Extraction of Retinal Blood Vessel Using Curvelet Transform and Fuzzy C-Means

摘要: This paper addresses the automatic blood vessel detection problem in retinal images using matched filtering an integrated system design platform that involves curve let transform and fuzzy c-means. Although noise is kept constant medical CCD cameras, due to a number of factors, contrast between background vessels consequently visual quality looks very poor. Some form pre-processing operation therefore essential for accurate extraction these vessels. Since can represent lines, edges curvatures well as compared other multi-resolution techniques, this uses enhance vasculature. Matched then used intensify which further employed by c-means algorithm extract silhouette from background. Performance evaluated on publicly available DRIVE database with existing methodology transform. Simulation results demonstrate proposed method much efficient detecting long thick short thin vessels, wherein methods fail tiny