Retinal blood vessel segmentation using an Extreme Learning Machine approach

Diabetic retinopathy is a vascular disorder caused by changes in the blood vessels of the retina. The proposed work uses an Extreme Learning Machine (ELM) approach for blood vessel detection in digital retinal images. This approach is based on pixel classification using a 7-D feature vector obtained from preprocessed retinal images and given as input to an ELM. Classification results categorizes each pixel into two classes namely vessel and non-vessel. Finally, post processing is done to fill pixel gaps in detected blood vessels and removes falsely-detected isolated vessel pixels. The proposed technique was assessed on the publicly available DRIVE and STARE datasets. The approach proves vessel detection is accurate for both datasets.