CN103499585B - Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision - Google Patents
Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision Download PDFInfo
- Publication number
- CN103499585B CN103499585B CN201310498576.0A CN201310498576A CN103499585B CN 103499585 B CN103499585 B CN 103499585B CN 201310498576 A CN201310498576 A CN 201310498576A CN 103499585 B CN103499585 B CN 103499585B
- Authority
- CN
- China
- Prior art keywords
- value
- pixel
- lithium battery
- image
- film
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Secondary Cells (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to the technical field utilizing machine vision and image processing techniques to carry out on-line checkingi, relating generally to lithium battery coating machine scene utilizes Vision Builder for Automated Inspection to carry out the method for on-line checkingi to noncontinuity lithium battery film defect, a kind of noncontinuity lithium battery film defect online automatic detection method based on machine vision is provided, the method adopts the neighboring gradation of three horizontal scanning lines point differentiation method to obtain gray scale catastrophe point, thus determine between continuity thin film region, adopt the binarization segmentation of optimal threshold algorithm realization gray level image, binary image is adopted and retains large area defect method location defect target, extraction defect geometry and projection properties are as identification parameter, finally adopt minimum euclidean distance to realize defect target identify fast and classify.
Description
Art
The present invention relates to the technical field utilizing machine vision and image processing techniques to carry out on-line checkingi, relate generally to lithium battery coating machine scene and utilize Vision Builder for Automated Inspection to carry out the method for on-line checkingi to noncontinuity lithium battery film defect.
Background technology
Tradition lithium battery film surface quality detection is realized by artificial online range estimation and the sampling observation of off-line finished product, is only suitable for the occasion that production scale is little.Manual detection is using subjective impression as examination criteria, be difficult to reach the consistance detected between horizontal different product and on longitudinal different time, in addition the restriction of examined speed and sampling observation frequency, and being subject to the restriction of human eye vision sensitivity and resolution, the product quality of manual detection is difficult to be guaranteed.In addition, the method all has great infringement to the health of testing staff and psychology.Thus develop defect automatic checkout system and replace traditional manual detection, be target and the direction of the technical development of lithium battery film surface quality detection always.
Machine vision technique replaces human eye measure and judge with machine.Vision Builder for Automated Inspection refers to that the target that will be detected by machine vision product (i.e. image-pickup device) converts digital signal to, these digital signals send special image processing system again to, image processing system arranges Detection task according to the mission requirements that will detect, and then records testing result or controls on-the-spot device action according to the result differentiated.Machine vision technique is applied to surface imperfection on-line checkingi, is the research direction that surface quality on-line checkingi one is new.
For noncontinuity, the lithium battery film being separated with aluminium film, aluminium membrane portions can be judged as film defects according to conventional needle to continuity film defects detection algorithm, produce erroneous judgement.The extraction of continuity film in noncontinuity film can be realized by the searching of catastrophe point position, what adopt image optimal threshold solves the segmentation that can realize defect and background image in continuity film, area in defect image, the ratio of major diameter and minor axis, girth, circularity, waveform character in zero degree directional projection feature, pulse characteristics, sharp peaks characteristic, nargin feature, the feature extraction of flexure value and kurtosis value can realize identification and the classification of defect, what finally can show that defect produces according to the type analysis of defect is come from environmental factor, technological factor or apparatus factor, can stop and reduce the regeneration of defect like this from source, better raising quality and reduction production cost.
Summary of the invention
Object of the present invention: provide a kind of noncontinuity lithium battery film defect online automatic detection method based on machine vision, it both can reduce workman and detect labour intensity, can improve again the production efficiency of lithium battery film.
Noncontinuity lithium battery film defect inspection method based on machine vision of the present invention, comprises the steps:
Threshold decision method realizes extracting continuity zero defect film in noncontinuity zero defect film and is realized by step 1, and the structure of continuity defects thin-film template eigenwert is realized by step 2.
