CN103872983A - Device and method for detecting defects on surface of solar cell - Google Patents
Device and method for detecting defects on surface of solar cell Download PDFInfo
- Publication number
- CN103872983A CN103872983A CN201410135246.XA CN201410135246A CN103872983A CN 103872983 A CN103872983 A CN 103872983A CN 201410135246 A CN201410135246 A CN 201410135246A CN 103872983 A CN103872983 A CN 103872983A
- Authority
- CN
- China
- Prior art keywords
- image
- point
- solar cell
- detection
- binaryzation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a device and method for detecting defects on the surface of a solar cell. The device comprises a structural member and a detection circuit system. The structural member is composed of a display frame, an observation platform and an installation frame. The detection circuit system comprises an illumination unit, an image collection unit, an image processing unit and a display unit. In the detection process, an unfilled corner defect image is obtained by means of a low-angle annular white LED light source and by conducting image segmentation, wavelet transform and two-dimensional 7*7 pixel field median filtering on an image; for a crack, a defect image of the crack is obtained by conducting two-dimensional median filtering, wavelet transform, image binaryzation, edge detection and morphology operator processing on the image, the detection recognition result is obtained, and the image processing unit finally transmits the processing result to an upper computer of the display unit. The method and the device have the advantages that compared with a manual visual detection and infrared scanning detection method, detection efficiency and detection accuracy are greatly improved, the method is easy to operate and practicable, a large amount of labor force is saved, and the labor intensity is lowered.
Description
Technical field
The present invention relates to energy field, a kind of particularly solar cell surface defect detection equipment and method, for the defects detection to solar panel surface.
Background technology
The quality of solar cell surface quality is the principal element that affects solar cell power generation efficiency, and therefore the surface quality of solar cell detects becomes a link indispensable in its production process.Checkout equipment and method mainly contain at present:
(1) artificial visual detects.Artificially detect cell panel surface quality by range estimation.The method is only applicable to comparatively significantly solar cell of blemish, is difficult to detect for the small defect of size.And the method human factor is large, defect index disunity, is difficult to adapt to large-scale industrial production demand.
(2) infrared scan detects.Infrared scan detects the architectural feature of the checkout equipment adopting for comprising display rack, observation platform and infraluminescence body, and the below of described observation platform is provided with display rack, and the below of described display rack is provided with infraluminescence body.Light source type is laser, utilizes this light source to take the mode of point by point scanning to scan solar panel, and corresponding light-sensitive element can complete the detection to defect.But the method is only applicable to detecting the less solar panel of size, be not suitable for for detecting size solar panel large or amorphous silicon type, therefore, as industrial production inspection machine, its limitation is larger.
Due to the strong reflection characteristic on solar battery sheet surface, the impact of light illumination technology effects on surface defects detection is very large, and the light source that checkout equipment adopts is in the past generally incandescent lamp, and its working life is short, and light efficiency is low, and job insecurity has stroboscopic phenomenon;
Solar cell surface has strong, the regular feature of grain, the method of the detection in the past adopting is not all for the processing of classifying of the concrete defect of solar cell surface, can not effectively differentiate and identify for the defect that comprises unfilled corner, crackle and electrode, also affect the correctness of the result of check.
In order to overcome the limitation of checkout equipment and method in the past, need design and development novel solar cell surface defect detection equipment and method.
Summary of the invention
Object of the present invention, exactly for overcoming the deficiencies in the prior art, for the problem of prior art existence, provides a kind of design of novel solar cell surface defect detection equipment, and the method for utilizing this equipment to test.For the strong reflection characteristic on solar battery sheet surface, consider the impact of light illumination technology effects on surface defects detection, adopt low angle annular White LED light source.
Consider that solar cell surface has strong, the regular feature of grain, adopted the method detecting for concrete classification of defects.For unfilled corner, by image is carried out, image is cut apart, wavelet transformation and two dimension 7 × 7 pixel field medium filtering processing obtain unfilled corner defect image; For crackle, by being carried out to two dimension median filter, wavelet transformation, image binaryzation and edge detection process, image obtains the defect image that comprises unfilled corner, crackle and electrode.The impact of differentiating in order to eliminate unfilled corner and electrode pair crackle, carries out the region that communicates with border that removes in morphology processing to testing image, obtains only comprising the image of crack defect.Then carry out the identification of defect by choosing corresponding characteristic parameter.
The present invention realizes by such technical scheme: solar cell surface defect detection equipment, comprise structural member and detection circuitry, it is characterized in that, structural member is made up of display rack, observation platform and installing rack, fixedly mounts light source shelf, camera frame, electronic box on observation platform; Mounting testing circuit system in electronic box; Detection circuitry comprises light illuminating unit, image acquisition units, graphics processing unit, display unit;
The AFT-D12 light source controller that light illuminating unit is produced by Ai Feite photoelectricity and white low angle annular LED cold light source connect and compose;
Image acquisition units comprises CCD camera VS078FC and M0814MP model camera lens;
Graphics processing unit comprises self-control V6000 image processor and MV-E1394Dual image pick-up card, self-control V6000 image processor is made up of computer motherboard, internal memory, CPU, hard disk and cabinet, in the computer motherboard bus slot of self-control V6000 image processor, MV-E1394Dual image pick-up card is installed; Display unit is made up of 19 inches of LCDs; Be placed on display rack as the solar cell of detected object;
The white low angle annular LED cold light source of light illuminating unit is by AFT-D12 light-source controller controls, direct irradiation is in the solar cell surface of detected object, the CCD camera VS078FC of image acquisition units collects solar panel surface image information, then CCD camera VS078FC is by connecting the vision cable of MV-E1394Dual image pick-up card, the V6000 image processor that image information is sent to graphics processing unit is processed, V6000 image processor the most at last result is sent to the host computer of display unit, shows result by display.
The method of utilizing described solar cell surface defect detection equipment to detect, it is characterized in that, adopt low angle annular White LED light source, by image is carried out, image is cut apart, wavelet transformation and two dimension 7 × 7 pixel field medium filtering processing obtain unfilled corner defect image; For crackle, by being carried out to two dimension median filter, wavelet transformation, image binaryzation, rim detection and morphological operator processing, image obtains the defect image of crackle, comprise the steps:
Step 1, utilize checkout equipment to obtain solar panel image, open light source, adopt video camera by solar panel IMAQ to processing unit, solar panel image reads in graphics processing unit, and shows at host computer interface;
A) two dimension 7 × 7 neighborhood of pixels medium filtering processing: (7 × 7 pixels are number of pixels)
Be two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, suppress disturbing pulse and spotted noise, keep level and smooth or round and smooth image border;
B) figure image intensifying, image binaryzation, removes electrode processing: utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, mark image border; Finally utilize morphological operator by the order of corrosion again that first expands, image is processed, remove image border, so that subsequent detection;
C) unfilled corner feature extraction: adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
D) unfilled corner defect recognition: chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out unfilled corner identification;
Step 4, in carrying out with step 3, obtain by image is carried out to two dimension median filter, wavelet transformation, image binaryzation and edge detection process the defect image that comprises unfilled corner, crackle and electrode, comprising:
A) two dimension 3 × 3 neighborhood of pixels medium filterings, wavelet transformation: that is two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, suppress disturbing pulse and spotted noise, keep level and smooth or round and smooth image border; (3 × 3 is number of pixels)
B) figure image intensifying, binaryzation, morphology processing, removes the region communicating with border;
Identical with unfilled corner, utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, marking image edge; Finally utilize morphological operator (first expand and corrode again) to process image, remove image border, so that subsequent detection;
C) crack extracts: adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
Step 5, obtain defect recognition result, graphics processing unit the most at last result is sent to the host computer of display unit, shows result by display.
Beneficial effect is: the present invention detects and compares with infrared scan detection method with artificial visual, and detection efficiency and accuracy rate significantly improve.Operation is simple for the method, saves a large amount of labours, alleviated labour intensity.
Accompanying drawing explanation
Fig. 1, solar cell surface defect detection equipment circuit block diagram;
Fig. 2, solar cell surface defects detection flow chart;
Fig. 3, structural member schematic diagram;
In: 1. display rack, 2. light source shelf, 3. camera frame.
Embodiment
For a more clear understanding of the present invention, describe in conjunction with the accompanying drawings and embodiments the present invention in detail:
Solar cell surface defect detection equipment, circuit comprises light illuminating unit, image acquisition units, graphics processing unit, display unit, and light illuminating unit is made up of AFT-D12 type light source controller (direct current 12V power supply adaptor) and white low angle annular LED cold light source.(light source controller is 12V DC power supply)
Image acquisition units is by MV-VS078FC model C CD camera (highest resolution 1024X768, 8 bit data outputs, frame per second 30fps, the colored CCD of lining by line scan), M0814MP model camera lens (image planes size 2/3 ", minimum object distance 0.1m, focal length 8mm), MV-E1394Dual model image pick-up card (adopts the two control chips of professional TSB43AB22A, high speed serialization real time data flow transmission, the every passage of data transmission rate reaches 400Mb/s, 6 core interfaces provide 12V power supply) and IEEE1394A model camera output interface formation, graphics processing unit is by the CPU of Intel (R) Core (TM) I3-2120CPU@3.30GHz, 3.29GHz, 1.98GB internal memory, 500GB hard disk forms, display unit comprises DELL19 inch LCDs.
Be image acquisition units under the effect of light illuminating unit, the solar panel information collecting is sent to graphics processing unit and processes, result is presented at display unit the most at last.
Light illuminating unit: white low angle annular LED cold light source;
Collecting unit: MV-VS078FC model C CD camera, M0814MP model camera lens, MV-E1394Dual model image pick-up card, IEEE1394A model camera output interface;
Processing unit: CPU:Intel (R) Core (TM) I3-2120CPU@3.30GHz;
Internal memory: 3.29GHz, 1.98GB hard disk: 500GB
Display unit: DELL19 inch LCDs;
Utilize described solar cell surface defect detection equipment to carry out detection method, adopt low angle annular White LED light source, by image is carried out, image is cut apart, wavelet transformation and two dimension 7 × 7 pixel field medium filtering processing obtain unfilled corner defect image; For crackle, by being carried out to two dimension median filter, wavelet transformation, image binaryzation, rim detection and morphological operator processing, image obtains the defect image of crackle, comprise the steps:
Step 1, utilize checkout equipment to obtain solar panel image, open light source, adopt video camera by solar panel IMAQ to processing unit, solar panel image reads in graphics processing unit and shows at host computer interface.
A) two dimension 7 × 7 neighborhood of pixels medium filterings:
Be two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, suppress disturbing pulse and spotted noise, keep level and smooth or round and smooth image border.
Two dimensional image
f(
x,
y) principle of two dimension median filter is:
In formula,
f(
x,
y) be two-dimensional data matrix set,
g(
x,
y) be the gray value of window center point after medium filtering.
B) figure image intensifying, image binaryzation, remove electrode:
Utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, marking image edge; Finally utilize morphological operator (first expand and corrode again) to process image, remove image border, so that subsequent detection.
