This paper proposes two efficient approaches for automatic detection and extraction of Exudates and Blood vessels in ocular fundus images. The blood vessel extraction algorithm is composed of three steps, i.e., matched filtering, thresholding and label filtering. The identification of exudates involves Preprocessing, Optic disk elimination, and Segmentation of Exudates. In both the methods the enhanced segments are extracted based on Spatially Weighted Fuzzy c-Means (SWFCM) clustering algorithm. The Spatially Weighted Fuzzy c-Means clustering algorithm is formulated by incorporating the spatial neighborhood information into the standard FCM clustering algorithm. Experimental evaluations of both the approaches demonstrate superior performances over other vessel detection and exudates detection algorithms recently reported in the literature. © 2008 IEEE.
cited By (since 1996)0; Conference of org.apache.xalan.xsltc.dom.DOMAdapter@11aef353 ; Conference Date: org.apache.xalan.xsltc.dom.DOMAdapter@74e8d736 Through org.apache.xalan.xsltc.dom.DOMAdapter@62895630; Conference Code:73588
G. Ba Kande, Savithri, T. Sb, and Subbaiah, P. Vc, “Extraction of exudates and blood vessels in digital fundus images”, in Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008, Sydney, NSW, 2008, pp. 526-531.