Step 1, employing threshold decision method realize extracting continuity zero defect film in noncontinuity zero defect film;
Step 1.1, the parameter of the industrial camera of shooting clear image is set;
Step 1.2, employing industrial camera shooting noncontinuity zero defect film, be delivered to computing machine by the standard picture of acquisition;
Step 1.3, gray processing process is carried out to standard picture;
Step 1.4,3 × 3 medium filterings are carried out to the standard picture after gray processing process;
Step 1.5, choose respectively on standard picture vertical direction 1/4,1/2 and 3/4 height horizontal scanning line;
Step 1.6, searching catastrophe point position;
Step 1.7, the minimum value choosing gray scale catastrophe point on 3 sweep traces deduct 10% of minimum value, and be the threshold value Gat extracting continuity zero defect film from the noncontinuity zero defect film containing aluminium foil, formula is as follows:
Gat=min(ωω(0),ωω(1),ωω(2))-min(ωω(0),ωω(1),ωω(2))×10%
The structure in step 2, defect image template characteristic storehouse;
Step 2.1, the parameter of the industrial camera of shooting clear image is set;
Step 2.2, employing industrial camera shooting noncontinuity defectiveness film, be delivered to computing machine by the defectiveness film graphics of acquisition;
Step 2.3, gray processing process is carried out to defectiveness film graphics;
Step 2.4,3 × 3 medium filterings are carried out to the defectiveness film graphics after gray processing process;
Step 2.5, solving of image optimal threshold is carried out to defectiveness film graphics;
Step 2.6, get optimal threshold, carry out binary conversion treatment to the image after step 2.4 processes, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 2.7, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, be 0 by other the 1 value pixel assignment beyond maximum area region;
Step 2.8, characteristic parameter extraction (this step is shown in below);
Step 3, extract lithium battery film continuity image-region to be detected;
Step 3.1, the parameter of the industrial camera of shooting clear image is set;
Step 3.2, employing industrial camera take lithium battery film to be detected, and the lithium battery film image to be detected obtained is delivered to computing machine;
Step 3.3, gray processing process is carried out to lithium battery film image to be detected;
Step 3.4,3 × 3 medium filterings are carried out to lithium battery film image to be detected;
Step 3.5, choose on lithium battery film image vertical direction to be detected 1/2 height horizontal scanning line, add up the gray scale catastrophe point number 1/2 height scan line being greater than the threshold value Gat in step 1.7,
If gray scale catastrophe point number is 0, be lithium battery film continuity chart picture to be detected;
If gray scale catastrophe point number is 1, and catastrophe point maximum position value is less than the half of image level pixel value, as shown in Fig. 1 (b), get maximum position in gray scale catastrophe point and add 4 again, with lithium battery film right margin, form lithium battery film continuity chart picture to be detected;
If catastrophe point number is 1, and catastrophe point minimum position value is greater than the half of image level pixel value, and as shown in Fig. 1 (f), get lithium battery film left margin, in gray scale catastrophe point, minimum position subtracts 4 again, forms continuity lithium battery film region;
If catastrophe point number is 2, as shown in Fig. 1 (c-e), get lithium battery film left margin, left side gray scale catastrophe point minimum position subtracts 4 again, form continuity lithium battery film region 1, get maximum position in the gray scale catastrophe point of right side and add 4 again, with lithium battery film right margin, form continuity lithium battery film region 1, region 1 and region 2 form continuity lithium battery film region;
Step 4, the feature extraction of lithium battery film continuity chart picture to be detected, detection and Identification
Step 4.1, obtain lithium battery film continuity chart picture to be detected by step 3;
Step 4.2, solving of image optimal threshold is carried out to lithium battery film continuity chart picture to be detected;
Step 4.3, get optimal threshold, carry out binary conversion treatment to lithium battery film continuity chart picture to be detected, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 4.4, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, other the 1 value pixel assignment beyond maximum area region is 0;
Step 4.5, characteristic parameter extraction;
Step 4.6, arrange and detect the accuracy rating of parameter, described detection parameter is that in the image after binary conversion treatment, 1 value pixel accounts for image pixel number percent;
The detection of step 4.7, testing image judges.
If percent value reaches accuracy rating, be then continuity zero defect film, computing machine judges that film is qualified.Otherwise be continuity defects film, be judged as defective;
The identification of step 4.8, testing image.
By step 4.7, if film is judged as defective, then the characteristic parameter that in the characteristic parameter extracted by the continuity defects film graphics of captured in real-time in step 4.5 and step 2.8, recognition template extracts adopts minimum euclidean distance algorithm realization identify fast and classify.
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said image optimal threshold to solve concrete steps as follows:
A image that () will obtain after carrying out gray processing process, be divided into 256 grades according to the gray-scale value of pixel, i is the progression of pixel, and the span of i is 0 ~ 255, and the total pixel number of image is N,
wherein N
irepresent the number of i-th grade of pixel, the probability of i-th grade of pixel appearance is P
i, P
i=N
i/ N;
B () gets threshold value k (0≤k≤255), each pixel is divided into two classes: first kind pixel is the pixel of gray-scale value in 0 ~ k closed interval, and the set of first kind pixel is C
0, Equations of The Second Kind pixel is the pixel of all gray-scale values in closed interval, k+1 ~ 255, and the set of Equations of The Second Kind pixel is C
1;
The overall average gray level μ of (c) computed image
μ,
c
0average gray level be μ
0(k),
c
1average gray level be μ
1(k), μ
1(k)=μ
t-μ
0(k);
D () calculates C
0the proportion omegab of area occupied
0,
calculate C
1the proportion omegab of area occupied
1,
E () k increases gradually by 0, make μ
0=μ
0(k)/ω
0, μ
1=μ
1(k)/ω
1, wherein μ
0for C
0average gray level and C
0area occupied proportion omegab
0ratio, μ
1for C
1average gray level and C
1area occupied proportion omegab
0ratio, calculate ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2, work as ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2time maximum, threshold value is now optimal threshold.
