Segmentation of Vessels in Fundus Images using Spatially Weighted Fuzzy c-Means Clustering Algorithm

† Department of Electronics & Communication Engineering, S.R.K. Institute of Technology, Vijayawada, India †† Department of Electronics & Communication Engineering, Jawaharlal Nehru Technological University, Hyderabad, India ††† Department of Electronics & Communication Engineering, Amrita Sai institute of Science & Technology, Paritala, India. Summary This paper presents an algorithm for the extraction of Blood Vessels from Fundus images using Matched filter and Thresholding based on Spatially Weighted Fuzzy cMeans (SWFCM) clustering algorithm. Such a tool should prove useful to eyecare specialists for purposes of patient screening, treatment, and clinical study. We make use of a set of linear filters sensitive to vessels of different orientation and thickness. Such filters are obtained as linear combinations of properly shifted Gaussian kernels. The Spatially Weighted Fuzzy c-Means clustering algorithm is formulated by incorporating the spatial neighborhood information into the standard FCM clustering algorithm. An experimental evaluation demonstrates superior performance over global thresholding and a vessel detection methods recently reported in the literature. Due to its simplicity and general nature, our proposed algorithm is expected to be applicable to a variety of other applications.