• Nazeer Baba SK
• Sunitha M V V L
• Meghana K
• Akhil Samarpana P
• Lakshmi jahnavi P

Solar cells are essential devices for converting sunlight into electricity, and ensuring their defect-free quality is crucial for optimal performance and longevity. Traditional defect detection methods often suffer from low accuracy, making it imperative to explore advanced detection techniques. In this work, we extend the optimized YOLOv5-based defect detection system by experimenting with the advanced YOLO family, specifically YOLOv6. The proposed extension utilizes the ELPV dataset, containing over 2,000 images classified into MONO and POLY defect categories with defect probability percentages instead of bounding boxes. YOLOv6, known for its enhanced architecture and improved computational efficiency, demonstrates superior performance in detecting solar cell surface defects. Key image enhancement techniques such as Mosaic, Mix-up, HSV transform, scaling, and flipping were applied to improve image clarity, facilitating better feature extraction.

"Advanced YOLOv6-Based Solar Cell Defect Detection with Image Enhancements", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.j352-j357, March-2025, Available :http://www.jetir.org/papers/JETIR2503944.pdf

"Advanced YOLOv6-Based Solar Cell Defect Detection with Image Enhancements", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppj352-j357, March-2025, Available at : http://www.jetir.org/papers/JETIR2503944.pdf