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said characteristic parameter extraction concrete steps are as follows:
Extract corresponding characteristic parameter and be stored in computing machine, as recognition feature library template, described characteristic parameter comprises the ratio of area, major diameter and minor axis in the geometric properties of defect image, girth and circularity, waveform character in zero degree directional projection feature, pulse characteristics, sharp peaks characteristic, nargin feature, flexure value and kurtosis value, described characteristic parameter is the content of this area formula, and the formula of characteristic parameter is as follows:
(a) area S:
wherein x
1for horizontal ordinate, y
1for ordinate, R
dfor pixel value is the region of 1, n
1for region point number;
The ratio of (b) major diameter and minor axis
wherein L
1major diameter, L
2it is minor axis;
(c) girth PP:
wherein x
2for horizontal ordinate, y
2for ordinate, R
bfor pixel value is the region of 1, n
2for region point number;
(d) circularity e:
wherein S is area, and PP is girth;
(f) projection waveform character F
b:
wherein xx (t) is zero degree direction projection value, and 1≤t≤T, T is zero degree direction projection total value;
(g) projection pulse characteristics F
m:
(h) projection sharp peaks characteristic F
f:
(i) projection nargin feature F
y:
(j) projection flexure value F
s:
the probability density function be wherein p (xx) being xx (t);
(k) projection kurtosis value F
k:
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said searching catastrophe point position concrete steps are as follows:
The gray-scale value A of 3 pixels nearest on the right side of pixel on note sweep trace
1, A
2, A
3, the gray-scale value B of 3 pixels nearest on the left of pixel on note sweep trace
1, B
2, B
3,
A
1=xy
1(v
1-3)+xy
1(v
1-2)+xy
1(v
1-1)
A
2=xy
2(v
2-3)+xy
2(v
2-2)+xy
2(v
2-1)
A
3=xy
3(v
3-3)+xy
3(v
3-2)+xy
3(v
3-1)
B
1=xy
1(v
1+1)+xy
1(v
1+2)+xy
1(v
1+3)
B
2=xy
2(v
2+1)+xy
2(v
2+2)+xy
2(v
2+3)
B
3=xy
3(v
3+1)+xy
3(v
3+2)+xy
3(v
3+3)
Wherein v
1, v
2, v
3be respectively the abscissa value of the pixel of the horizontal scanning line of 1/4,1/2,3/4 height, 4≤v
1≤ MM-4,4≤v
2≤ MM-4,4≤v
3≤ MM-4, MM are image horizontal ordinate maximal value; Wherein xy
1(v
1) be 1/4 height horizontal scanning line on v
1pixel value, xy
2(v
2) be 1/2 height horizontal scanning line on v
2pixel value, xy
3(v
3) be 3/4 height horizontal scanning line on v
3pixel value;
A
1with B
1the absolute value of difference, A
2with B
2the absolute value of difference, A
3with B
3the absolute value of difference is designated as C respectively
1, C
2, C
3; Then C
1=| A
1-B
1|, C
2=| A
2-B
2|, C
3=| A
3-B
3|;
Progressively increase v
1, v
2, v
3value, works as C
1when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (0) on 1/4 sweep trace; Work as C
2when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (1) on 1/2 sweep trace; Work as C
3when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (2) on 3/4 sweep trace.
Advantage of the present invention: a kind of noncontinuity lithium battery film defect online automatic detection method based on machine vision is provided, the method adopts the neighboring gradation of three horizontal scanning lines point differentiation method to obtain gray scale catastrophe point, thus determine between continuity thin film region, adopt the binarization segmentation of optimal threshold algorithm realization gray level image, binary image is adopted and retains large area defect method location defect target, extraction defect geometry and projection properties, as identification parameter, finally adopt minimum euclidean distance to realize defect target and identify fast and classify.The invention provides the recognition methods based on machine vision, parameter can adjust according to actual needs, and recognition efficiency is high, and discrimination is stablized, and can enhance productivity and reduce production cost.
Accompanying drawing explanation
Fig. 1 is six kinds of noncontinuity lithium battery film images, and wherein grey represents lithium battery film, and white represents aluminium film.
The horizontal scanning line schematic diagram of 1/4,1/2 and 3/4 height that Fig. 2 image vertical direction is chosen.
The structure process flow diagram in Fig. 3 defect image template characteristic storehouse.
Fig. 4 extracts the threshold value determination process flow diagram of continuity zero defect film from the noncontinuity zero defect film containing aluminium foil.
The identification process figure of Fig. 5 defect image to be measured.
Embodiment
Embodiment 1,
Noncontinuity lithium battery film defect inspection method based on machine vision of the present invention, comprises the steps:
Threshold decision method realizes extracting continuity zero defect film in noncontinuity zero defect film and is realized by step 1, and the structure of continuity defects thin-film template eigenwert is realized by step 2.
Step 1, employing threshold decision method realize extracting continuity zero defect film in noncontinuity zero defect film;
Step 1.1, the parameter of the industrial camera of shooting clear image is set;
Step 1.2, employing industrial camera shooting noncontinuity zero defect film, be delivered to computing machine by the standard picture of acquisition;
Step 1.3, gray processing process is carried out to standard picture;
Step 1.4,3 × 3 medium filterings are carried out to the standard picture after gray processing process;
Step 1.5, choose respectively on standard picture vertical direction 1/4,1/2 and 3/4 height horizontal scanning line;
Step 1.6, searching catastrophe point position;
Step 1.7, the minimum value choosing gray scale catastrophe point on 3 sweep traces deduct 10% of minimum value, and be the threshold value Gat extracting continuity zero defect film from the noncontinuity zero defect film containing aluminium foil, formula is as follows:
Gat=min(ωω(0),ωω(1),ωω(2))-min(ωω(0),ωω(1),ωω(2))×10%
The structure in step 2, defect image template characteristic storehouse;
Step 2.1, the parameter of the industrial camera of shooting clear image is set;
Step 2.2, employing industrial camera shooting noncontinuity defectiveness film, be delivered to computing machine by the defectiveness film graphics of acquisition;
Step 2.3, gray processing process is carried out to defectiveness film graphics;
Step 2.4,3 × 3 medium filterings are carried out to the defectiveness film graphics after gray processing process;
Step 2.5, solving of image optimal threshold is carried out to defectiveness film graphics;
Step 2.6, get optimal threshold, carry out binary conversion treatment to the image after step 2.4 processes, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 2.7, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, be 0 by other the 1 value pixel assignment beyond maximum area region;
Step 2.8, characteristic parameter extraction (this step is shown in below);
Step 3, extract lithium battery film continuity image-region to be detected;
Step 3.1, the parameter of the industrial camera of shooting clear image is set;
Step 3.2, employing industrial camera take lithium battery film to be detected, and the lithium battery film image to be detected obtained is delivered to computing machine;
Step 3.3, gray processing process is carried out to lithium battery film image to be detected;
Step 3.4,3 × 3 medium filterings are carried out to lithium battery film image to be detected;
Step 3.5, choose on lithium battery film image vertical direction to be detected 1/2 height horizontal scanning line, add up the gray scale catastrophe point number 1/2 height scan line being greater than the threshold value Gat in step 1.7,
If gray scale catastrophe point number is 0, be lithium battery film continuity chart picture to be detected;
If gray scale catastrophe point number is 1, and catastrophe point maximum position value is less than the half of image level pixel value, as shown in Fig. 1 (b), get maximum position in gray scale catastrophe point and add 4 again, with lithium battery film right margin, form lithium battery film continuity chart picture to be detected;
If catastrophe point number is 1, and catastrophe point minimum position value is greater than the half of image level pixel value, and as shown in Fig. 1 (f), get lithium battery film left margin, in gray scale catastrophe point, minimum position subtracts 4 again, forms continuity lithium battery film region;
If catastrophe point number is 2, as shown in Fig. 1 (c-e), get lithium battery film left margin, left side gray scale catastrophe point minimum position subtracts 4 again, form continuity lithium battery film region 1, get maximum position in the gray scale catastrophe point of right side and add 4 again, with lithium battery film right margin, form continuity lithium battery film region 1, region 1 and region 2 form continuity lithium battery film region;
Step 4, the feature extraction of lithium battery film continuity chart picture to be detected, detection and Identification
Step 4.1, obtain lithium battery film continuity chart picture to be detected by step 3;
Step 4.2, solving of image optimal threshold is carried out to lithium battery film continuity chart picture to be detected;
Step 4.3, get optimal threshold, carry out binary conversion treatment to lithium battery film continuity chart picture to be detected, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 4.4, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, other the 1 value pixel assignment beyond maximum area region is 0;
Step 4.5, characteristic parameter extraction;
Step 4.6, arrange and detect the accuracy rating of parameter, described detection parameter is that in the image after binary conversion treatment, 1 value pixel accounts for image pixel number percent;
The detection of step 4.7, testing image judges.
If percent value reaches accuracy rating, be then continuity zero defect film, computing machine judges that film is qualified.Otherwise be continuity defects film, be judged as defective;
The identification of step 4.8, testing image.
By step 4.7, if film is judged as defective, then the characteristic parameter that in the characteristic parameter extracted by the continuity defects film graphics of captured in real-time in step 4.5 and step 2.8, recognition template extracts adopts minimum euclidean distance algorithm realization identify fast and classify.
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said image optimal threshold to solve concrete steps as follows:
A image that () will obtain after carrying out gray processing process, be divided into 256 grades according to the gray-scale value of pixel, i is the progression of pixel, and the span of i is 0 ~ 255, and the total pixel number of image is N,
wherein N
irepresent the number of i-th grade of pixel, the probability of i-th grade of pixel appearance is P
i, P
i=N
i/ N;
B () gets threshold value k (0≤k≤255), each pixel is divided into two classes: first kind pixel is the pixel of gray-scale value in 0 ~ k closed interval, and the set of first kind pixel is C
0, Equations of The Second Kind pixel is the pixel of all gray-scale values in closed interval, k+1 ~ 255, and the set of Equations of The Second Kind pixel is C
1;
The overall average gray level μ of (c) computed image
t,
c
0average gray level be μ
0(k),
c
1average gray level be μ 1 (k), μ
1(k)=μ
t-μ
0(k);
D () calculates C
0the proportion omegab of area occupied
0,
calculate C
1the proportion omegab of area occupied
1,
E () k increases gradually by 0, make μ
0=μ
0(k)/ω
0, μ
1=μ
1(k)/ω
1, wherein μ
0for C
0average gray level and C
0area occupied proportion omegab
0ratio, μ
1for C
1average gray level and C
1area occupied proportion omegab
0ratio, calculate ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2, work as ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2time maximum, threshold value is now optimal threshold.