Order
f(
i,
j) be original image,
g(
i,
j) be the later image of binaryzation, threshold value is
t, its span is 0～255, the expression formula of binaryzation conversion
.
First Canny algorithm is chosen two-dimensional Gaussian function and is carried out smoothing processing:
Adopt the finite difference of 2 × 2 neighborhood single order local derviations in Canny algorithm to assign to calculate:
In formula,
be respectively the filtered device of original image
in the result of row, column effect.
Conventional Mathematical Morphology operator have expansion (dilation), corrosion (erosion), and on this basis development open (opening) and close (closing) computing.Utilize these operators and their combination shape and the structure to image to analyze and process, solve the problem that suppresses noise, rim detection, feature extraction field.Introduce the concept of several operators below.
Making Ω is two-dimentional Euclidean space, and A is image, and B is structural element, and A, B are all subsets of Ω, and Φ is empty set.
Expand:
In formula,
the mapping of structural element B about initial point.The meaning of above-mentioned expression formula is owned after image A is expanded by B
xafter translation
at least there is the common element of a non-zero with A.Expansion is used for filling hole.
Corrosion:
The result of the implication B corrosion A of above formula is all B translations
xafterwards all by the point of A
xset-inclusion.Corrosion is the dual operations of expanding, and its effect is acnode and the spike of removing image.
The definition of opening operation is:
To be A expanded by B the implication of above formula after B corrosion again, and opening operation is used for filtering and is less than the bur of structural element, for suppressing positive pulse noise, and the isolated spot of removal of images and burr;
The definition of closed operation is:
The implication of above formula is that A is corroded by B after B expands again, and closed operation can be filled the breach or the hole that are less than structural element, is usually used in suppressing negative pulse noise, fills up image crack and leak.
C) unfilled corner feature extraction
Adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
Labeling process is as follows:
1) if four adjoint point values considering are 0, give so
pthe mark value that point is new.
2), if only having the value of a point in these four adjoint points is 1, will
pthe sign flag Cheng Yuqi of point is identical.
3) if having the value of two or more adjoint points is 1, mark
pthe symbol of point, with one of them is identical during these are put, is recorded the equivalence of this adjoint point symbol simultaneously.
D) unfilled corner defect recognition
Chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out unfilled corner identification.
Unfilled corner defect characteristic parameter area table
| Defect type | Area A(pixel) | Rectangular degree R | Elongation L | Decentralization K |
| Unfilled corner | A＞30 | R＞0.48 | L＞1.0 | K＞13.2 |
For crackle, by being carried out to two dimension median filter, wavelet transformation, image binaryzation, rim detection and morphological operator processing, image obtains the defect image of crackle simultaneously, comprising:
A) 3 × 3 neighborhood of pixels medium filterings, wavelet transformation:
That is two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, be used for suppressing disturbing pulse and spotted noise, keep level and smooth or round and smooth image border;
Two dimensional image
f(
x,
y) principle of two dimension median filter is:
In formula,
f(
x,
y) be two-dimensional data matrix set,
g(
x,
y) be the gray value of window center point after medium filtering.
B) figure image intensifying, binaryzation, morphology processing, removes the region communicating with border;
Identical with unfilled corner, utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, mark image border; Finally utilize morphological operator (first expand and corrode again) to process image, remove image border, so that subsequent detection.
Order
f(
i,
j) be original image,
g(
i,
j) be the later image of binaryzation, threshold value is
t, its span is 0～255, the expression formula of binaryzation conversion
.
First Canny algorithm is chosen two-dimensional Gaussian function and is carried out smoothing processing:
Adopt the finite difference of 2 × 2 neighborhood single order local derviations in Canny algorithm to assign to calculate:
In formula,
be respectively the filtered device of original image
in the result of row, column effect.
Conventional Mathematical Morphology operator have expansion (dilation), corrosion (erosion), and on this basis development open (opening) and close (closing) computing.Utilize these operators and their combination shape and the structure to image to analyze and process, to solve the problem that suppresses noise, rim detection, feature extraction field.Introduce the concept of several operators below.
Making Ω is two-dimentional Euclidean space, and A is image, and B is structural element, and A, B are all subsets of Ω, and Φ is empty set.
Expand:
In formula,
the mapping of structural element B about initial point.The meaning of above-mentioned expression formula is owned after image A is expanded by B
xafter translation
at least there is the common element of a non-zero with A.Expansion is used for filling hole.
Corrosion:
The result of the implication B corrosion A of above formula is all B translations
xafterwards all by the point of A
xset-inclusion.Corrosion is the dual operations of expanding, and its effect is acnode and the spike of removing image.
The definition of opening operation is:
The implication of above formula is that A is expanded by B after B corrosion again.Opening operation is used for filtering and is less than the bur of structural element, is used for suppressing positive pulse noise, the isolated spot of removal of images and burr.
The definition of closed operation is:
The implication of above formula is that A is corroded by B after B expands again.Closed operation is used for filling the breach or the hole that are less than structural element, suppresses negative pulse noise, fills up image crack and leak.
C) crack extracts and adopts 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
Labeling process is as follows:
1) if four adjoint point values considering are 0, give so
pthe mark value that point is new.
2), if only having the value of a point in these four adjoint points is 1, will
pthe sign flag Cheng Yuqi of point is identical.
3) if having the value of two or more adjoint points is 1, mark
pthe symbol of point, with one of them is identical during these are put, is recorded the equivalence of this adjoint point symbol simultaneously.
D) crack defect identification
Chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out Identification of Cracks.
