CN106814088A - Based on machine vision to the detection means and method of cell piece colour sorting - Google Patents
Based on machine vision to the detection means and method of cell piece colour sorting Download PDFInfo
- Publication number
- CN106814088A CN106814088A CN201611269689.3A CN201611269689A CN106814088A CN 106814088 A CN106814088 A CN 106814088A CN 201611269689 A CN201611269689 A CN 201611269689A CN 106814088 A CN106814088 A CN 106814088A
- Authority
- CN
- China
- Prior art keywords
- cell piece
- module
- sorting
- machine vision
- colour
- 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.)
- Pending
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The present invention provide it is a kind of based on machine vision to the detection means and method of cell piece colour sorting, wherein, platform includes:Image capture module, coordinate transform and segmentation module, plane information acquisition module, processing module, judge module and sorting module;Image capture module is used to receive signal and obtains the view data of cell piece;Coordinate transform is used to carry out coordinate transform and image segmentation to the view data for obtaining with segmentation module;Plane information acquisition module is used to obtain each plane information of rgb space of cell piece picture;Processing module is used to carry out plane binaryzation and filtering process;Judge module is used to judge whether detected cell piece surface occurs breakage;Sorting module is used to sort the cell piece being detected.The present invention can carry out unified and accurate detection for solar battery sheet, be conducive to the sorting of solar battery sheet, it is ensured that the qualification rate of solar battery sheet, reduce the outflow of waste product solar battery sheet.
Description
Technical field
The present invention relates to solar battery sheet detection technique field, more particularly to one kind is for being based on machine vision to battery
The detection means and method of piece colour sorting.
Background technology
Solar battery sheet is the important component of solar cell, its in process of production different phase have lack
Sunken species is also different, influences also different.By taking the cell piece after plated film as an example, the quality of its coating quality directly determines follow-up work
The quality of cell piece printing in sequence, so as to influence the performance of solar cell, it is therefore necessary to which cell piece after plated film is sorted,
The unqualified cell piece that there will be defect is rejected.
But the influence of the factors such as the different, external environment of temperature due to graphite boat each groove, cell piece can go out after plated film
Existing shades of colour defect.The diversity and complexity of above-mentioned cell piece kind result in the uncertainty to its detection method, enter
And have impact on the detection and sorting of solar battery sheet.
Therefore, regarding to the issue above, further solution is proposed.
The content of the invention
It is an object of the invention to provide it is a kind of based on machine vision to the detection means of cell piece colour sorting, to overcome
The deficiencies in the prior art.
For achieving the above object, the present invention provides a kind of detection based on machine vision to cell piece colour sorting and fills
Put, it includes:Image capture module, coordinate transform with segmentation module, plane information acquisition module, processing module, judge module,
And sorting module;
Described image acquisition module is used to receive signal and obtains the view data of cell piece;
The coordinate transform is used to carry out coordinate transform and image segmentation to the view data for obtaining with segmentation module;
The plane information acquisition module is used to obtain each plane information of rgb space of cell piece picture;
The processing module is used to carry out plane binaryzation and filtering process;
The colour deficient that the judge module is used for the cell piece surface to being detected judges;
The sorting module is used for the judged result according to the judge module, and the cell piece to being detected is sorted.
As the improvement of the detection means based on machine vision to cell piece colour sorting of the invention, the judge module
By fuzzy self-adaption method and neural net method, the colour deficient on detected cell piece surface is judged.
It is described fuzzy adaptive as the improvement of the detection means based on machine vision to cell piece colour sorting of the invention
The formula of induction method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcTo get over a little
Locate corresponding degree of membership, PijIt is the degree of membership of pixel (i, j).
As the improvement of the detection means based on machine vision to cell piece colour sorting of the invention, the neutral net
The formula of method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f
It is excitation function, θ is threshold value.
As the improvement of the detection means based on machine vision to cell piece colour sorting of the invention, the sorting module
Including mechanical arm and sorting box, the sorting box is arranged on sorting position, is entered between the mechanical arm self-inspection location and sorting position
Row is moved back and forth.
For achieving the above object, the present invention provides one kind with machine vision to cell piece surface defects detection side
Method, it comprises the following steps:
S1, receive signal and obtain the view data of cell piece;
S2, the view data to obtaining carry out coordinate transform and image segmentation;
S3, each plane information of rgb space for obtaining cell piece picture;
S4, carry out plane binaryzation and filtering process;
S5, the colour deficient to detected cell piece surface judge;
S6, according to judged result, the cell piece to being detected is sorted.
As the improvement of the detection method based on machine vision to cell piece colour sorting of the invention, the step S5
In, by fuzzy self-adaption method and neural net method, judge the colour deficient on detected cell piece surface.
It is described fuzzy adaptive as the improvement of the detection method based on machine vision to cell piece colour sorting of the invention
The formula of induction method is:
The formula of the fuzzy self-adaption method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcTo get over a little
Locate corresponding degree of membership, PijIt is the degree of membership of pixel (i, j).
As the improvement of the detection method based on machine vision to cell piece colour sorting of the invention, the neutral net
The formula of method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f
It is excitation function, θ is threshold value.
Compared with prior art, the beneficial effects of the invention are as follows:It is of the invention cell piece color is divided based on machine vision
The colour deficient that the detection means of choosing can be directed to solar battery sheet carries out unified and accurate detection, is conducive to solar-electricity
The sorting of pond piece, it is ensured that the qualification rate of solar battery sheet, reduces the outflow of waste product solar battery sheet.
Brief description of the drawings
Fig. 1 is a specific embodiment of the detection means based on machine vision to cell piece colour sorting of the invention
Module diagram;
Fig. 2 is side of the utilization machine vision of the invention to a specific embodiment of cell piece detection method of surface flaw
Method schematic flow sheet.
Specific embodiment
The present invention is described in detail for shown each implementation method below in conjunction with the accompanying drawings, but it should explanation, these
Implementation method not limitation of the present invention, those of ordinary skill in the art according to these implementation method institutes works energy, method,
Or equivalent transformation or replacement in structure, belong within protection scope of the present invention.
As shown in figure 1, of the invention included based on machine vision to the detection means of cell piece colour sorting:IMAQ
Module 10, coordinate transform and segmentation module 20, plane information acquisition module 30, processing module 40, judge module 50 and sorting
Module 60.
Wherein, described image acquisition module 10 is used to receive signal and obtains the view data of cell piece, specifically, described
Image collection module 10 can include light source, camera lens and camera.Wherein, the light source is used for as detection light source, the mirror
Head carries out image data acquiring, and be passed to camera under detection light source irradiation.
The coordinate transform is used to carry out coordinate transform and image segmentation to the view data for obtaining with segmentation module 20,
In this way, in order to be prepared for follow-up image real time transfer.The plane information acquisition module 30 is used to obtain cell piece figure
Each plane information of rgb space of piece.The processing module 40 is used to carry out plane binaryzation and filtering process, so with raising
The accuracy of view data.
The judge module 50 is used to judge whether detected cell piece surface occurs breakage.Specifically, the judgement
Module judges the colour deficient on detected cell piece surface by fuzzy self-adaption method and neural net method.Wherein,
The formula of the fuzzy self-adaption method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcTo get over a little
Locate corresponding degree of membership, PijIt is the degree of membership of pixel (i, j).
The formula of the neural net method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f
It is excitation function, θ is threshold value.
The sorting module 60 is used for the judged result according to the judge module 50, and the cell piece to being detected is divided
Choosing.Specifically, the sorting module 60 carries out signal transmission with the judge module 50, so that, it can be according to being received from
Judge module 50 send judge module 50 judged result, and accordingly to be detected cell piece sort.The sorting
Module 60 includes mechanical arm and sorting box, wherein, the sorting box at least includes spec battery piece sorting box and unqualified electricity
Pond piece sorting box, and the sorting box is arranged at corresponding sorting on position.Enter between the mechanical arm self-inspection location and sorting position
Row is moved back and forth.As needed, there can be respective separate machine arm on any sorting position, additionally, also multiple can sort positions being total to
Use same mechanical arm.Cell piece on detecting position is sent to correspondence by the mechanical arm under the control of the sorting module 60
Sorting position on.During the mechanical arm crawl cell piece, cell piece can be drawn by the sucker for setting thereon and be realized
Grasping movement.
As shown in Fig. 2 being based on identical inventive concept, the present invention also provides one kind with machine vision to cell piece surface
Defect inspection method, it comprises the following steps:
S1, receive signal and obtain the view data of cell piece;
S2, the view data to obtaining carry out coordinate transform and image segmentation;
S3, each plane information of rgb space for obtaining cell piece picture;
S4, carry out plane binaryzation and filtering process;
Whether the detected cell piece surface of S5, judgement there is breakage;
S6, according to judged result, the cell piece to being detected is sorted.
Wherein, in the step S5, by fuzzy self-adaption method and neural net method, detected battery is judged
The colour deficient on piece surface.Specifically, the formula of the fuzzy self-adaption method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcTo get over a little
Locate corresponding degree of membership, PijIt is the degree of membership of pixel (i, j).
The formula of the neural net method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f
It is excitation function, θ is threshold value.
In sum, it is of the invention that solar energy can be directed to the detection means of cell piece colour sorting based on machine vision
The colour deficient of cell piece carries out unified and accurate detection, is conducive to the sorting of solar battery sheet, it is ensured that solar-electricity
The qualification rate of pond piece, reduces the outflow of waste product solar battery sheet.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be in other specific forms realized.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires to be limited rather than described above, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as the claim involved by limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each implementation method is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that for clarity, those skilled in the art should
Specification an as entirety, the technical scheme in each embodiment can also be formed into those skilled in the art through appropriately combined
May be appreciated other embodiment.
Claims (9)
1. it is a kind of based on machine vision to the detection means of cell piece colour sorting, it is characterised in that the cell piece surface lacks
The platform for falling into detection includes:Image capture module, coordinate transform and segmentation module, plane information acquisition module, processing module, sentence
Disconnected module and sorting module;
Described image acquisition module is used to receive signal and obtains the view data of cell piece;
The coordinate transform is used to carry out coordinate transform and image segmentation to the view data for obtaining with segmentation module;
The plane information acquisition module is used to obtain each plane information of rgb space of cell piece picture;
The processing module is used to carry out plane binaryzation and filtering process;
The colour deficient that the judge module is used for the cell piece surface to being detected judges;
The sorting module is used for the judged result according to the judge module, and the cell piece to being detected is sorted.
2. it is according to claim 1 based on machine vision to the detection means of cell piece colour sorting, it is characterised in that institute
Judge module is stated by fuzzy self-adaption method and neural net method, judges that the color on detected cell piece surface lacks
Fall into.
3. it is according to claim 2 based on machine vision to the detection means of cell piece colour sorting, it is characterised in that institute
The formula for stating fuzzy self-adaption method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcFor right at getting over
The degree of membership answered, PijIt is the degree of membership of pixel (i, j).
4. it is according to claim 2 based on machine vision to the detection means of cell piece colour sorting, it is characterised in that institute
The formula for stating neural net method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f is sharp
Function is encouraged, θ is threshold value.
5. it is according to claim 1 based on machine vision to the detection means of cell piece colour sorting, it is characterised in that institute
State sorting module include mechanical arm and sorting box, the sorting box be arranged at sorting position on, the mechanical arm self-inspection location and point
Moved back and forth between bit selecting.
6. it is a kind of to use machine vision to cell piece detection method of surface flaw, it is characterised in that the cell piece surface defect
The method of detection comprises the following steps:
S1, receive signal and obtain the view data of cell piece;
S2, the view data to obtaining carry out coordinate transform and image segmentation;
S3, each plane information of rgb space for obtaining cell piece picture;
S4, carry out plane binaryzation and filtering process;
S5, the colour deficient to detected cell piece surface judge;
S6, according to judged result, the cell piece to being detected is sorted.
7. it is according to claim 6 based on machine vision to the detection method of cell piece colour sorting, it is characterised in that institute
State in step S5, by fuzzy self-adaption method and neural net method, judge that the color on detected cell piece surface lacks
Fall into.
8. it is according to claim 6 based on machine vision to the detection method of cell piece colour sorting, it is characterised in that institute
The formula for stating fuzzy self-adaption method is:
μ′ij=Ir(μij)=I1(Ir-1(μij)), r=1,2 ..., wherein,
The μ 'ijRepresent the degree of membership of element in the corresponding fuzzy matrix of the cell piece color, the PcFor right at getting over
The degree of membership answered, PijIt is the degree of membership of pixel (i, j).
9. it is according to claim 6 based on machine vision to the detection method of cell piece colour sorting, it is characterised in that institute
The formula for stating neural net method is:
Wherein, G represents the mapping of element in the corresponding fuzzy matrix of the cell piece color, piIt is input, wiIt is weights, f is sharp
Function is encouraged, θ is threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611269689.3A CN106814088A (en) | 2016-12-30 | 2016-12-30 | Based on machine vision to the detection means and method of cell piece colour sorting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611269689.3A CN106814088A (en) | 2016-12-30 | 2016-12-30 | Based on machine vision to the detection means and method of cell piece colour sorting |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106814088A true CN106814088A (en) | 2017-06-09 |
Family
ID=59109991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611269689.3A Pending CN106814088A (en) | 2016-12-30 | 2016-12-30 | Based on machine vision to the detection means and method of cell piece colour sorting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106814088A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239075A (en) * | 2018-08-27 | 2019-01-18 | 北京百度网讯科技有限公司 | Battery detection method and device |
CN111054658A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Color sorting system and sorting method |
CN111105405A (en) * | 2019-12-24 | 2020-05-05 | 刘甜甜 | New energy lithium battery surface defect detection method based on adaptive deep learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103611690A (en) * | 2013-10-29 | 2014-03-05 | 上海欧普泰科技创业有限公司 | Solar battery slice sorting device |
CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技(杭州)有限公司 | Battery piece chromatism selection control method based on color machine vision |
CN104952754A (en) * | 2015-05-05 | 2015-09-30 | 江苏大学 | Coated silicon chip sorting method based on machine vision |
CN104966101A (en) * | 2015-06-17 | 2015-10-07 | 镇江苏仪德科技有限公司 | Solar cell classification method based on LabVIEW |
-
2016
- 2016-12-30 CN CN201611269689.3A patent/CN106814088A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103611690A (en) * | 2013-10-29 | 2014-03-05 | 上海欧普泰科技创业有限公司 | Solar battery slice sorting device |
CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技(杭州)有限公司 | Battery piece chromatism selection control method based on color machine vision |
CN104952754A (en) * | 2015-05-05 | 2015-09-30 | 江苏大学 | Coated silicon chip sorting method based on machine vision |
CN104966101A (en) * | 2015-06-17 | 2015-10-07 | 镇江苏仪德科技有限公司 | Solar cell classification method based on LabVIEW |
Non-Patent Citations (5)
Title |
---|
姜桃等: "自适应图像模糊增强快速算法", 《计算机工程》 * |
张建同: "《实用多元统计分析》", 30 August 2016, 上海:同济大学出版社 * |
张晓光,高顶: "《射线检测焊接缺陷的提取和自动识别》", 31 October 2004, 北京:国防工业出版社 * |
徐干成等: "《地下工程支护结构与设计》", 31 January 2013, 北京:中国水利水电出版社 * |
李庆辉等: "HIS 空间的火灾图像模糊增强快速算法", 《激光技术》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239075A (en) * | 2018-08-27 | 2019-01-18 | 北京百度网讯科技有限公司 | Battery detection method and device |
US11158044B2 (en) | 2018-08-27 | 2021-10-26 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Battery detection method and device |
CN109239075B (en) * | 2018-08-27 | 2021-11-30 | 北京百度网讯科技有限公司 | Battery detection method and device |
CN111054658A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Color sorting system and sorting method |
CN111105405A (en) * | 2019-12-24 | 2020-05-05 | 刘甜甜 | New energy lithium battery surface defect detection method based on adaptive deep learning |
CN111105405B (en) * | 2019-12-24 | 2020-12-25 | 芜湖楚睿智能科技有限公司 | New energy lithium battery surface defect detection method based on adaptive deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Akram et al. | Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning | |
Akram et al. | CNN based automatic detection of photovoltaic cell defects in electroluminescence images | |
CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
CN109919934B (en) | Liquid crystal panel defect detection method based on multi-source domain deep transfer learning | |
CN101981683B (en) | Method for classifying defects and device for classifying defects | |
CN109584227A (en) | A kind of quality of welding spot detection method and its realization system based on deep learning algorithm of target detection | |
CN111179251A (en) | Defect detection system and method based on twin neural network and by utilizing template comparison | |
CN110135521A (en) | Pole-piece pole-ear defects detection model, detection method and system based on convolutional neural networks | |
CN109142371A (en) | High density flexible exterior substrate defect detecting system and method based on deep learning | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN106204618A (en) | Product surface of package defects detection based on machine vision and sorting technique | |
CN107064170A (en) | One kind detection phone housing profile tolerance defect method | |
WO2023168972A1 (en) | Linear array camera-based copper surface defect detection method and apparatus | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
CN109307675A (en) | A kind of product appearance detection method and system | |
CN106814088A (en) | Based on machine vision to the detection means and method of cell piece colour sorting | |
CN109840900A (en) | A kind of line detection system for failure and detection method applied to intelligence manufacture workshop | |
CN107169491A (en) | A kind of ring gear die number detection method | |
CN106097320B (en) | Underwater sea cucumber image automatic segmentation method and device | |
CN113837994B (en) | Photovoltaic panel defect diagnosis method based on edge detection convolutional neural network | |
CN112258490A (en) | Low-emissivity coating intelligent damage detection method based on optical and infrared image fusion | |
CN110415238A (en) | Diaphragm spots detection method based on reversed bottleneck structure depth convolutional network | |
CN104200215A (en) | Method for identifying dust and pocking marks on surface of big-caliber optical element | |
Wu et al. | An end-to-end learning method for industrial defect detection | |
CN115035082A (en) | YOLOv4 improved algorithm-based aircraft transparency defect detection 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170609 |