PCB image, hole handle
The white portion of PCB image is divided into upper and lower two simply connected regions, wherein, horizontal direction be hole wall direction, white represent wire,
Black represents non-wire；
2) the upper half area printed circuit board (PCB) number of plies of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor,
Concrete calculation procedure is as follows：
21) starting of conducting line segment is calculated, terminating the coordinate of pixel, row number is designated as BijAnd Eij；Conducting line segment is reflected in PCB
It is a horizontal white wire in image, the white wire is a part for certain layer conductor；According to input printed circuit board (PCB) in certain
The white that the bitmap images of the bianry image of the microsection in hole specify represents wire, black and represents non-wire, it can be found that leading
Line segment has property：Starting pixels point is white but the pixel less by 1 than the pixel row number of the pixel is black, terminates pixel
Point is white but the pixel bigger by 1 than the pixel row number of the pixel is black；
22) it is related to maximum pixel line number R of the PCB image in region when determining and calculate output parameter0；
23) conducting line segment cluster；
24) PCB layer number, outer layer conductor thickness, the thickness of every inner conductor are calculated；
3) the lower half region PCB layer number of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor, which is concrete
Method is：
31) flip vertical step 1) PCB image that is input into, obtain its flip vertical image and using the image as new defeated
Enter image；
32) the flip vertical image of input picture is counted with the computational methods for calculating upper half area before again
Calculate, obtain the lower half region PCB layer number of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor and (correspond to former input respectively
The lower half region PCB layer number of PCB image, left outside layer conductor thickness, the thickness of every inner conductor, right outer layer conductor thickness)；
4) combining step 2) and step 3) result of calculation, export the number of plies of printed circuit board (PCB) of corresponding aperture, outer layer conductor
The thickness of thickness, every inner conductor.
Bitmap images of the present invention for the bianry image of the microsection in certain hole in infput sheet, i.e. PCB
Image, hole are divided into the white portion of PCB image the feature of upper and lower two simply connected regions, propose first to calculate the upper half of corresponding aperture
The region printed circuit board (PCB) number of plies, outer layer conductor thickness, the thickness of every inner conductor；Then the PCB image to being input into is hung down
It is straight to overturn, obtain the flip vertical image of input picture；Then again with the computational methods of calculating upper half area before to defeated
The flip vertical image for entering image is calculated, and obtains the lower half region PCB layer number of corresponding aperture, outer layer conductor thickness, per in bar
The thickness of layer conductor；The result of calculation in last comprehensive upper and lower two regions obtain the PCB layer number in whole hole, outer layer conductor thickness,
The measurement result of the thickness of every inner conductor.PCB layer number and conductor thickness are the important parameters for weighing PCB internal soundnesses.This
By observation analysis PCB microsections bianry image and PCB layer number, the relationship schedule of conductor thickness, invention proposes that one kind is based on
The printed circuit board (PCB) number of plies and conductor thickness measuring method of microsection bianry image.The present invention is applied to the inspection of PCB internal soundnesses
Survey, and certainty of measurement and measurement efficiency can be significantly improved.The present invention is a kind of convenient and practical based on microsection bianry image
Printed circuit board (PCB) measuring method.
Description of the drawings
Fig. 1 is the PCB microsection bitonal bitmap example images of input.
Fig. 2 is that conducting line segment and partial parameters are schematically illustrate.
Flip verticals of the Fig. 3 for PCB image.
Fig. 4 is the flow chart of the present invention.
