Extraction of Solar Panel Image Texture Feature Using GLCM Method for Damage Analysis on Solar Panel Surface Images

Abstract

Existing techniques for assessing solar panel surface damage frequently lack precision in differentiating defect kinds, necessitating a dependable automated solution. Defects like cracks and scratches substantially diminish panel efficiency, underscoring the necessity of robust analytical procedures. This study seeks to validate the Gray Level Cooccurrence Matrix (GLCM) technique for extracting texture information to identify and analyze damage on solar panel surfaces. This method utilizes Python software and a dataset of solar panel surface photos to accurately distinguish between damaged and undamaged surfaces. The spot category demonstrates the lowest homogeneity (5636.922) and contrast (5632.922), signifying a smoother yet less uniform texture. Energy values are predominantly low across all categories, with marginally higher consistency in fractures (0.005) relative to others (0.002). The results indicate that faults enhance unpredictability and randomization in texture relative to the homogeneity of intact surfaces. These insights facilitate precise damage identification and enhanced maintenance plans. This research provides advancements in renewable energy, materials science, and computer vision, applicable to solar panel maintenance, quality assurance, and automated flaw identification within the photovoltaic sector.