Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells

This study provides an automatic method for detecting finger interruptions in electroluminescence (EL) images of multicrystalline solar cells. The proposed method is a supervised classification method. We obtain regions of interest (ROI) by separating the EL image to several regions. The fingers wit...

Full description

Bibliographic Details
Main Authors: Din-Chang Tseng, Yu-Shuo Liu, Chang-Min Chou
Format: Article
Language:English
Published: Hindawi Limited 2015-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2015/879675
id doaj-8a44eb5277fa4f9c88200c1ce4eec66d
record_format Article
spelling doaj-8a44eb5277fa4f9c88200c1ce4eec66d2020-11-24T22:12:32ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472015-01-01201510.1155/2015/879675879675Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar CellsDin-Chang Tseng0Yu-Shuo Liu1Chang-Min Chou2Department of Computer Science and Information Engineering, National Central University, No. 300, Jhongda Road, Jhongli 32001, TaiwanDepartment of Computer Science and Information Engineering, National Central University, No. 300, Jhongda Road, Jhongli 32001, TaiwanDepartment of Electronic Engineering, Chien Hsin University of Science and Technology, No. 229, Jianxing Road, Jhongli 32097, TaiwanThis study provides an automatic method for detecting finger interruptions in electroluminescence (EL) images of multicrystalline solar cells. The proposed method is a supervised classification method. We obtain regions of interest (ROI) by separating the EL image to several regions. The fingers within each ROI are candidates for defect detection. We horizontally scan each ROI region and extract features from each finger pixel. In the training stage, we record a set of features which are extracted from interrupted fingers and noninterrupted fingers. These features are represented as points in a spectral embedding space produced by spectral clustering method. These points will be classified into two clusters: interrupted fingers and noninterrupted fingers. In the classification stage, we firstly detect the position of fingers in an EL image and obtain features from each finger. The set of features in each finger combined with known features in the training stage will be represented as points in the spectral embedding space and then will be classified to the cluster with nearer cluster centroid of known features. Experimental results show that the proposed method can effectively detect finger interruptions on a set of EL images of various solar cells.http://dx.doi.org/10.1155/2015/879675
collection DOAJ
language English
format Article
sources DOAJ
author Din-Chang Tseng
Yu-Shuo Liu
Chang-Min Chou
spellingShingle Din-Chang Tseng
Yu-Shuo Liu
Chang-Min Chou
Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
Mathematical Problems in Engineering
author_facet Din-Chang Tseng
Yu-Shuo Liu
Chang-Min Chou
author_sort Din-Chang Tseng
title Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
title_short Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
title_full Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
title_fullStr Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
title_full_unstemmed Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
title_sort automatic finger interruption detection in electroluminescence images of multicrystalline solar cells
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2015-01-01
description This study provides an automatic method for detecting finger interruptions in electroluminescence (EL) images of multicrystalline solar cells. The proposed method is a supervised classification method. We obtain regions of interest (ROI) by separating the EL image to several regions. The fingers within each ROI are candidates for defect detection. We horizontally scan each ROI region and extract features from each finger pixel. In the training stage, we record a set of features which are extracted from interrupted fingers and noninterrupted fingers. These features are represented as points in a spectral embedding space produced by spectral clustering method. These points will be classified into two clusters: interrupted fingers and noninterrupted fingers. In the classification stage, we firstly detect the position of fingers in an EL image and obtain features from each finger. The set of features in each finger combined with known features in the training stage will be represented as points in the spectral embedding space and then will be classified to the cluster with nearer cluster centroid of known features. Experimental results show that the proposed method can effectively detect finger interruptions on a set of EL images of various solar cells.
url http://dx.doi.org/10.1155/2015/879675
work_keys_str_mv AT dinchangtseng automaticfingerinterruptiondetectioninelectroluminescenceimagesofmulticrystallinesolarcells
AT yushuoliu automaticfingerinterruptiondetectioninelectroluminescenceimagesofmulticrystallinesolarcells
AT changminchou automaticfingerinterruptiondetectioninelectroluminescenceimagesofmulticrystallinesolarcells
_version_ 1725803330108653568