Specific embodiment
Measuring method of the present invention based on the printed circuit board (PCB) of microsection bianry image, including having the following steps：
1) in infput sheet the bianry image of the microsection in certain hole bitmap images, i.e. PCB image, hole handle
The white portion of PCB image is divided into upper and lower two simply connected regions, wherein, horizontal direction be hole wall direction, white represent wire,
Black represents non-wire；
2) the upper half area printed circuit board (PCB) number of plies of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor,
Concrete calculation procedure is as follows：
21) starting of conducting line segment is calculated, terminating the coordinate of pixel, row number is designated as BijAnd Eij；Conducting line segment is reflected in PCB
It is a horizontal white wire in image, the white wire is a part for certain layer conductor；According to input printed circuit board (PCB) in certain
The white that the bitmap images of the bianry image of the microsection in hole specify represents wire, black and represents non-wire, it can be found that leading
Line segment has property：Starting pixels point is white but the pixel less by 1 than the pixel row number of the pixel is black, terminates pixel
Point is white but the pixel bigger by 1 than the pixel row number of the pixel is black；
22) it is related to maximum pixel line number R of the PCB image in region when determining and calculate output parameter0；
23) conducting line segment cluster；
24) PCB layer number, outer layer conductor thickness, the thickness of every inner conductor are calculated；
3) the lower half region PCB layer number of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor, which is concrete
Method is：
31) flip vertical step 1) PCB image that is input into, obtain its flip vertical image and using the image as new defeated
Enter image；
32) the flip vertical image of input picture is counted with the computational methods for calculating upper half area before again
Calculate, obtain the lower half region PCB layer number of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor and (correspond to former input respectively
The lower half region PCB layer number of PCB image, left outside layer conductor thickness, the thickness of every inner conductor, right outer layer conductor thickness)；
4) combining step 2) and step 3) result of calculation, export the number of plies of printed circuit board (PCB) of corresponding aperture, outer layer conductor
The thickness of thickness, every inner conductor.
Above-mentioned steps concrete grammar 21) is as follows：
The height and the width of image are read in units of pixel, height H and width W is designated as respectively；Open from pixel (0,0)
Begin, conducting line segment is recognized from left to right, from top to bottom to input picture, by the starting of j-th conducting line segment of ith pixel row, terminate
The row number of pixel is designated as B respectivelyijAnd Eij, i represents the line number that pixel is located, and j represents BijAnd EijBelong to j-th conducting line segment, if
Determine the maximum possible number of plies of the maximum possible value for L, i.e. PCB of j, this patent setting L=30.
Above-mentioned steps concrete grammar 22) is as follows：
221) calculate Bmin=min { Bij；I=0,1,2 .., H, j=1,2 ..., L }, i.e. BminFor Bij(i=0,1,
2 .., H, j=1,2 ..., L) BijMinima, below be similar to explain；Calculate Emax=max { Eij；I=0,1,2 .., H, j
=1,2 ..., L }；
222) according to i=0,1,2 .., H, j=1, the order of 2 ..., L, to Bij, judge | Bij-Bmin|≤P1And | Eij-
Emax|≤P1Whether set up, once find BijSet up which, then make R0=i-Rc, go to step 23)；P1It is auxiliary for hole wall location recognition
Help parameter, unit：Pixel；100 times of PCB images P1=80,50 times of PCB images P1=[(50/100) * 80]=40, other amplifications
The P of multiple image1Value is similar to setting in proportion；RcFor the number of lines of pixels that two ends during traverse survey intercept；100 times of PCB images Rc
=40,50 times of PCB images Rc=[(50/100) * 40]=20, the R of other amplification imagescValue is similar to setting in proportion；
If there is no the B for meeting conditions aboveij, then " PCB there may be quality problems, or image abnormity " is exported, is terminated；
If 223) R0≤ 0, then " PCB there may be quality problems, or image abnormity " is exported, terminated.
Above-mentioned steps concrete grammar 23) is as follows：
231) calculate and work as j=1,2 ..., the B of jth class data during LijMinima B of attributej=min { Bij, i=0,1,
2,..,R0}；
232) calculate and work as j=1,2 ..., the E of jth class data during LijMinima E of attributej=min { Eij；I=0,1,
2,..,R0}；
233) to data to Bij、EijClustered so that each data of each apoplexy due to endogenous wind after cluster are to correspond to certain layer
The row number on the left and right border in possible wire place image white region；Concrete grammar is as follows：For i=0,1,2 .., R0, j=
1,2 ..., L, if Bij、EijFor valid data and there is BmOr Em(1≤m≤L) is caused | Bij-Bm|≤P2With | Eij-Em|≤
P2At least one establishment, then by data to Bij、EijIt is classified as m classes), the new data for finishing are clustered to B so as to obtainij、Eij：
Wherein P2To cluster auxiliary parameter, unit：Pixel；100 times of PCB images P2=80,50 times of PCB images P2=[(50/100) * 80]
=40, the P of other amplification images2Value is similar to setting in proportion：
If 234) BijWith EijAt least exist one be not belonging to it is any kind, then output " PCB there may be quality problems,
Or image abnormity ", terminate.