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said characteristic parameter extraction concrete steps are as follows:
Extract corresponding characteristic parameter and be stored in computing machine, as recognition feature library template, described characteristic parameter comprises the ratio of area, major diameter and minor axis in the geometric properties of defect image, girth and circularity, waveform character in zero degree directional projection feature, pulse characteristics, sharp peaks characteristic, nargin feature, flexure value and kurtosis value, above-mentioned characteristic formula is as follows:
(a) area S:
wherein x
1for horizontal ordinate, y
1for ordinate, R
dfor pixel value is the region of 1, n
1for region point number;
The ratio of (b) major diameter and minor axis
wherein L
1major diameter, L
2it is minor axis;
(c) girth PP:
wherein x
2for horizontal ordinate, y
2for ordinate, R
bfor pixel value is the region of 1, n
2for region point number;
(d) circularity e:
wherein S is area, and PP is girth;
(f) projection waveform character F
b:
wherein xx (t) is zero degree direction projection value, and 1≤t≤T, T is zero degree direction projection total value;
(g) projection pulse characteristics F
m:
(h) projection sharp peaks characteristic F
f:
(i) projection nargin feature F
y:
(j) projection flexure value F
s:
the probability density function be wherein p (xx) being xx (t);
(k) projection kurtosis value F
k:
The above-mentioned noncontinuity lithium battery film defect inspection method based on machine vision, wherein said searching catastrophe point position concrete steps are as follows:
The gray-scale value A of 3 pixels nearest on the right side of pixel on note sweep trace
1, A
2, A
3, the gray-scale value B of 3 pixels nearest on the left of pixel on note sweep trace
1, B
2, B
3,
A
1=xy
1(v
1-3)+xy
1(v
1-2)+xy
1(v
1-1)
A
2=xy
2(v
2-3)+xy
2(v
2-2)+xy
2(v
2-1)
A
3=xy
3(v
3-3)+xy
3(v
3-2)+xy
3(v
3-1)
B
1=xy
1(v
1+1)+xy
1(v
1+2)+xy
1(v
1+3)
B
2=xy
2(v
2+1)+xy
2(v
2+2)+xy
2(v
2+3)
B
3=xy
3(v
3+1)+xy
3(v
3+2)+xy
3(v
3+3)
Wherein v
1, v
2, v
3be respectively the abscissa value of the pixel of the horizontal scanning line of 1/4,1/2,3/4 height, 4≤v
1≤ MM-4,4≤v
2≤ MM-4,4≤v
3≤ MM-4, MM are image horizontal ordinate maximal value; Wherein xy
1(v
1) be 1/4 height horizontal scanning line on v
1pixel value, xy
2(v
2) be 1/2 height horizontal scanning line on v
2pixel value, xy
3(v
3) be 3/4 height horizontal scanning line on v
3pixel value;
A
1with B
1the absolute value of difference, A
2with B
2the absolute value of difference, A
3with B
3the absolute value of difference is designated as C respectively
1, C
2, C
3; Then C
1=| A
1-B
1|, C
2=| A
2-B
2|, C
3=| A
3-B
3|;
Progressively increase v
1, v
2, v
3value, works as C
1when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (0) on 1/4 sweep trace; Work as C
2when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (1) on 1/2 sweep trace; Work as C
3when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (2) on 3/4 sweep trace.
Claims (4)
1., based on the noncontinuity lithium battery film defect inspection method of machine vision, it is characterized in that comprising the steps:
Step 1, employing threshold decision method realize extracting continuity zero defect film in noncontinuity zero defect film;
Step 1.1, the parameter of the industrial camera of shooting clear image is set;
Step 1.2, employing industrial camera shooting noncontinuity zero defect film, be delivered to computing machine by the standard picture of acquisition;
Step 1.3, gray processing process is carried out to standard picture;
Step 1.4,3 × 3 medium filterings are carried out to the standard picture after gray processing process;
Step 1.5, choose respectively on standard picture vertical direction 1/4,1/2 and 3/4 height horizontal scanning line;
Step 1.6, searching catastrophe point position;
Step 1.7, the minimum value choosing gray scale catastrophe point on 3 sweep traces deduct 10% of minimum value, and be the threshold value Gat extracting continuity zero defect film from the noncontinuity zero defect film containing aluminium foil, formula is as follows:
Gat=min(ωω(0),ωω(1),ωω(2))-min(ωω(0),ωω(1),ωω(2))×10%;
ω ω (0) is the gray scale catastrophe point on 1/4 sweep trace, and ω ω (1) is the gray scale catastrophe point on 1/2 sweep trace, and ω ω (2) is the gray scale catastrophe point on 3/4 sweep trace;
The structure in step 2, defect image template characteristic storehouse;
Step 2.1, the parameter of the industrial camera of shooting clear image is set;
Step 2.2, employing industrial camera shooting noncontinuity defectiveness film, be delivered to computing machine by the defectiveness film graphics of acquisition;
Step 2.3, gray processing process is carried out to defectiveness film graphics;
Step 2.4,3 × 3 medium filterings are carried out to the defectiveness film graphics after gray processing process;
Step 2.5, solving of image optimal threshold is carried out to defectiveness film graphics;
Step 2.6, get optimal threshold, carry out binary conversion treatment to the image after step 2.4 processes, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 2.7, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, be 0 by other the 1 value pixel assignment beyond maximum area region;
Step 2.8, characteristic parameter extraction;
Step 3, extract lithium battery film continuity image-region to be detected;
Step 3.1, the parameter of the industrial camera of shooting clear image is set;
Step 3.2, employing industrial camera take lithium battery film to be detected, and the lithium battery film image to be detected obtained is delivered to computing machine;
Step 3.3, gray processing process is carried out to lithium battery film image to be detected;
Step 3.4,3 × 3 medium filterings are carried out to lithium battery film image to be detected;
Step 3.5, choose on lithium battery film image vertical direction to be detected 1/2 height horizontal scanning line, add up the gray scale catastrophe point number 1/2 height scan line being greater than the threshold value Gat in step 1.7,
If gray scale catastrophe point number is 0, be lithium battery film continuity chart picture to be detected;
If gray scale catastrophe point number is 1, and catastrophe point maximum position value is less than the half of image level pixel value, gets maximum position in gray scale catastrophe point and adds 4 again, with lithium battery film right margin, forms lithium battery film continuity chart picture to be detected;
If catastrophe point number is 1, and catastrophe point minimum position value is greater than the half of image level pixel value, gets lithium battery film left margin, and in gray scale catastrophe point, minimum position subtracts 4 again, forms continuity lithium battery film region;
If catastrophe point number is 2, get lithium battery film left margin, left side gray scale catastrophe point minimum position subtracts 4 again, form continuity lithium battery film region 1, get maximum position in the gray scale catastrophe point of right side and add 4 again, with lithium battery film right margin, form continuity lithium battery film region 2, region 1 and region 2 form continuity lithium battery film region;
Step 4, the feature extraction of lithium battery film continuity chart picture to be detected, detection and Identification;
Step 4.1, obtain lithium battery film continuity chart picture to be detected by step 3;
Step 4.2, solving of image optimal threshold is carried out to lithium battery film continuity chart picture to be detected;
Step 4.3, get optimal threshold, carry out binary conversion treatment to lithium battery film continuity chart picture to be detected, gray-scale value is less than or equal to the pixel assignment 0 of optimal threshold, gray-scale value is greater than the pixel assignment 1 of optimal threshold;
Step 4.4, to the image after binary conversion treatment, retain 1 value pixel form maximum area region, other the 1 value pixel assignment beyond maximum area region is 0;
Step 4.5, characteristic parameter extraction;
Step 4.6, arrange and detect the accuracy rating of parameter, described detection parameter is that in the image after binary conversion treatment, 1 value pixel accounts for image pixel number percent;
The detection of step 4.7, testing image judges;
If percent value reaches accuracy rating, be then continuity zero defect film, computing machine judges that film is qualified; Otherwise be continuity defects film, be judged as defective;
The identification of step 4.8, testing image;
By step 4.7, if film is judged as defective, then the characteristic parameter that in the characteristic parameter extracted by the continuity defects film graphics of captured in real-time in step 4.5 and step 2.8, recognition template extracts adopts minimum euclidean distance algorithm realization identify fast and classify.
