SCREENING RETINAL DISEASES WITH LOCAL BINARY PATTERNSBASED IMAGE ANALYSIS

Abstract

Retinal diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma are among the leading causes of visual impairment and blindness worldwide. Early detection and screening are essential to prevent irreversible damage and improve patient outcomes. This study proposes an automated framework for retinal disease screening using Local Binary Patterns (LBP)-based image analysis. LBP, a texture descriptor, has demonstrated robustness in characterizing fine variations in retinal structures, making it highly suitable for identifying pathological changes in fundus images. By integrating LBP feature extraction with machine learning classifiers, the system aims to improve the accuracy and efficiency of early diagnosis. Experimental evaluations on publicly available retinal image datasets highlight the potential of the proposed approach in differentiating between healthy and diseased retinas, demonstrating its significance as a low-cost, computationally efficient, and reliable screening tool for large-scale medical applications