Crack defect characteristic parameter scope table
| Defect type | Area A(pixel) | Rectangular degree R | Elongation L | Decentralization K |
| Crackle | R＜0.66 | L＞1.3 | K＞8.5 |
Step 4, acquisition defect recognition result;
Be applied to the system operation interface of researching and developing a man-machine interaction based on VC++6.0.Enter after this system, region, upper left side can show the image of the solar panel of taking in real time, click operation button, system can be carried out defects detection to current cell panel, defect image after detection completes can be presented at respectively the respective regions of below, interface, and the number of the unfilled corner detecting and crack defect can show by pop-up window.
According to the above description, can realize the solution of the present invention in conjunction with art technology.
Claims (9)
1. solar cell surface defect detection equipment, comprises structural member and detection circuitry, it is characterized in that, structural member is made up of display rack, observation platform and installing rack, fixedly mounts light source shelf, camera frame, electronic box on observation platform; Mounting testing circuit system in electronic box; Detection circuitry comprises light illuminating unit, image acquisition units, graphics processing unit, display unit;
The AFT-D12 light source controller that light illuminating unit is produced by Ai Feite photoelectricity and white low angle annular LED cold light source connect and compose;
Image acquisition units comprises CCD camera VS078FC and M0814MP model camera lens;
Graphics processing unit comprises self-control V6000 image processor and MV-E1394Dual, image pick-up card, self-control V6000 image processor is made up of computer motherboard, internal memory, CPU, hard disk and cabinet, in the computer motherboard bus slot of self-control V6000 image processor, MV-E1394Dual image pick-up card is installed; Display unit is made up of 19 inches of LCDs; Be placed on display rack as the solar cell of detected object;
The white low angle annular LED cold light source of light illuminating unit is by AFT-D12 light-source controller controls, direct irradiation is in the solar cell surface of detected object, the CCD camera VS078FC of image acquisition units collects solar panel surface image information, then CCD camera VS078FC is by connecting the vision cable of MV-E1394Dual image pick-up card, the V6000 image processor that image information is sent to graphics processing unit is processed, V6000 image processor the most at last result is sent to the host computer of display unit, shows result by display.
2. utilize the method that solar cell surface defect detection equipment detects described in claim 1, it is characterized in that, adopt low angle annular White LED light source, by image is carried out, image is cut apart, wavelet transformation and two dimension 7 × 7 pixel field medium filtering processing obtain unfilled corner defect image; For crackle, by being carried out to two dimension median filter, wavelet transformation, image binaryzation, rim detection and morphological operator processing, image obtains the defect image of crackle, and described method comprises the steps:
Step 1, utilize checkout equipment to obtain solar panel image, open light source, adopt video camera by solar panel IMAQ to processing unit, solar panel image reads in graphics processing unit, and shows at host computer interface;
Step 2, by graphics processing unit, image is converted into gray level image;
Step 3, by image is carried out, image is cut apart, wavelet transformation and two dimension 7 × 7 pixel field medium filtering processing obtain unfilled corner defect image; Comprising:
A) two dimension 7 × 7 neighborhood of pixels medium filtering processing:
Be two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, suppress disturbing pulse and spotted noise, keep level and smooth or round and smooth image border;
B) figure image intensifying, image binaryzation, removes electrode processing: utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, marking image edge; Finally utilize morphological operator by the order of corrosion again that first expands, image is processed, remove image border, so that subsequent detection;
C), unfilled corner feature extraction: adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
D), unfilled corner defect recognition: chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out unfilled corner identification;
Step 4, by being carried out to two dimension median filter, wavelet transformation, image binaryzation and edge detection process, image obtains the defect image of crackle, comprising:
A) two dimension 3 × 3 neighborhood of pixels medium filterings, wavelet transformation: that is two dimension median filter, be characterized in rejecting abnormalities point in the situation that not reducing contrast, suppress disturbing pulse and spotted noise, keep level and smooth or round and smooth image border;
B) figure image intensifying, binaryzation, morphology processing, removes the region communicating with border;
Identical with unfilled corner, utilize wavelet transformation to strengthen image; Carry out afterwards binary conversion treatment, make to demonstrate two kinds of obvious visual effects of black and white; Carry out rim detection with Canny operator again, mark image border; Finally utilize morphological operator by the order of corrosion again that first expands, image is processed, remove image border, so that subsequent detection;
C) crack extracts: adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
Step 5, acquisition defect recognition result.
3. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
A) two dimension 7 × 7 neighborhood of pixels medium filtering processing procedures in described step 3 are:
Utilize two dimensional image
f(
x,
y) principle of two dimension median filter:
In formula,
f(
x,
y) be two-dimensional data matrix set,
g(
x,
y) be the gray value of window center point after medium filtering.
4. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
B) figure image intensifying in described step 3, image binaryzation, removal electrode processing procedure is:
Order
f(
i,
j) be original image,
g(
i,
j) be the later image of binaryzation, threshold value is
t, its span is 0～255,
i,=1,2,3 ... n,
j=1,2,3 ... n;
:
The expression formula of binaryzation conversion
;
First Canny algorithm is chosen two-dimensional Gaussian function and is carried out smoothing processing:
Adopt the finite difference of 2 × 2 neighborhood single order local derviations in Canny algorithm to assign to calculate:
In formula,
be respectively the filtered device of original image
in the result of row, column effect;
Mathematical Morphology operator has expansion (dilation), corrosion (erosion), and the opening (opening) and close (closing) computing of development on this basis, utilize shape to image of these operators and their combination and structure to analyze and process and solve the problem that suppresses noise, rim detection or extraction field;
Making Ω is two-dimentional Euclidean space, and A is image, and B is structural element, and A, B are all subsets of Ω, and Φ is empty set;
Expand:
In formula,
be the mapping of structural element B about initial point, the meaning of above-mentioned expression formula is owned after image A is expanded by B
xafter translation
at least there is the common element of a non-zero with A, expand and be used for filling hole;
Corrosion:
The result of the implication B corrosion A of above formula is all B translations
xafterwards all by the point of A
xset-inclusion, corrosion is the dual operations of expanding, its effect is to remove acnode and the spike of image;
The definition of opening operation is:
To be A expanded by B the implication of above formula after B corrosion again, and opening operation is used for filtering and is less than the bur of structural element, suppresses positive pulse noise, the isolated spot of removal of images and burr;
The definition of closed operation is:
The implication of above formula is that A is corroded by B after B expands again, and closed operation is used for filling the breach or the hole that are less than structural element, suppresses negative pulse noise, fills up image crack and leak.
5. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
In described step 3 c), unfilled corner characteristic extraction procedure is:
Adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain;
Labeling process is as follows:
1) if four adjoint point values considering are 0, give so
pthe mark value that point is new;
2), if only having the value of a point in these four adjoint points is 1, will
pthe sign flag Cheng Yuqi of point is identical;
3) if having the value of two or more adjoint points is 1, mark
pthe symbol of point, with one of them is identical during these are put, is recorded the equivalence of this adjoint point symbol simultaneously.
6. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
In described step 3 d), unfilled corner defect recognition process is:
Chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out unfilled corner identification:
Unfilled corner defect characteristic parameter area table
The method of utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
A) two dimension 3 × 3 neighborhood of pixels medium filterings in described step 4, wavelet transform process is:
Utilize two dimensional image
f(
x,
y) principle of two dimension median filter:
In formula,
f(
x,
y) be two-dimensional data matrix set,
g(
x,
y) be the gray value of window center point after medium filtering.
7. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
B) figure image intensifying, binaryzation, morphology processing in described step 4, the processing procedure that removes the region communicating with border are:
Order
f(
i,
j) be original image,
g(
i,
j) be the later image of binaryzation, threshold value is
t, its span is 0～255, the expression formula of binaryzation conversion
;
First Canny algorithm is chosen two-dimensional Gaussian function and is carried out smoothing processing:
Adopt the finite difference of 2 × 2 neighborhood single order local derviations in Canny algorithm to assign to calculate:
In formula,
be respectively the filtered device of original image
in the result of row, column effect;
Making Ω is two-dimentional Euclidean space, and A is image, and B is structural element, and A, B are all subsets of Ω, and Φ is empty set;
Expand:
In formula,
the mapping of structural element B about initial point; The meaning of above-mentioned expression formula is owned after image A is expanded by B
xafter translation
at least there is the common element of a non-zero with A; Expansion is used for filling hole;
Corrosion:
The result of the implication B corrosion A of above formula is all B translations
xafterwards all by the point of A
xset-inclusion; Corrosion is the dual operations of expanding, and its effect is acnode and the spike of removing image;
The definition of opening operation is:
The implication of above formula is that A is expanded by B after B corrosion again; Opening operation is used for filtering and is less than the bur of structural element, suppresses positive pulse noise, the isolated spot of removal of images and burr;
The definition of closed operation is:
The implication of above formula is that A is corroded by B after B expands again, and closed operation is used for filling the breach or the hole that are less than structural element, suppresses negative pulse noise, fills up image crack and leak.
8. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
C) crack leaching process in described step 4 is:
Adopt 8 connection labelling methods correctly to separate cutting apart the different defects that obtain; Labeling process is as follows:
1) if four adjoint point values considering are 0, give so
pthe mark value that point is new;
2), if only having the value of a point in these four adjoint points is 1, will
pthe sign flag Cheng Yuqi of point is identical;
3) if having the value of two or more adjoint points is 1, mark
pthe symbol of point, with one of them is identical during these are put, is recorded the equivalence of this adjoint point symbol simultaneously.
