Enhanced Retinal Vessel Detection Using Gradient Pyramid Fusion Algorithm

Abstract

The main goal of this study is to create an innovative approach to retinal vessel detection using the gradient pyramid fusion algorithm to improve edge continuity and measurement precision in retinal images. Traditional methods, like wavelet transform and guided filter, face challenges with background noise, artifacts and uneven illumination, which can distort vessel measurement. The proposed fusion method manages to overcome these limitations by combining the strengths of traditional techniques, which creates more continuous edges through gradient fusion across multiple scales, thus managing to also limit the number of image artifacts. We used images from the DRIVE database, to evaluate the fusion algorithm’s precision, with results showing improved vascular tree detection and continuous edges, a reduction in the number of artifacts and improved measurement accuracy. The results show that this image fusion method improves the retinal image analysis, thus helping in early disease diagnosis.