Image segmentation is the problem of partitioning an image in a semantically meaningful way. This vague definition implies the generality of the problem-segmentation can be found in any image-driven process, e.g. fingerprint/- text/face recognition, detection of anomalies in industrial pipelines, tracking of moving people/cars/airplanes, etc. For many applications, segmentation reduces to finding an object in an image. Retinal image vessel segmentation and their branching pattern can provide us with the information about abnormality or disease by examining its pathological variance. Retinal vascular pattern are used for automated screening and diagnosis of diabetic retinopathy to assist the ophthalmologists. To enhance the blood vessels and suppress the background information, in this paper, we are proposing smoothing operation on the retinal image using mathematical morphology. Then the enhanced image will be used for segmented using K-means clustering algorithm. We will use the proposed approach on the DRIVE dataset and it will be compared with alternative approaches.
Keywords: Gabor filter, retinal images, segmentations, k-mean clustering, drive dataset, stare dataset.