A Composite Architecture for an Automatic Detection of Optic Disc in Retinal Imaging

An automatic detection of the position of optic disc (OD) is an important step in a deep analysis of retinal images, due to the fact that information about OD can be used to examine the severity of some ophthalmic pathology via the extraction of a region of interest. Since errors caused by artifacts and bright fringes on retinal images could affect results in image processing, in this work a Composite Architecture for an accurate identification of the centre of OD is presented. More in detail, a Maximum Difference Evaluation Subsystem and a Maximum Gray Level Evaluation Subsystem are combined to analyze retinal images in parallel and find possible values of the centre of optic disc in different ways; locations of resulting pixels are then processed by an OD Centre Positioning Subsystem, which provides a reliable point to be adopted as the centre of the optic disc as effectively as possible. Simulation results are reported on selected fundus oculi images.