Automatic segmentation of blood vessels in retinal image using morphological filters

Abstract

This paper presents the method for automatic segmentation of blood vessels in retinal image. Proposed approach makes use of morphological filter called top hat transform oriented at three directions for extraction of vessel network. Segmentation of vessel structure is done using single global threshold. This approach is tested on standard DRIVE database. Experimental results show better performance of the proposed method for segmentation of vessel structure. Proposed approach is superior over the algorithms available in literature with respect to accuracy and computation time.