2. the noncontinuity lithium battery film defect inspection method based on machine vision according to claim 1, is characterized in that, wherein said image optimal threshold to solve concrete steps as follows:
A image that () will obtain after carrying out gray processing process, be divided into 256 grades according to the gray-scale value of pixel, i is the progression of pixel, and the span of i is 0 ~ 255, and the total pixel number of image is N,
wherein N
irepresent the number of i-th grade of pixel, the probability of i-th grade of pixel appearance is P
i, P
i=N
i/ N;
B () gets threshold value k (0≤k≤255), each pixel is divided into two classes: first kind pixel is the pixel of gray-scale value in 0 ~ k closed interval, and the set of first kind pixel is C
0, Equations of The Second Kind pixel is the pixel of all gray-scale values in closed interval, k+1 ~ 255, and the set of Equations of The Second Kind pixel is C
1;
The overall average gray level μ of (c) computed image
t,
c
0average gray level be μ
0(k),
c
1average gray level be μ
1(k), μ
1(k)=μ
t-μ
0(k);
D () calculates C
0the proportion omegab of area occupied
0,
calculate C
1the proportion omegab of area occupied
1,
E () k increases gradually by 0, make μ
0=μ
0(k)/ω
0, μ
1=μ
1(k)/ω
1, wherein μ
0for C
0average gray level and C
0area occupied proportion omegab
0ratio, μ
1for C
1average gray level and C
1area occupied proportion omegab
1ratio, calculate ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2, work as ω
0(μ
0-μ
t)
2+ ω
1(μ
1-μ
t)
2time maximum, threshold value is now optimal threshold.
3. the noncontinuity lithium battery film defect inspection method based on machine vision according to claim 1, is characterized in that: wherein said characteristic parameter extraction concrete steps are as follows:
Extract corresponding characteristic parameter and be stored in computing machine, as recognition feature library template, described characteristic parameter comprises the ratio of area, major diameter and minor axis in the geometric properties of defect image, girth and circularity, waveform character in zero degree directional projection feature, pulse characteristics, sharp peaks characteristic, nargin feature, flexure value and kurtosis value, above-mentioned characteristic formula is as follows:
(a) area S:
wherein x
1for horizontal ordinate, y
1for ordinate, R
dfor pixel value is the region of 1, n
1for region point number;
The ratio of (b) major diameter and minor axis
wherein L
1major diameter, L
2it is minor axis;
(c) girth PP:
wherein x
2for horizontal ordinate, y
2for ordinate, R
bfor pixel value is the region of 1, n
2for region point number;
(d) circularity e:
wherein S is area, and P is girth;
(f) projection waveform character F
b:
wherein xx (t) is zero degree direction projection value, and 1≤t≤T, T is zero degree direction projection total value;
(g) projection pulse characteristics F
m:
(h) projection sharp peaks characteristic F
f:
(i) projection nargin feature F
y:
(j) projection flexure value F
s:
the probability density function be wherein p (xx) being xx (t);
(k) projection kurtosis value F
k:
4. the noncontinuity lithium battery film defect inspection method based on machine vision according to claim 1, is characterized in that, wherein said searching catastrophe point position concrete steps are as follows:
The gray-scale value A of 3 pixels nearest on the right side of pixel on note sweep trace
1, A
2, A
3, the gray-scale value B of 3 pixels nearest on the left of pixel on note sweep trace
1, B
2, B
3,
A
1=xy
1(v
1-3)+xy
1(v
1-2)+xy
1(v
1-1)
A
2=xy
2(v
2-3)+xy
2(v
2-2)+xy
2(v
2-1)
A
3=xy
3(v
3-3)+xy
3(v
3-2)+xy
3(v
3-1)
B
1=xy
1(v
1+1)+xy
1(v
1+2)+xy
1(v
1+3)
B
2=xy
2(v
2+1)+xy
2(v
2+2)+xy
2(v
2+3)
B
3=xy
3(v
3+1)+xy
3(v
3+2)+xy
3(v
3+3)
Wherein v
1, v
2, v
3be respectively the abscissa value of the pixel of the horizontal scanning line of 1/4,1/2,3/4 height, 4≤v
1≤ MM-4,4≤v
2≤ MM-4,4≤v
3≤ MM-4, MM are image horizontal ordinate maximal value; Wherein xy
1(v
1) be 1/4 height horizontal scanning line on v
1pixel value, xy
2(v
2) be 1/2 height horizontal scanning line on v
2pixel value, xy
3(v
3) be 3/4 height horizontal scanning line on v
3pixel value;
A
1with B
1the absolute value of difference, A
2with B
2the absolute value of difference, A
3with B
3the absolute value of difference is designated as C respectively
1, C
2, C
3; Then C
1=| A
1-B
1|, C
2=| A
2-B
2|, C
3=| A
3-B
3|;
Progressively increase v
1, v
2, v
3value, works as C
1when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (0) on 1/4 sweep trace; Work as C
2when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (1) on 1/2 sweep trace; Work as C
3when reaching maximal value, corresponding location of pixels is the gray scale catastrophe point ω ω (2) on 3/4 sweep trace.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310498576.0A CN103499585B (en) | 2013-10-22 | 2013-10-22 | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310498576.0A CN103499585B (en) | 2013-10-22 | 2013-10-22 | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103499585A CN103499585A (en) | 2014-01-08 |
CN103499585B true CN103499585B (en) | 2015-07-29 |
Family
ID=49864815
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310498576.0A Active CN103499585B (en) | 2013-10-22 | 2013-10-22 | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103499585B (en) |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104359920B (en) * | 2014-11-18 | 2017-01-25 | 杭州电子科技大学 | Image processing method for apparent defect detection of thin-film capacitor |
CN104655644A (en) * | 2015-02-13 | 2015-05-27 | 华南理工大学 | Method and device for automatically detecting defects of lithium battery pole piece |
CN105092591A (en) * | 2015-08-27 | 2015-11-25 | 任红霞 | Image-processing-based workpiece defect positioning method |
CN105548201B (en) * | 2016-01-15 | 2018-07-13 | 浙江野马电池有限公司 | A kind of battery welding cap visible detection method |
CN105548216B (en) * | 2016-01-15 | 2019-03-12 | 浙江野马电池有限公司 | A kind of semi-finished product battery apparent visual detection method |
CN105548186B (en) * | 2016-01-15 | 2018-09-14 | 浙江野马电池有限公司 | A kind of pulp layered paper visible detection method |
CN105783782B (en) * | 2016-05-12 | 2018-06-15 | 电子科技大学 | Surface curvature is mutated optical profilometry methodology |
CN106546897A (en) * | 2016-11-01 | 2017-03-29 | 山东大学 | Solar cell luminescence generated by light high-speed detection system and its operation method based on short-wave infrared imager |
CN106770321B (en) * | 2016-12-08 | 2019-07-19 | 广东工业大学 | A kind of plastic part defect inspection method based on multi-threshold section |
CN107941808B (en) * | 2017-11-10 | 2024-04-12 | 中国计量大学 | 3D printing forming quality detection system and method based on machine vision |
CN107941805A (en) * | 2017-12-01 | 2018-04-20 | 无锡先导智能装备股份有限公司 | Battery core quality determining method |
CN108107051B (en) * | 2017-12-19 | 2020-03-31 | 无锡先导智能装备股份有限公司 | Lithium battery defect detection system and method based on machine vision |
CN108333188A (en) * | 2018-02-01 | 2018-07-27 | 天津力神电池股份有限公司 | A kind of online apparent visual detection device of battery pole piece |
CN108694711A (en) * | 2018-02-19 | 2018-10-23 | 江苏新时高温材料股份有限公司 | Ceramic membrane surface defect two-dimensional detecting method is realized based on machine vision technique |
CN109360186A (en) * | 2018-08-31 | 2019-02-19 | 广州超音速自动化科技股份有限公司 | Lithium battery diaphragm detection method, electronic equipment, storage medium and system |
CN109738437B (en) * | 2018-12-29 | 2021-07-06 | 西安西电电力电容器有限责任公司 | Self-healing point measuring device and method for metalized film capacitor |
EP3905696A4 (en) * | 2019-01-07 | 2022-06-08 | Sony Group Corporation | Image processing device and method |
CN109870459B (en) * | 2019-02-21 | 2021-07-06 | 武汉光谷卓越科技股份有限公司 | Track slab crack detection method for ballastless track |
CN109732270B (en) * | 2019-02-23 | 2020-10-02 | 圣达电气有限公司 | Ray type copper foil overhauling and correcting process |
CN109946315A (en) * | 2019-03-14 | 2019-06-28 | 镇江苏仪德科技有限公司 | A kind of appearance delection device of solar battery sheet |
CN110389127B (en) * | 2019-07-03 | 2020-08-14 | 浙江大学 | System and method for identifying metal ceramic parts and detecting surface defects |
CN111667475B (en) * | 2020-06-09 | 2023-04-18 | 陕西科技大学 | Machine vision-based Chinese date grading detection method |
CN112710669A (en) * | 2020-12-09 | 2021-04-27 | 北方华锦化学工业股份有限公司 | Method for rapidly evaluating crystal points of hard elastic diaphragm of homo-polypropylene lithium battery |
CN113030093B (en) * | 2020-12-30 | 2022-07-22 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
CN113129260B (en) * | 2021-03-11 | 2023-07-21 | 广东工业大学 | Automatic detection method and device for internal defects of lithium battery cell |
WO2023077404A1 (en) * | 2021-11-05 | 2023-05-11 | 宁德时代新能源科技股份有限公司 | Defect detection method, apparatus and system |
CN114136981A (en) * | 2021-11-26 | 2022-03-04 | 广东速美达自动化股份有限公司 | Detection method and detection system for Mylar film of lithium battery pack |
CN114764790B (en) * | 2022-03-31 | 2023-05-12 | 河北鹰眼智能科技有限公司 | Gear broken tooth detection method based on Hough circle detection |
CN115631173B (en) * | 2022-10-28 | 2023-04-18 | 兰州理工大学 | Composite film defect identification method |
CN115963114B (en) * | 2023-02-28 | 2023-07-28 | 广东鲲鹏环保技术有限公司 | Lithium battery production quality inspection system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6075880A (en) * | 1994-03-16 | 2000-06-13 | Jenoptik Technologie Gmbh | Method for detection of defects in the inspection of structured surfaces |