Above-mentioned steps concrete grammar 24) is as follows：
241) current traverse survey starting pixels line number R is set1Terminate pixel line number R with current traverse survey2Initial value be
0, PCB layer number F initial values are set to 0；
242) width of j-th conducting line segment of ith pixel row is set as Cij, then for i=0,1,2 .., R0, j=1,
2 ..., L, if Bij、EijFor valid data, C is madeij=Eij-Bij+1；
243) PCB layer number F, concrete grammar are calculated：According to j=1, the order of 2 ..., L, if there is i (i=0,1,
2,..,R0) make Cij≠ 0 F=F+1；
244) calculate the thickness C of jth layer conductorj, concrete grammar is as follows：To each j (j=1,2 ..., F), i=is taken successively
0,1,2,..,R0If there is i to make Cij≠ 0, then make R1=i+Rc, R2=R1+P3- 1, calculate Cj=min { Cij；R1≤i≤R2, P3With
In the wire segment length (unit of measurement：Pixel), 100 times of PCB images P3=43,50 times of PCB images P3=[(50/100) * 43]
=21, the P of other amplification images3Value is similar to setting in proportion；
245) PCB layer number F, left side outer layer conductor thickness C are exported0, right side outer layer conductor thickness CF；Jth internal layer from left to right
The thickness of wire is Cj, j=2,3 ..., F-1, value of the output result only when not being initialization are only effectively.
Above-mentioned 100 times of PCB images P1=80,50 times of PCB images P1=[(50/100) * 80]=40, other amplification figures
The P of picture1Value is similar to setting in proportion；RcFor the number of lines of pixels that two ends during traverse survey intercept, 100 times of PCB images Rc=40,
50 times of PCB images Rc=[(50/100) * 40]=20, the R of other amplification imagescValue is similar to setting in proportion.
Above-mentioned 100 times of PCB images P2=80,50 times of PCB images P2=[(50/100) * 80]=40, other amplification figures
The P of picture2Value is similar to setting in proportion.
Above-mentioned 100 times of PCB images P3=43,50 times of PCB images P3=[(50/100) * 43]=21, other amplification figures
The P of picture3Value is similar to setting in proportion.
The enforcement stream of the printed circuit board (PCB) number of plies and conductor thickness measuring method of the present invention based on microsection bianry image
Journey figure is as shown in Figure 4.Specific embodiment is as follows：
Step 1：The bitmap images of the bianry image of the microsection in certain hole, i.e. PCB image in infput sheet,
Hole is divided into upper and lower two simply connected regions the white portion of PCB image, wherein, horizontal direction is hole wall direction, white to represent
Wire, black represent non-wire.As shown in Figure 1.
Step 2：Calculate the upper half area printed circuit board (PCB) number of plies of corresponding aperture, outer layer conductor thickness, every inner conductor
Thickness, concrete calculation procedure are as follows：
Step 2.1：The starting of conducting line segment is calculated, terminating the coordinate of pixel, row number is designated as BijAnd Eij.Conducting line segment reflects
It is a horizontal white wire in PCB image, the white wire is a part for certain layer conductor；In printed circuit board (PCB) according to input
The white that the bitmap images of the bianry image of the microsection in certain hole specify represents wire, black and represents non-wire, Ke Yifa
Existing conducting line segment has property：Starting pixels point is white but the pixel less by 1 than the pixel row number of the pixel is black, terminates
Pixel is white but the pixel bigger by 1 than the pixel row number of the pixel is black.Concrete grammar：Read in units of pixel
The height and the width of image, are designated as height H and width W respectively.From pixel (0,0) start, to input picture from left to right, from upper
To lower identification conducting line segment, the row number of the starting of j-th conducting line segment of ith pixel row, termination pixel is designated as into B respectivelyijWith
Eij, i represents the line number that pixel is located, and j represents BijAnd EijBelong to j-th conducting line segment, the maximum possible value of j is set as L, i.e.,
The maximum possible number of plies of PCB, this patent setting L=30.
