CN110426395A - A kind of solar energy EL cell silicon chip surface inspecting method and device - Google Patents
A kind of solar energy EL cell silicon chip surface inspecting method and device Download PDFInfo
- Publication number
- CN110426395A CN110426395A CN201910597030.8A CN201910597030A CN110426395A CN 110426395 A CN110426395 A CN 110426395A CN 201910597030 A CN201910597030 A CN 201910597030A CN 110426395 A CN110426395 A CN 110426395A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- silicon chip
- diagram picture
- region
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Abstract
The invention discloses a kind of solar energy EL cell silicon chip surface inspecting methods, it include: that the pyramidal number of plies is set and according to the number of plies, the first pyramid diagram picture of the corresponding source images got of creation and the second pyramid diagram picture of corresponding preset template image;The first pyramid diagram picture is successively traversed, while corresponding each layer of the first pyramid diagram picture generates region of interest area image;The region of interest area image is matched with each tomographic image of the second pyramid diagram picture and exports matching result;Image to be detected is generated according to the matching result;Detect described image to be detected and output test result.The present invention can be improved the matching efficiency of source images and template image, to improve image processing efficiency, and then enhance the quality testing ability of cell silicon chip.
Description
Technical field
The present invention relates to technical field of machine vision, more particularly, to a kind of solar energy EL cell silicon chip surface inspecting method
And device.
Background technique
TheCourse of PV Industry is swift and violent, and the market demand is very big, and competition among enterprises are fierce, and the quality of solar battery sheet is directly determined
The efficiency and service life of photovoltaic generating system are determined.Wherein, the luminous point transformation efficiency and service life of cell silicon chip are limited
Quality problems include the dirty defect in cell silicon chip surface.
It is continuous excellent with the continuous development of machine vision technique, the continuous improvement of image processing techniques and related algorithm
Change, Machine Vision Detection has become one of the important means of detection cell silicon chip surface.But the prior art cannot be with
The paces of upper photovoltaic industry fast development, in the detection process of conventional method, machine needs to handle a large amount of graphics calculations, figure
The efficiency of picture processing is still very low, leads to the quality testing inferior capabilities of cell silicon chip.
Summary of the invention
In view of the above technical problems, the present invention provides a kind of solar energy EL cell silicon chip surface inspecting method and device,
It can be improved the matching efficiency of source images and template image, to accelerate image processing speed, and then enhance the matter of cell silicon chip
Measure detectability.The technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of solar energy EL cell silicon chip surface inspecting methods, comprising:
The pyramidal number of plies is set and according to the number of plies, the first pyramid diagram of the corresponding source images got of creation
Second pyramid diagram picture of picture and corresponding preset template image;
The first pyramid diagram picture is successively traversed, while corresponding each layer of the first pyramid diagram picture generates region of interest
Area image;
The region of interest area image is matched with each tomographic image of the second pyramid diagram picture and is exported
With result;
Image to be detected is generated according to the matching result;
Detect described image to be detected and output test result.
In a first possible implementation of the first aspect of the invention, described to the region of interest area image and institute
The each tomographic image for stating the second pyramid diagram picture is matched and exports matching result, comprising:
Calculate the similarity of the region of interest area image Yu the second pyramid diagram picture.
In a second possible implementation of the first aspect of the invention, described to be checked according to matching result generation
Altimetric image, comprising:
Interference region image is divided and excluded from described image to be detected.
In the third possible implementation of first aspect present invention, it is described by interference region image from described to be checked
Divide in altimetric image and exclude, comprising:
Feature rejects background area image from described image to be detected according to area.
In the 4th kind of possible implementation of first aspect present invention, it is described by interference region image from described to be checked
Divide in altimetric image and exclude, comprising:
Black surround feature is extracted from described image to be detected;
Region merging technique operation and region difference operation are carried out according to the black surround feature to exclude black surround area image.
It is described to detect described image to be detected and export in the 5th kind of possible implementation of first aspect present invention
Testing result, specifically:
According to the round degree of characteristics, dirty region is filtered out from described image to be detected and calculates dirty area and dirty region
Quantity.
In the 6th kind of possible implementation of first aspect present invention, the solar energy EL cell silicon chip surface inspection
Survey method, further includes:
The level of processing on cell silicon chip surface is judged according to testing result.
Second aspect, the embodiment of the invention provides a kind of solar energy EL cell silicon chip surface detection apparatus, feature exists
In, comprising:
Figure layer creation module, for the pyramidal number of plies to be arranged and according to the number of plies, the corresponding source got of creation
Second pyramid diagram picture of the first pyramid diagram picture of image and corresponding preset template image;
Figure layer access modules, for successively traversing the first pyramid diagram picture, while corresponding each layer of the first gold medal word
Tower image generates region of interest area image;
Images match module, for each tomographic image to the region of interest area image and the second pyramid diagram picture
It is matched and exports matching result;
Framing module, for generating image to be detected according to the matching result;
Image detection module, for detecting described image to be detected and output test result.
In a first possible implementation of the second aspect of the invention, described image matching module, comprising:
Similarity computing module, for calculating the similitude of the region of interest area image Yu the second pyramid diagram picture
Value.
In second of possible implementation of second aspect of the present invention, described image locating module, comprising:
Optical sieving module, for dividing and excluding interference region image from described image to be detected.
Compared with the prior art, the embodiment of the present invention has the following beneficial effects:
A kind of solar energy EL cell silicon chip surface inspecting method provided by the invention, by pyramid form by image data
It is layered, the huge source images of data volume is divided into multiple figure layers that are orderly, being easily processed, this is conducive to carry out the same time-division
Layer access images, to improve the speed of traversal image;Meanwhile the layering of pyramid form is conducive to the lesser rate of data volume
The figure layer first accessed carries out images match, achievees the effect that image traversal is synchronous with images match and carries out, to improve source figure
As the matching efficiency with template image, and then accelerate the speed of image procossing, and then enhances the quality testing ability of cell silicon chip.
Detailed description of the invention
Fig. 1 is the flow chart of one of embodiment of the present invention solar energy EL cell silicon chip surface inspecting method;
Fig. 2 is the structure chart of one of embodiment of the present invention solar energy EL cell silicon chip surface detection apparatus.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Figure 1, it illustrates a kind of solar energy EL cell silicon chip tables that an illustrative embodiment of the invention provides
Face detection method, comprising:
S101, the pyramidal number of plies is set and according to the number of plies, the first pyramid diagram picture of the corresponding source images of creation
And the second pyramid diagram picture of corresponding preset template image;Wherein, the template image is that X-ray is shot from dark room conditions
Resulting no surface is dirty, the preferable standard solar cells silicon chip image of quality.
S102, the first pyramid diagram picture is successively traversed, while corresponding each layer of the first pyramid diagram picture generates sense
Interest area image;
S103, the region of interest area image is matched with each tomographic image of the second pyramid diagram picture and defeated
Matching result out;Wherein, the matching result includes the row, column coordinate and the information such as angle and matching score of matching position.
It is understood that the number of plies is bigger, the time for matching and using is found with regard to smaller.In addition it must assure that top
Image have enough information (1 points), if the pyramidal number of plies is too big, template is not easy to identify, if
The time that the pyramid number of plies finds template very little will increase.Therefore, computer is carried out according to the data volume size of image to be processed
Rationally layering, the time required to being conducive to shorten recognition template, to improve the efficiency of images match.
It is matched preferably for most of battery pictures setting pyramid number of plies for 2.
S104, image to be detected is generated according to the matching result;
It is preferably, described that image to be detected is generated according to the matching result, comprising:
By translating, rotating the image processing methods such as affine transformation, image to be detected is obtained.
S105, the described image to be detected of detection and output test result.
A kind of solar energy EL cell silicon chip surface inspecting method provided in an embodiment of the present invention will be schemed by pyramid form
As data are layered, the huge source images of data volume are divided into multiple figure layers that are orderly, being easily processed, this is conducive to carry out
Hierarchical access image simultaneously, to improve the speed of traversal image;Meanwhile the layering of pyramid form be conducive to data volume compared with
The small figure layer for taking the lead in having accessed carries out images match, achievees the effect that image traversal is synchronous with images match and carries out, to mention
The matching efficiency of high source images and template image, and then accelerate the speed of image procossing, and then enhance the quality inspection of cell silicon chip
Survey ability.
Preferably, the setting number of plies and according to the number of plies, create the first pyramid diagram picture of corresponding source images with
And the second pyramid diagram picture of corresponding preset template image, comprising:
Image procossing is carried out to the first pyramid diagram picture and the second pyramid diagram picture using smoothing filter.
It is understood that creation every layer of pyramid diagram as when, be related to it is down-sampled, it is down-sampled after image will appear saw
Tooth needs to be handled using smoothing filter;Gaussian filter effect is good but time-consuming, it is preferable that using small template
Mean filter carries out image procossing.
Preferably, each tomographic image progress to the region of interest area image and the second pyramid diagram picture
Match and export matching result, comprising:
Calculate the similarity of the region of interest area image Yu the second pyramid diagram picture.
It is understood that needing to select when the similarity of calculation template image and region of interest area image (ROI image)
Select similarity measurement criterion;Similarity measurement criterion has SAD (absolute value summation), SSD (difference of two squares summation) and NCC (normalization
Related coefficient), the calculating of NCC is most time-consuming but effect is best, can well adapt to illumination variation, is preferably chosen NCC (normalization
Related coefficient).
In the present embodiment, during target detection, common method is exactly that a template is arranged, with sliding window
Form traverses whole picture source images;Sliding can all generate the ROI image of the sizes such as one and template every time, be based on certain measurement side
Formula, the similarity measure values of calculation template and current ROI image.It just will form an image after having traversed entire image in this way,
The corresponding position of maximum comparability metric is found out, it is exactly the position of our targets to be found.Utilize similarity measurement amount
Change similitude, for quickly identifying that image and positioning target area image have greater advantage.
It is preferably, described that image to be detected is generated according to the matching result, comprising:
Interference region image is divided and excluded from described image to be detected.
It is understood that the image shape template matching method based on pyramidal configuration, can allow subsequent to be detected
Any amount cell piece when the location information in picture changes, can be carried out translation, rotate to navigate to and template
The same location information of image to guarantee that subsequent segmentation effect is consistent, and then improves the solar energy EL cell silicon chip surface
The versatility of detection method, agility.
It is preferably, described that interference region image is divided and excluded from described image to be detected, comprising:
Binarization of gray value processing is carried out to described image to be detected;
Feature rejects background area image from binarization of gray value treated image to be detected according to area.
In the present embodiment, binarization of gray value is carried out to the picture to be processed after positioning;Gray value phase in picture
Close is linked to be a region, since silicon wafer shape-area features are most obvious, it is preferable that carries out area features screening, setting area
Fixed threshold;Region after Feature Selection is first corroded and carries out expansion process again;The rectangle pair for being 500*500 with long * wide
Region after Feature Selection carries out the operation of morphology opening operation.
It is preferably, described that interference region image is divided and excluded from described image to be detected, further includes:
Black surround feature is extracted from described image to be detected;
Region merging technique operation and region difference operation are carried out according to the black surround feature to exclude black surround area image.
It is understood that four black surrounds meeting Interference Detection on cell silicon chip surface from top to bottom, thus cause to judge by accident,
Cannot correct recognition detection to go out surface impression of the hand class etc. dirty.
In the present embodiment, four black surrounds on EL cell silicon chip are extracted respectively, and then this four black surrounds, four region is one by one
Region merging technique operation is carried out, entire black surround region is obtained;EL cell silicon chip to be processed region and black surround region are subjected to difference set
Operation;Due to having been based on shape template matching, affine transformation positioning, so can be to subsequent any number of electricity to be detected
Pond silicon wafer is correctly partitioned into black surround region.
Preferably, the described image to be detected of the detection and output test result, comprising:
Image enhancement processing is carried out to described image to be detected;
Local threshold binary conversion treatment and connected region operation are carried out to described image to be detected;
According to the round degree of characteristics, dirty region is filtered out from described image to be detected and calculates dirty area and dirty region
Quantity.
It is understood that having one usually relative to stria, crack etc. caused by dirty primary hand or dirty touch
A apparent feature is exactly that general circularity is bigger, and it is dirty that this surface is filtered out based on this.
Preferably, described described image to be detected of detection, further includes:
The level of processing on cell silicon chip surface is judged according to testing result.
Specifically, the battery silicon in source images is judged according to the quantity of the dirty area on cell silicon chip surface and dirty region
Piece surface whether there is dirty defect, will when the dirty area or the discrepancy of quantity in dirty region conjunction preset condition
The cell silicon chip is determined as that there are dirty defects on surface.
In the present embodiment, for dirty aspect, A, B, C three grades type and unqualified type are specifically defined:
The first step judges the quantity in dirty region;
As dirty number≤M, into next step;
As dirty number > M, be determined as D grades it is unqualified;
Second step judges dirty area;
As dirty single area≤SA, it is determined as A grades;
As SA < dirty single area≤SB, it is determined as B grades;
As SB < dirty single area≤SC, it is determined as C grades;
As SC < dirty single area≤SD, be determined as D grades it is unqualified;
Wherein, specific SA, SB, SC, SD, M number of threshold values is counted according to the requirement of EL cell silicon chip manufacturer quality inspection personnel
Value definition.
In the present embodiment, threshold value can be arranged according to demand on the basis of basic test standard with personalization in technical staff
Testing standard adapts to the special producing standard and the variation of industry of enterprise, promotes the flexibility of detection method step, improves enterprise
Benefit.
Preferably, the acquisition methods of source images are specific as follows:
Adjust camera vertical height, be put into experimental bench with ruler, be adjusted to the picture size that can be shot 175~177 this
Until the visual field of the length and width of a range;
Focal length is adjusted, silicon slice under test is placed into experimental bench, camera focus is adjusted, can see four chamfering grid of silicon wafer
Until line;
Lens distortion is eliminated, the square scaling board for the use of side length being 170mm is adjusted to see on scaling board and owns
Dot until;
By extracting the silicon chip of solar cell image to be detected of X-ray shooting, source images are obtained.
Fig. 2 is referred to, it illustrates a kind of solar energy EL cell silicon chip tables that an illustrative embodiment of the invention provides
Face detection device, comprising:
Figure layer creation module 201, for the pyramidal number of plies to be arranged and according to the number of plies, creation correspondence is got
Second pyramid diagram picture of the first pyramid diagram picture of source images and corresponding preset template image;
Figure layer access modules 202, for successively traversing the first pyramid diagram picture, while corresponding each layer of the first gold medal
Word tower image generates region of interest area image;
Images match module 203, for each layer to the region of interest area image and the second pyramid diagram picture
Image is matched and exports matching result;
Framing module 204, for generating image to be detected according to the matching result;
Image detection module 205, for detecting described image to be detected and output test result.
Preferably, described image matching module, comprising:
Similarity computing module, for calculating the similitude of the region of interest area image Yu the second pyramid diagram picture
Value.
Preferably, described image locating module, comprising:
Optical sieving module, for dividing and excluding interference region image from described image to be detected.
Preferably, described image screening module, comprising:
Background area image screening module rejects Background regional image from described image to be detected for feature according to area
Picture.
Preferably, described image screening module, comprising:
Black surround area image screening module, for extracting black surround feature from described image to be detected;According to the black surround
Feature carries out region merging technique operation and region difference operation to exclude black surround area image.
Preferably, described image detection module, comprising:
Roundness measurement module, for filtering out dirty region from described image to be detected and calculating according to the round degree of characteristics
The quantity of dirty area and dirty region.
Preferably, the solar energy EL cell silicon chip surface detection apparatus, further includes:
Judgment module, for judging the level of processing on cell silicon chip surface according to testing result.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Claims (10)
1. a kind of solar energy EL cell silicon chip surface inspecting method characterized by comprising
The pyramidal number of plies is set and according to the number of plies, the first pyramid diagram picture of the corresponding source images got of creation with
And the second pyramid diagram picture of corresponding preset template image;
The first pyramid diagram picture is successively traversed, while corresponding each layer of the first pyramid diagram picture generates area-of-interest figure
Picture;
The region of interest area image is matched with each tomographic image of the second pyramid diagram picture and exports matching knot
Fruit;
Image to be detected is generated according to the matching result;
Detect described image to be detected and output test result.
2. solar energy EL cell silicon chip surface inspecting method as described in claim 1, which is characterized in that described emerging to the sense
Interesting area image is matched with each tomographic image of the second pyramid diagram picture and exports matching result, comprising:
Calculate the similarity of the region of interest area image Yu the second pyramid diagram picture.
3. solar energy EL cell silicon chip surface inspecting method as described in claim 1, which is characterized in that described according to
Image to be detected is generated with result, comprising:
Interference region image is divided and excluded from described image to be detected.
4. solar energy EL cell silicon chip surface inspecting method as claimed in claim 3, which is characterized in that described by interference region
Image is divided and is excluded from described image to be detected, comprising:
Feature rejects background area image from described image to be detected according to area.
5. solar energy EL cell silicon chip surface inspecting method as described in claim 3 or 4, which is characterized in that described to interfere
Area image is divided and is excluded from described image to be detected, comprising:
Black surround feature is extracted from described image to be detected;
Region merging technique operation and region difference operation are carried out according to the black surround feature to exclude black surround area image.
6. solar energy EL cell silicon chip surface inspecting method as described in any one of claims 1 to 3, which is characterized in that described
Described image to be detected and output test result are detected, specifically:
According to the round degree of characteristics, dirty region is filtered out from described image to be detected and calculates the number of dirty area and dirty region
Amount.
7. solar energy EL cell silicon chip surface inspecting method as described in claim 1, which is characterized in that further include:
The level of processing on cell silicon chip surface is judged according to testing result.
8. a kind of solar energy EL cell silicon chip surface detection apparatus characterized by comprising
Figure layer creation module, for the pyramidal number of plies to be arranged and according to the number of plies, the corresponding source images got of creation
The first pyramid diagram picture and corresponding preset template image the second pyramid diagram picture;
Figure layer access modules, for successively traversing the first pyramid diagram picture, while corresponding each layer of the first pyramid diagram
As generating region of interest area image;
Images match module is carried out for each tomographic image to the region of interest area image and the second pyramid diagram picture
It matches and exports matching result;
Framing module, for generating image to be detected according to the matching result;
Image detection module, for detecting described image to be detected and output test result.
9. solar energy EL cell silicon chip surface detection apparatus as claimed in claim 8, which is characterized in that described image matches mould
Block, comprising:
Similarity computing module, for calculating the similarity of the region of interest area image Yu the second pyramid diagram picture.
10. solar energy EL cell silicon chip surface detection apparatus as claimed in claim 8, which is characterized in that described image positioning
Module, comprising:
Optical sieving module, for dividing and excluding interference region image from described image to be detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910597030.8A CN110426395B (en) | 2019-07-02 | 2019-07-02 | Method and device for detecting surface of solar EL battery silicon wafer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910597030.8A CN110426395B (en) | 2019-07-02 | 2019-07-02 | Method and device for detecting surface of solar EL battery silicon wafer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110426395A true CN110426395A (en) | 2019-11-08 |
CN110426395B CN110426395B (en) | 2022-02-11 |
Family
ID=68410250
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910597030.8A Active CN110426395B (en) | 2019-07-02 | 2019-07-02 | Method and device for detecting surface of solar EL battery silicon wafer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110426395B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
CN113359049A (en) * | 2021-04-29 | 2021-09-07 | 张火锐 | Method for detecting loss of solid-state lithium battery |
CN116433672A (en) * | 2023-06-15 | 2023-07-14 | 山东九思新材料科技有限责任公司 | Silicon wafer surface quality detection method based on image processing |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004205218A (en) * | 2002-12-20 | 2004-07-22 | Nec Tohoku Ltd | Device and method of inspecting appearance of inside diameter part |
JP2005188991A (en) * | 2003-12-24 | 2005-07-14 | Nagoya Electric Works Co Ltd | Abnormality detection method for conical or truncated conical bump, and abnormality detector for the conical or truncated conical bump |
WO2011144374A1 (en) * | 2010-05-19 | 2011-11-24 | Robert Bosch Gmbh | Method and device for characterising pyramidal surface structures on a substrate |
JP2016018359A (en) * | 2014-07-08 | 2016-02-01 | キヤノン株式会社 | Image processing method, image processing device, program, and recording medium |
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 |
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 |
CN107768269A (en) * | 2017-10-30 | 2018-03-06 | 河北工业大学 | A kind of method of the dirty defects detection of polysilicon solar battery slice outward appearance |
CN107831173A (en) * | 2017-10-17 | 2018-03-23 | 哈尔滨工业大学(威海) | Photovoltaic component defect detection method and system |
CN109215026A (en) * | 2018-09-29 | 2019-01-15 | 广东工业大学 | A kind of accurate LED defect inspection method of high speed based on machine vision |
CN109711457A (en) * | 2018-12-20 | 2019-05-03 | 江南大学 | It is a kind of based on improve the HU not rapid image matching method of bending moment and its application |
CN109801279A (en) * | 2019-01-21 | 2019-05-24 | 京东方科技集团股份有限公司 | Object detection method and device, electronic equipment, storage medium in image |
-
2019
- 2019-07-02 CN CN201910597030.8A patent/CN110426395B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004205218A (en) * | 2002-12-20 | 2004-07-22 | Nec Tohoku Ltd | Device and method of inspecting appearance of inside diameter part |
JP2005188991A (en) * | 2003-12-24 | 2005-07-14 | Nagoya Electric Works Co Ltd | Abnormality detection method for conical or truncated conical bump, and abnormality detector for the conical or truncated conical bump |
WO2011144374A1 (en) * | 2010-05-19 | 2011-11-24 | Robert Bosch Gmbh | Method and device for characterising pyramidal surface structures on a substrate |
JP2016018359A (en) * | 2014-07-08 | 2016-02-01 | キヤノン株式会社 | Image processing method, image processing device, program, and recording medium |
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 |
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 |
CN107831173A (en) * | 2017-10-17 | 2018-03-23 | 哈尔滨工业大学(威海) | Photovoltaic component defect detection method and system |
CN107768269A (en) * | 2017-10-30 | 2018-03-06 | 河北工业大学 | A kind of method of the dirty defects detection of polysilicon solar battery slice outward appearance |
CN109215026A (en) * | 2018-09-29 | 2019-01-15 | 广东工业大学 | A kind of accurate LED defect inspection method of high speed based on machine vision |
CN109711457A (en) * | 2018-12-20 | 2019-05-03 | 江南大学 | It is a kind of based on improve the HU not rapid image matching method of bending moment and its application |
CN109801279A (en) * | 2019-01-21 | 2019-05-24 | 京东方科技集团股份有限公司 | Object detection method and device, electronic equipment, storage medium in image |
Non-Patent Citations (1)
Title |
---|
SHUTAO ZHAO 等: ""A Correction Testing Method for Mechanical Characteristic Parameter of Circuit Breaker Based on Vision Technology"", 《IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
WO2022170702A1 (en) * | 2021-02-09 | 2022-08-18 | 广东拓斯达科技股份有限公司 | Mold state monitoring method, apparatus and system, and industrial personal computer and storage medium |
CN112837302B (en) * | 2021-02-09 | 2024-02-13 | 广东拓斯达科技股份有限公司 | Method and device for monitoring state of die, industrial personal computer, storage medium and system |
CN113359049A (en) * | 2021-04-29 | 2021-09-07 | 张火锐 | Method for detecting loss of solid-state lithium battery |
CN113359049B (en) * | 2021-04-29 | 2022-07-29 | 张火锐 | Method for detecting loss of solid-state lithium battery |
CN116433672A (en) * | 2023-06-15 | 2023-07-14 | 山东九思新材料科技有限责任公司 | Silicon wafer surface quality detection method based on image processing |
CN116433672B (en) * | 2023-06-15 | 2023-08-25 | 山东九思新材料科技有限责任公司 | Silicon wafer surface quality detection method based on image processing |
Also Published As
Publication number | Publication date |
---|---|
CN110426395B (en) | 2022-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ren et al. | State of the art in defect detection based on machine vision | |
CN102374993B (en) | Unit and method for detecting appearance of three dimensional pin of integrated circuit package chip | |
CN105956582B (en) | A kind of face identification system based on three-dimensional data | |
CN110426395A (en) | A kind of solar energy EL cell silicon chip surface inspecting method and device | |
CN109711474A (en) | A kind of aluminium material surface defects detection algorithm based on deep learning | |
CN113592845A (en) | Defect detection method and device for battery coating and storage medium | |
CN112862760B (en) | Bearing outer ring surface defect area detection method | |
CN109242828A (en) | 3D printing product 3 D defects detection method based on optical grating projection multistep phase shift method | |
CN111223093A (en) | AOI defect detection method | |
CN109191421B (en) | Visual detection method for pits on circumferential surface of cylindrical lithium battery | |
CN107274393B (en) | Monocrystaline silicon solar cell piece detection method of surface flaw based on grid line detection | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN106600600A (en) | Wafer defect detection method based on characteristic matching | |
CN106600593B (en) | A kind of middle aluminium porcelain ball surface defect inspection method | |
CN106934803A (en) | The detection method and device of electronic device surface defect | |
CN106657789A (en) | Thread panoramic image synthesis method | |
CN109632808A (en) | Seamed edge defect inspection method, device, electronic equipment and storage medium | |
CN116433672B (en) | Silicon wafer surface quality detection method based on image processing | |
CN113052797B (en) | BGA solder ball three-dimensional detection method based on depth image processing | |
CN110503638A (en) | Spiral colloid amount online test method | |
CN109241948A (en) | A kind of NC cutting tool visual identity method and device | |
CN110443278A (en) | A kind of detection method, device and the equipment of solar battery sheet grid line thickness exception | |
CN113295698B (en) | Defect detection method, storage medium and detection system | |
CN113436102A (en) | Method for detecting surface defects of machined part | |
CN113705564A (en) | Pointer type instrument identification reading method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |