A Novel Approach to the Detection of Macula in Human Retinal Imagery

Abstract

This paper demonstrates an approach to the rapid detection and extraction of macula from the images of human retina. For the diagnosis of ophthalmic pathologies, digital fundus images are becoming increasingly popular. This fact opens up the possibility of applying digital image processing techniques in ocular fundus images to facilitate and improve diagnosis in different ways. Macula is the major landmark for retinal fundus image registration and is indispensible for the quick understanding of retinal images. For the detection and subsequent extraction of macula, we first perform bit plane decomposition to the preprocessed image. The bit plane 0 and bit plane 1 are found to carry vital information of the location and boundary of macula. Then we locate the exact boundary by means of mathematical morphology. The proposed algorithm is computationally simple and does not require a prior knowledge of other retinal image features like optic disc or vasculature. The algorithm has been evaluated on a subset of MESSIDOR image database with various visual qualities. Robustness with respect to changes in the parameters of the algorithm has been examined.