Majlesi Journal of Electrical Engineering New Method for Blood Vessels Segmentation in Retinal Images Volume 1 (2007) Issue 1, June 2007 2024 02 28 New Method for Blood Vessels Segmentation in Retinal Images 10.1234/mjee.v1i1.47 EN Hadi Farzin Trent University Hamid Abrishami Moghaddam Khaje Nasir Toosi University of Technology Mohammad-Shahram Moin Iran Telecommunication Research Center Journal Article 2024 02 28 Retinal image analysis has many applications in various fields such as biometrics or medical diagnosis. Blood vessel segmentation is the first and important stage in these analyses. This paper presents an efficient method for automatic segmentation of blood vessels in retinal images. In the first stage, the proposed algorithm uses a template matching technique for reducing the effect of optical disk in the image. Then, it uses a new local processing operation based on the statistical properties of the image in order to enhance the vessel/background contrast. Next morphological operations are used for filling the vessel spaces caused by the previous stages. Finally, a binary image containing blood vessels is resulted by histogram thresholding of the contrast enhanced image. Evaluation of the results obtained by the new segmentation algorithm demonstrated its superior sensitivity and comparable accuracy with respect to the results of the previous works.