Step 2.2：It is determined that being related to maximum pixel line number R of the PCB image in region when calculating output parameter0.Concrete grammar：
Step 2.2.1：Calculate Bmin=min { Bij；I=0,1,2 .., H, j=1,2 ..., L }, i.e. BminFor Bij(i=0,
1,2 .., H, j=1,2 ..., L) BijMinima, below be similar to explain.Calculate Emax=max { Eij；I=0,1,2 ..,
H, j=1,2 ..., L }.
Step 2.2.2：According to i=0,1,2 .., H, j=1, the order of 2 ..., L, to Bij, judge | Bij-Bmin|≤P1And
|Eij-Emax|≤P1Whether set up, once find BijSet up which, then make R0=i-Rc, go to step 2.3.P1Know for hole wall position
Other auxiliary parameter (unit：Pixel).100 times of PCB images P1=80,50 times of PCB images P1=[(50/100) * 80]=40, other
The P of amplification image1Value is similar to setting in proportion；RcFor the number of lines of pixels that two ends during traverse survey intercept.100 times of PCB figures
As Rc=40,50 times of PCB images Rc=[(50/100) * 40]=20, the R of other amplification imagescValue is similar in proportion and sets
It is fixed.If there is no the B for meeting conditions aboveij, then " PCB there may be quality problems, or image abnormity " is exported, is terminated.
Step 2.2.3：If R0≤ 0, then " PCB there may be quality problems, or image abnormity " is exported, terminated.
Step 2.3：Conducting line segment is clustered.Concrete grammar：
Step 2.3.1：J=1,2 is worked as in calculating ..., the B of jth class data during LijMinima B of attributej=min { Bij, i=
0,1,2,..,R0}。
Step 2.3.2：J=1,2 is worked as in calculating ..., the E of jth class data during LijMinima E of attributej=min { Eij；I=
0,1,2,..,R0}。
Step 2.3.3：To data to Bij、EijClustered so that each data of each apoplexy due to endogenous wind after cluster are to correspondence
The row number on the left and right border in certain layer of possible wire place image white region；Concrete grammar：For i=0,1,2 .., R0, j
=1,2 ..., L, if Bij、EijFor valid data and there is BmOr Em(1≤m≤L) is caused | Bij-Bm|≤P2With | Eij-Em|
≤P2At least one establishment, then by data to Bij、EijIt is classified as m classes), the new data for finishing are clustered to B so as to obtainij、
Eij.Wherein P2To cluster auxiliary parameter (unit：Pixel).100 times of PCB images P2=80,50 times of PCB images P2=[(50/
100) * 80]=40, the P of other amplification images2Value is similar to setting in proportion.
Step 2.3.4：If BijWith EijAt least exist one be not belonging to it is any kind, then output " PCB there may be matter
Amount problem, or image abnormity ", terminates.
Step 2.4：Calculate PCB layer number, outer layer conductor thickness, the thickness of every inner conductor.Concrete grammar：
Step 2.4.1：Current traverse survey starting pixels line number R is set1Terminate pixel line number R with current traverse survey2's
Initial value is 0.PCB layer number F initial values are set to 0.
Step 2.4.2：If the width of j-th conducting line segment of ith pixel row is Cij, then for i=0,1,2 .., R0, j=
1,2 ..., L, if Bij、EijFor valid data, C is madeij=Eij-Bij+1。
Step 2.4.3：Calculate PCB layer number F.Concrete grammar：According to j=1, the order of 2 ..., L, if there is i (i=0,
1,2,..,R0) make Cij≠ 0 F=F+1.
Step 2.4.4：Calculate the thickness C of jth layer conductorj.Concrete grammar：To each j (j=1,2 ..., F), i is taken successively
=0,1,2 .., R0If there is i to make Cij≠ 0, then make R1=i+Rc, R2=R1+P3- 1, calculate Cj=min { Cij；R1≤i≤R2}。P3
For the wire segment length (unit of measurement：Pixel).100 times of PCB images P3=43,50 times of PCB images P3=[(50/100) *
43]=21, the P of other amplification images3Value is similar to setting in proportion.
Step 2.4.5：Output PCB layer number F, left side outer layer conductor thickness C0, right side outer layer conductor thickness CF；From left to right
The thickness of jth inner conductor is Cj, j=2,3 ..., F-1.Value of the output result only when not being initialization is only effectively.