9. the method for utilizing solar cell surface defect detection equipment to detect as claimed in claim 2, is characterized in that,
In described step 4 d), crack defect identifying is:
Chosen area area A, rectangular degree R, elongation L, tetra-kinds of characteristic parameters of decentralization K carry out Identification of Cracks;
Crack defect characteristic parameter scope table
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410135246.XA CN103872983B (en) | 2014-04-04 | 2014-04-04 | Solar cell surface defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410135246.XA CN103872983B (en) | 2014-04-04 | 2014-04-04 | Solar cell surface defect inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103872983A true CN103872983A (en) | 2014-06-18 |
| CN103872983B CN103872983B (en) | 2016-05-25 |
Family
ID=50911178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410135246.XA Expired - Fee Related CN103872983B (en) | 2014-04-04 | 2014-04-04 | Solar cell surface defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103872983B (en) |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104701207A (en) * | 2015-03-04 | 2015-06-10 | 通威太阳能（合肥）有限公司 | Snail track predication method for solar cell pack |
| CN104978747A (en) * | 2015-06-26 | 2015-10-14 | 清华大学 | Target extraction method and apparatus for micro-defect detection of spatial light modulator |
| CN105071772A (en) * | 2015-08-17 | 2015-11-18 | 杨高林 | Solar cell classification test control system |
| CN105261019A (en) * | 2015-10-16 | 2016-01-20 | 深圳市浦洛电子科技有限公司 | Method and system for testing glass integrated circuit (IC) |
| CN105281665A (en) * | 2015-09-29 | 2016-01-27 | 中国电子科技集团公司第四十一研究所 | Portable solar cell defect detection device and method |
| CN105678800A (en) * | 2016-03-17 | 2016-06-15 | 清华大学 | Mask extraction method and system in stacked structure spatial light modulator defect detection |
| CN106206357A (en) * | 2016-09-06 | 2016-12-07 | 江苏大学 | A kind of direction, microchip foot position embedded vision automatic checkout system and detection method thereof |
| CN106533361A (en) * | 2016-12-14 | 2017-03-22 | 河海大学常州校区 | Wavelet analysis-based photovoltaic module fault diagnosis method |
| WO2017113422A1 (en) * | 2015-12-31 | 2017-07-06 | 深圳配天智能技术研究院有限公司 | Image speckle processing method |
| CN107014819A (en) * | 2017-06-09 | 2017-08-04 | 杭州电子科技大学 | A kind of solar panel surface defects detection system and method |
| CN107274393A (en) * | 2017-06-12 | 2017-10-20 | 郑州轻工业学院 | The monocrystaline silicon solar cell piece detection method of surface flaw detected based on grid line |
| CN107490582A (en) * | 2017-09-20 | 2017-12-19 | 深圳市晟达机械设计有限公司 | A kind of streamline Work Piece Verification System Based |
| CN107578409A (en) * | 2017-09-16 | 2018-01-12 | 河北工业大学 | A kind of method of the disconnected grid defects detection of solar battery sheet outward appearance |
| CN107622484A (en) * | 2017-07-15 | 2018-01-23 | 河北工业大学 | A kind of photovoltaic cell unfilled corner detection algorithm based on form fit |
| CN107742286A (en) * | 2017-09-28 | 2018-02-27 | 河北工业大学 | A kind of polysilicon solar battery slice EL tests crack defect detection method |
| CN107749057A (en) * | 2017-09-16 | 2018-03-02 | 河北工业大学 | A kind of method of solar battery sheet outward appearance spillage defects detection |
| CN107764829A (en) * | 2016-08-15 | 2018-03-06 | 上海太阳能工程技术研究中心有限公司 | Solar cell open defect recognition methods |
| CN107895376A (en) * | 2017-12-11 | 2018-04-10 | 福州大学 | Based on the solar panel recognition methods for improving Canny operators and contour area threshold value |
| CN107966454A (en) * | 2017-12-25 | 2018-04-27 | 陕西科技大学 | A kind of end plug defect detecting device and detection method based on FPGA |
| CN108445018A (en) * | 2018-03-20 | 2018-08-24 | 苏州巨能图像检测技术有限公司 | Validity feature curve extracting method applied to the detection of cell piece evil mind |
| CN108664980A (en) * | 2018-05-14 | 2018-10-16 | 昆明理工大学 | A kind of sun crown ring structure recognition methods based on guiding filtering and wavelet transformation |
| CN109324060A (en) * | 2018-10-11 | 2019-02-12 | 广东德尔智慧工厂科技有限公司 | A kind of lithium electropaining cloth surface defects detection system |
| CN109668832A (en) * | 2019-01-30 | 2019-04-23 | 江苏理工学院 | Cellular li-ion battery surface bulge detection device and its method based on subregion light source |
| CN109685760A (en) * | 2018-11-05 | 2019-04-26 | 华中科技大学 | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB |
| CN109738454A (en) * | 2019-03-18 | 2019-05-10 | 福建工程学院 | A kind of soft-package battery tab detection device and method |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| 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 |
| CN110487803A (en) * | 2019-08-20 | 2019-11-22 | Oppo（重庆）智能科技有限公司 | The defect inspection method and device of infrared light-emitting component |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN110687121A (en) * | 2019-09-19 | 2020-01-14 | 湖北三江航天万峰科技发展有限公司 | Intelligent online detection and automatic grading method and system for ceramic tiles |
| CN110766672A (en) * | 2019-10-21 | 2020-02-07 | 郑州迈拓信息技术有限公司 | Electrode fouling detection method |
| CN110926359A (en) * | 2019-11-05 | 2020-03-27 | 长安大学 | Three-dimensional crack curved surface contour detection method for optimizing two-phase scanning pavement |
| CN111353992A (en) * | 2020-03-10 | 2020-06-30 | 塔里木大学 | Agricultural product defect detection method and system based on textural features |
| CN112561896A (en) * | 2020-12-22 | 2021-03-26 | 广州大学 | Method, system and device for detecting defects of glass bottle mouth and storage medium |
| CN112881407A (en) * | 2021-01-14 | 2021-06-01 | 广州大学 | Method, system, device and medium for detecting welding quality of LED chip |
| US11080860B2 (en) | 2018-12-28 | 2021-08-03 | Chroma Ate Inc. | Image inspection method |
| CN113517877A (en) * | 2021-04-30 | 2021-10-19 | 华中科技大学 | Steel wire rope online detection signal noise reduction method and system based on generalized morphological filtering |
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114937011A (en) * | 2022-05-12 | 2022-08-23 | 北京航空航天大学 | Photovoltaic cell image anomaly detection method based on empirical Garbor wavelet transform |
| CN115661148A (en) * | 2022-12-26 | 2023-01-31 | 视睿（杭州）信息科技有限公司 | Wafer crystal grain arrangement detection method and system |
| CN116681752A (en) * | 2023-08-03 | 2023-09-01 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563990B (en) * | 2017-07-15 | 2021-05-04 | 河北工业大学 | Detection method for edge breakage, blunt type and V-shaped notches of photovoltaic cell |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202712128U (en) * | 2012-03-02 | 2013-01-30 | 杭州乔戈里科技有限公司 | Surface defect detection equipment of solar cell panel packaging material |
| CN203012590U (en) * | 2012-12-06 | 2013-06-19 | 东莞市盟拓光电科技有限公司 | Machine vision system |
-
2014
- 2014-04-04 CN CN201410135246.XA patent/CN103872983B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202712128U (en) * | 2012-03-02 | 2013-01-30 | 杭州乔戈里科技有限公司 | Surface defect detection equipment of solar cell panel packaging material |
| CN203012590U (en) * | 2012-12-06 | 2013-06-19 | 东莞市盟拓光电科技有限公司 | Machine vision system |
Non-Patent Citations (2)
| Title |
|---|
| 盛小春: "基于图像处理的太阳能单晶硅片表面质量检测", 《中国学位论文全文数据库》 * |
| 赵慧阳: "基于机器视觉的太阳能电池片表面缺陷的研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (58)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104701207A (en) * | 2015-03-04 | 2015-06-10 | 通威太阳能（合肥）有限公司 | Snail track predication method for solar cell pack |
| CN104701207B (en) * | 2015-03-04 | 2017-06-23 | 通威太阳能（合肥）有限公司 | A kind of snail line Forecasting Methodology for solar cell module |
| CN104978747A (en) * | 2015-06-26 | 2015-10-14 | 清华大学 | Target extraction method and apparatus for micro-defect detection of spatial light modulator |
| CN105071772A (en) * | 2015-08-17 | 2015-11-18 | 杨高林 | Solar cell classification test control system |
| CN105281665A (en) * | 2015-09-29 | 2016-01-27 | 中国电子科技集团公司第四十一研究所 | Portable solar cell defect detection device and method |
| CN105261019B (en) * | 2015-10-16 | 2018-07-17 | 深圳市浦洛电子科技有限公司 | A kind of detection method and system of glass IC |
| CN105261019A (en) * | 2015-10-16 | 2016-01-20 | 深圳市浦洛电子科技有限公司 | Method and system for testing glass integrated circuit (IC) |
| WO2017113422A1 (en) * | 2015-12-31 | 2017-07-06 | 深圳配天智能技术研究院有限公司 | Image speckle processing method |
| CN105678800A (en) * | 2016-03-17 | 2016-06-15 | 清华大学 | Mask extraction method and system in stacked structure spatial light modulator defect detection |
| CN107764829A (en) * | 2016-08-15 | 2018-03-06 | 上海太阳能工程技术研究中心有限公司 | Solar cell open defect recognition methods |
| CN106206357B (en) * | 2016-09-06 | 2023-02-17 | 江苏大学 | Micro-chip pin direction embedded visual automatic detection system and detection method thereof |
| CN106206357A (en) * | 2016-09-06 | 2016-12-07 | 江苏大学 | A kind of direction, microchip foot position embedded vision automatic checkout system and detection method thereof |
| CN106533361A (en) * | 2016-12-14 | 2017-03-22 | 河海大学常州校区 | Wavelet analysis-based photovoltaic module fault diagnosis method |
| CN106533361B (en) * | 2016-12-14 | 2018-08-03 | 河海大学常州校区 | A kind of photovoltaic module method for diagnosing faults based on wavelet analysis |
| CN107014819A (en) * | 2017-06-09 | 2017-08-04 | 杭州电子科技大学 | A kind of solar panel surface defects detection system and method |
| CN107274393A (en) * | 2017-06-12 | 2017-10-20 | 郑州轻工业学院 | The monocrystaline silicon solar cell piece detection method of surface flaw detected based on grid line |
| CN107274393B (en) * | 2017-06-12 | 2018-03-23 | 郑州轻工业学院 | Monocrystaline silicon solar cell piece detection method of surface flaw based on grid line detection |
| CN107622484A (en) * | 2017-07-15 | 2018-01-23 | 河北工业大学 | A kind of photovoltaic cell unfilled corner detection algorithm based on form fit |
| CN107749057A (en) * | 2017-09-16 | 2018-03-02 | 河北工业大学 | A kind of method of solar battery sheet outward appearance spillage defects detection |
| CN107578409B (en) * | 2017-09-16 | 2020-10-16 | 河北工业大学 | Method for detecting appearance grid breakage defect of solar cell |
| CN107578409A (en) * | 2017-09-16 | 2018-01-12 | 河北工业大学 | A kind of method of the disconnected grid defects detection of solar battery sheet outward appearance |
| CN107749057B (en) * | 2017-09-16 | 2021-06-18 | 河北工业大学 | Method for detecting appearance slurry leakage defect of solar cell |
| CN107490582A (en) * | 2017-09-20 | 2017-12-19 | 深圳市晟达机械设计有限公司 | A kind of streamline Work Piece Verification System Based |
| CN107742286A (en) * | 2017-09-28 | 2018-02-27 | 河北工业大学 | A kind of polysilicon solar battery slice EL tests crack defect detection method |
| CN107742286B (en) * | 2017-09-28 | 2021-01-29 | 河北工业大学 | Method for detecting EL test crack defects of polycrystalline silicon solar cell |
| CN107895376A (en) * | 2017-12-11 | 2018-04-10 | 福州大学 | Based on the solar panel recognition methods for improving Canny operators and contour area threshold value |
| CN107966454A (en) * | 2017-12-25 | 2018-04-27 | 陕西科技大学 | A kind of end plug defect detecting device and detection method based on FPGA |
| CN108445018A (en) * | 2018-03-20 | 2018-08-24 | 苏州巨能图像检测技术有限公司 | Validity feature curve extracting method applied to the detection of cell piece evil mind |
| CN108664980A (en) * | 2018-05-14 | 2018-10-16 | 昆明理工大学 | A kind of sun crown ring structure recognition methods based on guiding filtering and wavelet transformation |
| CN109324060A (en) * | 2018-10-11 | 2019-02-12 | 广东德尔智慧工厂科技有限公司 | A kind of lithium electropaining cloth surface defects detection system |
| CN109685760B (en) * | 2018-11-05 | 2022-05-20 | 华中科技大学 | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method |
| CN109685760A (en) * | 2018-11-05 | 2019-04-26 | 华中科技大学 | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB |
| US11080860B2 (en) | 2018-12-28 | 2021-08-03 | Chroma Ate Inc. | Image inspection method |
| CN109816652B (en) * | 2019-01-25 | 2022-08-12 | 湖州云通科技有限公司 | Complex casting defect identification method based on gray level significance |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| CN109668832A (en) * | 2019-01-30 | 2019-04-23 | 江苏理工学院 | Cellular li-ion battery surface bulge detection device and its method based on subregion light source |
| 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 |
| CN109738454A (en) * | 2019-03-18 | 2019-05-10 | 福建工程学院 | A kind of soft-package battery tab detection device and method |
| CN110487803A (en) * | 2019-08-20 | 2019-11-22 | Oppo（重庆）智能科技有限公司 | The defect inspection method and device of infrared light-emitting component |
| CN110687121A (en) * | 2019-09-19 | 2020-01-14 | 湖北三江航天万峰科技发展有限公司 | Intelligent online detection and automatic grading method and system for ceramic tiles |
| CN110766672A (en) * | 2019-10-21 | 2020-02-07 | 郑州迈拓信息技术有限公司 | Electrode fouling detection method |
| CN110926359B (en) * | 2019-11-05 | 2021-10-29 | 长安大学 | Three-dimensional crack curved surface contour detection method for optimizing two-phase scanning pavement |
| CN110926359A (en) * | 2019-11-05 | 2020-03-27 | 长安大学 | Three-dimensional crack curved surface contour detection method for optimizing two-phase scanning pavement |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN111353992B (en) * | 2020-03-10 | 2023-04-07 | 塔里木大学 | Agricultural product defect detection method and system based on textural features |
| CN111353992A (en) * | 2020-03-10 | 2020-06-30 | 塔里木大学 | Agricultural product defect detection method and system based on textural features |
| CN112561896B (en) * | 2020-12-22 | 2023-08-15 | 广州大学 | Method, system and device for detecting defects of glass bottle mouth and storage medium |
| CN112561896A (en) * | 2020-12-22 | 2021-03-26 | 广州大学 | Method, system and device for detecting defects of glass bottle mouth and storage medium |
| CN112881407A (en) * | 2021-01-14 | 2021-06-01 | 广州大学 | Method, system, device and medium for detecting welding quality of LED chip |
| CN113517877A (en) * | 2021-04-30 | 2021-10-19 | 华中科技大学 | Steel wire rope online detection signal noise reduction method and system based on generalized morphological filtering |
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114719749B (en) * | 2022-04-06 | 2023-07-14 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114937011A (en) * | 2022-05-12 | 2022-08-23 | 北京航空航天大学 | Photovoltaic cell image anomaly detection method based on empirical Garbor wavelet transform |
| CN114937011B (en) * | 2022-05-12 | 2024-05-28 | 北京航空航天大学 | Photovoltaic cell image anomaly detection method based on empirical Garbor wavelet transformation |
| CN115661148A (en) * | 2022-12-26 | 2023-01-31 | 视睿（杭州）信息科技有限公司 | Wafer crystal grain arrangement detection method and system |
| CN115661148B (en) * | 2022-12-26 | 2023-04-11 | 视睿（杭州）信息科技有限公司 | Wafer grain arrangement detection method and system |
| CN116681752A (en) * | 2023-08-03 | 2023-09-01 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
| CN116681752B (en) * | 2023-08-03 | 2023-10-27 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103872983B (en) | 2016-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103872983B (en) | Solar cell surface defect inspection method | |
| CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
| CN105894036A (en) | Image feature template matching method being applied to detection of mobile phone screen defects | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN105405142A (en) | Edge defect detection method and system for glass panel | |
| CN109190623B (en) | Method for identifying brand and model of projector | |
| CN104655641A (en) | High-precision full-automatic FPC (Flexible Printed Circuit) defect detecting device and detecting process | |
| CN114119462A (en) | Deep learning-based blue film appearance detection algorithm for lithium battery cell aluminum shell | |
| CN110751619A (en) | Insulator defect detection method | |
| CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
| KR101779040B1 (en) | Method and apparatus for extracting panel area from thermal infrared images of photovoltaic array | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN103177426B (en) | Morphology-based strong-interference laser edge image restoration method | |
| CN109271882B (en) | Method for extracting color-distinguished handwritten Chinese characters | |
| CN110766675B (en) | Solar cell panel defect detection method | |
| CN111598851B (en) | Solar cell broken piece detection method based on morphological image processing | |
| CN102313740A (en) | Solar panel crack detection method | |
| CN117036825A (en) | Solar cell panel detection method, medium and system | |
| CN115082504B (en) | Light spot identification method for solar photovoltaic panel | |
| CN110610474A (en) | Solar panel defect real-time detection method based on infrared image | |
| Huang et al. | Mango surface defect detection based on HALCON | |
| CN113820322B (en) | Detection device and method for appearance quality of seeds | |
| CN116818763A (en) | Rapid detection method for surface defects of wind power blade | |
| CN112116579B (en) | Defect detection method and device for transparent medicine bottle |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160525 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |