Automatic detection of Microaneurysm in Colour Fundus Images

Abstract

This paper addresses the automatic detection of microaneurysms (MA) in color fundus images, which may play a key role in computer assisted diagnosis of Diabetic Retinopathy (DR), a serious and frequent eye disease. The algorithm can be divided into 4 steps. The first step consists in image enhancement, shade correction and image normalization of the green channel of the color fundus image. The second step aims to detect the candidates, i.e. all patterns which may correspond to MA, which is achieved by the diameter closing and an automatic threshold scheme. Then, features are extracted, which are used in the last step to automatically classify candidates into real MA and other objects.