So complete to calculate the upper half area PCB layer number of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor.
Step 3：The lower half region PCB layer number of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor, its
Concrete grammar is：
Step 3.1：The PCB image of flip vertical step 1 input, obtains its flip vertical image and using the image as new
Input picture.
Step 3.2：The flip vertical image of input picture is entered with the computational methods for calculating upper half area before again
Row is calculated, and is obtained the lower half region PCB layer number of corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor and (is corresponded to original respectively
The lower half region PCB layer number of input PCB image, left outside layer conductor thickness, the thickness of every inner conductor, right outer layer conductor are thick
Degree).
Step 4：The result of calculation of combining step 2 and step 3, exports the number of plies of the printed circuit board (PCB) of corresponding aperture, outer layer and leads
The thickness of line thickness, every inner conductor.
Using the method for the present invention, the measurement result of PCB image upper half area shown in Fig. 1 is as follows：PCB layer number is 5, each layer
Thickness is followed successively by 72 pixels (left outside layer), 21 pixels (the 1st internal layer), 21 pixels (the 2nd internal layer), 21 pixels (in the 3rd from left to right
Layer), 71 pixels (right outer layer)；The measurement result in lower half region is as follows：PCB layer number is 5, and each thickness degree is followed successively by 74 from left to right
Pixel (left outside layer), 21 pixels (the 1st internal layer), 21 pixels (the 2nd internal layer), 21 pixels (the 3rd internal layer), 71 pixels (right outer layer).
According to amplification during image acquisition and per the corresponding actual size of pixel, every layer conductor is readily available using this patent
Actual (real) thickness.
The method according to the invention can in the short period of time, realize that with higher precision PCB layer number and conductor thickness are surveyed
Amount.
Claims (1)
1. a kind of measuring method of the printed circuit board (PCB) based on microsection bianry image, it is characterised in that include following step
Suddenly：
1) in infput sheet the bianry image of the microsection in certain hole bitmap images, i.e. PCB image, hole is PCB
The white portion of image is divided into upper and lower two simply connected regions, wherein, horizontal direction is hole wall direction, and white represents wire, black
Color represents non-wire；
2) the upper half area printed circuit board (PCB) number of plies of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor, specifically
Calculation procedure is as follows：
21) starting of conducting line segment is calculated, terminating the coordinate of pixel, row number is designated as BijAnd Eij；Conducting line segment is reflected in PCB image
It is a horizontal white wire, the white wire is a part for certain layer conductor；According to the gold in certain hole in the printed circuit board (PCB) of input
The white that the bitmap images of the bianry image mutually cut into slices specify represents wire, black and represents non-wire, it can be found that conducting line segment tool
There is property：Starting pixels point is white but the pixel less by 1 than the pixel row number of the pixel is black, and it is white to terminate pixel
The color but pixel bigger by 1 than the pixel row number of the pixel is black；
22) it is related to maximum pixel line number R of the PCB image in region when determining and calculate output parameter0；
23) conducting line segment cluster；
24) PCB layer number, outer layer conductor thickness, the thickness of every inner conductor are calculated；
3) the lower half region PCB layer number of calculating corresponding aperture, outer layer conductor thickness, the thickness of every inner conductor, its concrete grammar
It is：
31) flip vertical step 1) PCB image that is input into, obtain its flip vertical image and using the image as new input figure
Picture；
32) the flip vertical image of input picture is calculated with the computational methods for calculating upper half area before again, is obtained
Lower half region PCB layer number, outer layer conductor thickness, the thickness of every inner conductor to corresponding aperture；
4) combining step 2) and step 3) result of calculation, export the number of plies of printed circuit board (PCB) of corresponding aperture, outer layer conductor thickness,
The thickness of every inner conductor；
Above-mentioned steps concrete grammar 21) is as follows：
The height and the width of image are read in units of pixel, height H and width W is designated as respectively；From pixel, (0,0) beginning, right
Input picture recognizes conducting line segment from left to right, from top to bottom, by the starting of j-th conducting line segment of ith pixel row, terminates pixel
Row number be designated as B respectivelyijAnd Eij, i represents the line number that pixel is located, and j represents BijAnd EijBelong to j-th conducting line segment, set j's
The maximum possible number of plies of the maximum possible value for L, i.e. PCB, sets L=30；
Above-mentioned steps concrete grammar 22) is as follows：
221) calculate Bmin=min { Bij；I=0,1,2 .., H, j=1,2 ..., L }, i.e. BminFor Bij(i=0,1,2 .., H, j
=1,2 ..., L) BijMinima, below be similar to explain；Calculate Emax=max { Eij；I=0,1,2 .., H, j=1,
2,…,L}；
222) according to i=0,1,2 .., H, j=1, the order of 2 ..., L, to Bij, judge | Bij-Bmin|≤P1And | Eij-Emax|≤
P1Whether set up, once find BijSet up which, then make R0=i-Rc, go to step 23)；P1For hole wall location recognition auxiliary parameter,
Unit：Pixel；100 times of PCB images P1=80,50 times of PCB images P1=[(50/100) * 80]=40, other amplification images
P1Value is similar to setting in proportion；RcFor the number of lines of pixels that two ends during traverse survey intercept；100 times of PCB images Rc=40,50
Times PCB image Rc=[(50/100) * 40]=20, the R of other amplification imagescValue is similar to setting in proportion；If do not deposited
Meeting the B of conditions aboveij, then " PCB there may be quality problems, or image abnormity " is exported, is terminated；
If 223) R0≤ 0, then " PCB there may be quality problems, or image abnormity " is exported, terminated；
Above-mentioned steps concrete grammar 23) is as follows：
231) calculate and work as j=1,2 ..., the B of jth class data during LijMinima B of attributej=min { Bij, i=0,1,2 ..,
R0}；
232) calculate and work as j=1,2 ..., the E of jth class data during LijMinima E of attributej=min { Eij；I=0,1,2 ..,
R0}；
233) to data to Bij、EijClustered so that each data of each apoplexy due to endogenous wind after cluster are to correspond to certain layer of possibility
The row number on the left and right border in wire place image white region；Concrete grammar is as follows：For i=0,1,2 .., R0, j=1,
2 ..., L, if Bij、EijFor valid data and there is BmOr Em(1≤m≤L) is caused | Bij-Bm|≤P2With | Eij-Em|≤P2
At least one establishment, then by data to Bij、EijM classes are classified as, and the new data for finishing are clustered to B so as to obtainij、Eij：Wherein
P2To cluster auxiliary parameter, unit：Pixel；100 times of PCB images P2=80,50 times of PCB images P2=[(50/100) * 80]=
40, the P of other amplification images2Value is similar to setting in proportion：
If 234) BijWith EijAt least exist one be not belonging to it is any kind, then output " PCB there may be quality problems, or
Image abnormity ", terminates；
Above-mentioned steps concrete grammar 24) is as follows：
241) current traverse survey starting pixels line number R is set1Terminate pixel line number R with current traverse survey2Initial value be 0,
PCB layer number F initial values are set to 0；
242) width of j-th conducting line segment of ith pixel row is set as Cij, then for i=0,1,2 .., R0, j=1,2 ..., L,
If Bij、EijFor valid data, C is madeij=Eij-Bij+1；
243) PCB layer number F, concrete grammar are calculated：According to j=1, the order of 2 ..., L, if there is i (i=0,1,2 .., R0)
Make Cij≠ 0 F=F+1；
244) calculate the thickness C of jth layer conductorj, concrete grammar is as follows：To each j (j=1,2 ..., F), i=0 is taken successively, 1,
2,..,R0If there is i to make Cij≠ 0, then make R1=i+Rc, R2=R1+P3- 1, calculate Cj=min { Cij；R1≤i≤R2, P3For surveying
The wire segment length of amount, 100 times of PCB images P3=43,50 times of PCB images P3=[(50/100) * 43]=21, other times magnifications
The P of number image3Value is similar to setting in proportion；
245) PCB layer number F, left side outer layer conductor thickness C are exported0, right side outer layer conductor thickness CF；Jth inner conductor from left to right
Thickness be Cj, j=2,3 ..., F-1, value of the output result only when not being initialization are only effectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310461359.4A CN103543151B (en) | 2013-09-29 | 2013-09-29 | A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310461359.4A CN103543151B (en) | 2013-09-29 | 2013-09-29 | A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103543151A CN103543151A (en) | 2014-01-29 |
| CN103543151B true CN103543151B (en) | 2017-04-05 |
Family
ID=49966818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310461359.4A Expired - Fee Related CN103543151B (en) | 2013-09-29 | 2013-09-29 | A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103543151B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021565B (en) * | 2014-06-26 | 2017-02-15 | 广东工业大学 | PCB (Printed Circuit Board) layer quantity and lead wire thickness measurement method based on straight-line detection |
| CN109084718A (en) * | 2018-07-10 | 2018-12-25 | 郑州云海信息技术有限公司 | The method and apparatus of medium and copper foil structure data in a kind of measurement printed circuit board |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5787191A (en) * | 1991-02-26 | 1998-07-28 | Matsushita Electric Industrial Co., Ltd. | Wiring pattern inspection apparatus for printed circuit board |
| CN101216438A (en) * | 2008-01-16 | 2008-07-09 | 中国电子科技集团公司第四十五研究所 | Printed circuit boards coarse defect image detection method based on FPGA |
| CN101799428A (en) * | 2010-04-09 | 2010-08-11 | 深圳信息职业技术学院 | Ball grid array welding spot remelting test method and marking device |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN102221549A (en) * | 2011-03-06 | 2011-10-19 | 丘荣意 | Fully-automatic board feeding optical image detecting device for PCB (printed circuit board) |
-
2013
- 2013-09-29 CN CN201310461359.4A patent/CN103543151B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5787191A (en) * | 1991-02-26 | 1998-07-28 | Matsushita Electric Industrial Co., Ltd. | Wiring pattern inspection apparatus for printed circuit board |
| CN101216438A (en) * | 2008-01-16 | 2008-07-09 | 中国电子科技集团公司第四十五研究所 | Printed circuit boards coarse defect image detection method based on FPGA |
| CN101799428A (en) * | 2010-04-09 | 2010-08-11 | 深圳信息职业技术学院 | Ball grid array welding spot remelting test method and marking device |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN102221549A (en) * | 2011-03-06 | 2011-10-19 | 丘荣意 | Fully-automatic board feeding optical image detecting device for PCB (printed circuit board) |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103543151A (en) | 2014-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548182B (en) | Pavement crack detection method and device based on deep learning and main cause analysis | |
| CN104574353B (en) | The surface defect decision method of view-based access control model conspicuousness | |
| CN109712162B (en) | Cable character defect detection method and device based on projection histogram difference | |
| WO2016055031A1 (en) | Straight line detection and image processing method and relevant device | |
| CN108009591A (en) | A kind of contact network key component identification method based on deep learning | |
| CN115283296B (en) | Visual detection system and method based on IGBT production | |
| CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
| CN109284674A (en) | A kind of method and device of determining lane line | |
| CN105844621A (en) | Method for detecting quality of printed matter | |
| JP2017053819A (en) | Crack detection method and detection program of concrete | |
| CN106056597B (en) | Object visual detection method and device | |
| CN106682665B (en) | Seven-segment type digital display instrument number identification method based on computer vision | |
| CN106951905A (en) | Apple identification and localization method on a kind of tree based on TOF camera | |
| CN106651828A (en) | Product dimension sub-pixel measurement method under industrial microscale motion blurred imaging condition | |
| JP6403547B2 (en) | Steel component identification device and program thereof | |
| CN103630093B (en) | Image analysis method for concrete surface roughness measurement | |
| CN108961331A (en) | A kind of measurement method and device of twisted string pitch | |
| CN108663382A (en) | The method and device of the paper surface defects detection of view-based access control model conspicuousness | |
| CN110910443A (en) | Contact net geometric parameter real-time measuring method and device based on single monitoring camera | |
| CN111257329A (en) | Smartphone camera defect detection method and detection system | |
| CN104614386A (en) | Lens defects type identification method | |
| CN113096121A (en) | Pavement crack detection method and system based on cross fracture mechanics and image processing | |
| CN103543151B (en) | A kind of measuring method of the printed circuit board (PCB) based on microsection bianry image | |
| CN105260559B (en) | A kind of paper pulp fiber morphological parameters calculation method based on contour area and contour thinning | |
| CN103514460B (en) | Video monitoring multi-view-angle vehicle detecting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170405 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |