Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images

The rapid growth of photovoltaic (PV) systems has highlighted the need for efficient and reliable defect detection to maintain system performance. Electroluminescence (EL) imaging has emerged as a promising technique for identifying defects in PV cells; however, challenges remain in accurately class...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanim Suraya Mohd Mokhtar, Aimi Salihah Abdul Nasir, Mohammad Faridun Naim Tajuddin, Muhammad Hafeez Abdul Nasir, Kumuthawathe Ananda Rao
Format: Article
Language:English
Published: Iran University of Science and Technology 2025-06-01
Series:Iranian Journal of Electrical and Electronic Engineering
Subjects:
Online Access:http://ijeee.iust.ac.ir/article-1-3571-en.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849690290573541376
author Hanim Suraya Mohd Mokhtar
Aimi Salihah Abdul Nasir
Mohammad Faridun Naim Tajuddin
Muhammad Hafeez Abdul Nasir
Kumuthawathe Ananda Rao
author_facet Hanim Suraya Mohd Mokhtar
Aimi Salihah Abdul Nasir
Mohammad Faridun Naim Tajuddin
Muhammad Hafeez Abdul Nasir
Kumuthawathe Ananda Rao
author_sort Hanim Suraya Mohd Mokhtar
collection DOAJ
description The rapid growth of photovoltaic (PV) systems has highlighted the need for efficient and reliable defect detection to maintain system performance. Electroluminescence (EL) imaging has emerged as a promising technique for identifying defects in PV cells; however, challenges remain in accurately classifying defects due to the variability in image quality and the complex nature of the defects. Existing studies often focus on single image enhancement techniques or fail to comprehensively compare the performance of various image enhancement methods across different deep learning (DL) models. This research addresses these gaps by proposing an in-depth analysis of the impact of multiple image enhancement techniques on defect detection performance, using various deep learning models of low, medium, and high complexity. The results demonstrate that mid-complexity models, especially DarkNet-53, achieve the highest performance with an accuracy of 94.55% after MSR2 enhancement. DarkNet-53 consistently outperformed both lower-complexity models and higher-complexity models in terms of accuracy, precision, and F1-score. The findings highlight that medium-depth models, enhanced with MSR2, offer the most reliable results for photovoltaic defect detection, demonstrating a significant improvement over other models in terms of accuracy and efficiency. This research provides valuable insights for optimizing defect detection systems in photovoltaic applications, emphasizing the importance of both model complexity and image enhancement techniques for robust performance.
format Article
id doaj-art-2d12b80cccf741018956e070d982fb55
institution DOAJ
issn 1735-2827
2383-3890
language English
publishDate 2025-06-01
publisher Iran University of Science and Technology
record_format Article
series Iranian Journal of Electrical and Electronic Engineering
spelling doaj-art-2d12b80cccf741018956e070d982fb552025-08-20T03:21:22ZengIran University of Science and TechnologyIranian Journal of Electrical and Electronic Engineering1735-28272383-38902025-06-0121235713571Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence ImagesHanim Suraya Mohd Mokhtar0Aimi Salihah Abdul Nasir1Mohammad Faridun Naim Tajuddin2Muhammad Hafeez Abdul Nasir3Kumuthawathe Ananda Rao4 Faculty of Electrical Engineering & Technology, Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia. Centre of Excellence for Renewable Energy (CERE), Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia. Centre of Excellence for Renewable Energy (CERE), Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia. School of Housing, Building and Planning, Universiti Sains Malaysia (USM), 11700 Gelugor, Pulau Pinang, Malaysia. Centre of Excellence for Renewable Energy (CERE), Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia. The rapid growth of photovoltaic (PV) systems has highlighted the need for efficient and reliable defect detection to maintain system performance. Electroluminescence (EL) imaging has emerged as a promising technique for identifying defects in PV cells; however, challenges remain in accurately classifying defects due to the variability in image quality and the complex nature of the defects. Existing studies often focus on single image enhancement techniques or fail to comprehensively compare the performance of various image enhancement methods across different deep learning (DL) models. This research addresses these gaps by proposing an in-depth analysis of the impact of multiple image enhancement techniques on defect detection performance, using various deep learning models of low, medium, and high complexity. The results demonstrate that mid-complexity models, especially DarkNet-53, achieve the highest performance with an accuracy of 94.55% after MSR2 enhancement. DarkNet-53 consistently outperformed both lower-complexity models and higher-complexity models in terms of accuracy, precision, and F1-score. The findings highlight that medium-depth models, enhanced with MSR2, offer the most reliable results for photovoltaic defect detection, demonstrating a significant improvement over other models in terms of accuracy and efficiency. This research provides valuable insights for optimizing defect detection systems in photovoltaic applications, emphasizing the importance of both model complexity and image enhancement techniques for robust performance.http://ijeee.iust.ac.ir/article-1-3571-en.pdfphotovoltaic (pv)defect classificationelectroluminescencemulti-scale retinex (msr)multi-scale retinex 2 (msr2)pre-trained models.
spellingShingle Hanim Suraya Mohd Mokhtar
Aimi Salihah Abdul Nasir
Mohammad Faridun Naim Tajuddin
Muhammad Hafeez Abdul Nasir
Kumuthawathe Ananda Rao
Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
Iranian Journal of Electrical and Electronic Engineering
photovoltaic (pv)
defect classification
electroluminescence
multi-scale retinex (msr)
multi-scale retinex 2 (msr2)
pre-trained models.
title Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
title_full Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
title_fullStr Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
title_full_unstemmed Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
title_short Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images
title_sort integrating deep transfer learning and image enhancement for enhancing defective photovoltaic cells classification in electroluminescence images
topic photovoltaic (pv)
defect classification
electroluminescence
multi-scale retinex (msr)
multi-scale retinex 2 (msr2)
pre-trained models.
url http://ijeee.iust.ac.ir/article-1-3571-en.pdf
work_keys_str_mv AT hanimsurayamohdmokhtar integratingdeeptransferlearningandimageenhancementforenhancingdefectivephotovoltaiccellsclassificationinelectroluminescenceimages
AT aimisalihahabdulnasir integratingdeeptransferlearningandimageenhancementforenhancingdefectivephotovoltaiccellsclassificationinelectroluminescenceimages
AT mohammadfaridunnaimtajuddin integratingdeeptransferlearningandimageenhancementforenhancingdefectivephotovoltaiccellsclassificationinelectroluminescenceimages
AT muhammadhafeezabdulnasir integratingdeeptransferlearningandimageenhancementforenhancingdefectivephotovoltaiccellsclassificationinelectroluminescenceimages
AT kumuthawatheanandarao integratingdeeptransferlearningandimageenhancementforenhancingdefectivephotovoltaiccellsclassificationinelectroluminescenceimages