Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172201,
        author = {prasad and anushka phadtare and isha velankar and umakant shinde},
        title = {Solar Panel Defect Detection: Integrating YOLOv8 with Classification Techniques.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {2673-2679},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172201},
        abstract = {Defect detection in solar panels is a crucial step to ensure product quality within automated production lines. However, traditional manual inspection methods suffer from low efficiency. This paper proposes an enhanced YOLOv8 algorithm tailored for the detection of three common types of defects: hotspots, branch cracks, and line cracks. Utilizing publicly available solar panel datasets alongside data collected from actual photovoltaic production lines, the datasets were carefully annotated to train the proposed algorithm. Experimental results demonstrate that the YOLOv8-based approach performs effectively on both public and real-world datasets. Notably, despite the subtle nature and smaller size of defects in real-world datasets, the algorithm successfully identifies even minor defects such as small hotspots.},
        keywords = {},
        month = {January},
        }