Retinal vessel segmentation using spatially weighted fuzzy c-means clustering and histogram matching

This paper presents a novel approach for automated segmentation of the vasculature in retinal images. The approach uses the intensity information from red and green channels of the same retinal image to correct nonuniform illumination in colour fundus images. Matched filtering is utilized to enhance the contrast of blood vessels against the background. The enhanced blood vessels are then segmented by employing spatially weighted fuzzy c-means clustering based thresholding which can well maintain the spatial structure of the vascular tree segments. Experimental results of the proposed method using STARE and DRIVE databases are superior to previously reported unsupervised methods and comparable to those obtained with the supervised methods.