Abstarct: The thesis aims to propose an efficient algorithm for segmentation of blood vessel in colored retinal fundus image. We have used an algorithm contains three main stages. Preprocessing is the first stage which is divided into two steps itself. Obtain threshold via Contourlet Transform and PSO algorithm, modification of Contourlet coefficients and enhance image are these two steps. The second stage is extracting the vessels. In order to extract vessels we have used use a line detector at eight scales and twelve directions to extract proper features for detecting vessels. Last stage is postprossesing to improve the quality of extracted vessels. At this stage removes some noise and broken blood vessels are connected to the Vessel tree. The broken vessels are lixnked using a grouping strategy. The proposed method is evaluated and compared with several recent methods using images from the DRIVE databaxse Keywords-component: Retinal