CN102636490A (en) * | 2012-04-12 | 2012-08-15 | 江南大学 | Method for detecting surface defects of dustproof cover of bearing based on machine vision |
CN103245666A (en) * | 2013-04-02 | 2013-08-14 | 杭州电子科技大学 | Automatic detecting method for appearance defects of storage battery polar plate |
CN103258206A (en) * | 2012-11-28 | 2013-08-21 | 河海大学常州校区 | Silicon solar cell surface defect detection and identification method |
CN103345632A (en) * | 2013-06-25 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Method for detecting surface scratch defects of battery tail end |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3657930B2 (en) * | 2002-07-05 | 2005-06-08 | パイオニアプラズマディスプレイ株式会社 | Plasma display panel manufacturing method, phosphor layer inspection method, and phosphor layer inspection apparatus |
WO2011016420A1 (en) * | 2009-08-03 | 2011-02-10 | 株式会社エヌ・ピー・シー | Solar cell defect inspection apparatus, defect inspection method and program |
-
2013
- 2013-10-22 CN CN201310498576.0A patent/CN103499585B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6075880A (en) * | 1994-03-16 | 2000-06-13 | Jenoptik Technologie Gmbh | Method for detection of defects in the inspection of structured surfaces |
CN102636490A (en) * | 2012-04-12 | 2012-08-15 | 江南大学 | Method for detecting surface defects of dustproof cover of bearing based on machine vision |
CN103258206A (en) * | 2012-11-28 | 2013-08-21 | 河海大学常州校区 | Silicon solar cell surface defect detection and identification method |
CN103245666A (en) * | 2013-04-02 | 2013-08-14 | 杭州电子科技大学 | Automatic detecting method for appearance defects of storage battery polar plate |
CN103345632A (en) * | 2013-06-25 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Method for detecting surface scratch defects of battery tail end |
Non-Patent Citations (2)
Title |
---|
基于亮度和OAA-SVM锂电池薄膜缺陷识别;陈功 等;《通信技术》;20130310;第46卷(第3期);第107-109页 * |
锂电池薄膜缺陷图像特征提取技术研究;吴雪芬 等;《电子质量》;20130820(第08期);第17-19页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103499585A (en) | 2014-01-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103499585B (en) | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision | |
Yanan et al. | Rail surface defect detection method based on YOLOv3 deep learning networks | |
CN102854191B (en) | Real-time visual detection and identification method for high speed rail surface defect | |
CN104535586B (en) | Strip steel edge defect detection identification method | |
Liang et al. | Defect detection of rail surface with deep convolutional neural networks | |
CN110211101A (en) | A kind of rail surface defect rapid detection system and method | |
CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
CN104101600A (en) | Method and apparatus for detecting fine cracks on cross section of continuous casting slab | |
Dubey et al. | Maximally stable extremal region marking-based railway track surface defect sensing | |
CN105571502A (en) | Measuring method of weld gap in friction-stir welding | |
CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
CN115797354B (en) | Method for detecting appearance defects of laser welding seam | |
CN104992429A (en) | Mountain crack detection method based on image local reinforcement | |
CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
CN104778684A (en) | Method and system thereof for automatically measuring, representing and classifying heterogeneous defects on surface of steel | |
CN106914428A (en) | A kind of New Algorithm of the steel ball surface defect Differential Detection based on machine vision | |
CN115482195A (en) | Train part deformation detection method based on three-dimensional point cloud | |
CN110096980A (en) | Character machining identifying system | |
CN112991271A (en) | Aluminum profile surface defect visual detection method based on improved yolov3 | |
Fu et al. | Research on image-based detection and recognition technologies for cracks on rail surface | |
CN115601359A (en) | Welding seam detection method and device | |
WO2021109011A1 (en) | Intelligent capacitor internal defect detection method based on ultrasound image | |
CN108492306A (en) | A kind of X-type Angular Point Extracting Method based on image outline | |
CN104598906B (en) | Vehicle outline detection method and its device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20170920 Address after: 213102, No. 333 East Changhong Road, Changzhou Town, Wujin District, Jiangsu, China Patentee after: LINGTONG EXHIBITION SYSTEM CO., LTD. Address before: 213022 Wushan Road, Xinbei District, Jiangsu, China, No. 1, No. Patentee before: Changzhou Polytechnic College |
|
TR01 | Transfer of patent right |