Open Access Open Access  Restricted Access Subscription or Fee Access

Automatic Optic Disc and Macula Extraction in Retinal Images Using Curvelet Transform-based Enhancement and Multi-Directional Functors

Saleh Shahbeig, Hossein Pourghassem, Homayoun Mahdavi-Nasab

Abstract


Retina images have different and vast applications in security systems and medicine such as human identification and eye disease diagnosis. In all of these applications, the need for an automatic system which can recognize and locate eye different parts (such as optical disc (OD) and Macula) as features in the retinal images is quite vital. In this paper, a novel automatic OD and macula extraction algorithm based on Curvelet transform as a multi-scale transforms and multi-directional functor is proposed. In this algorithm, using the introduced multi-directional functor, a brightness structure for the OD and macula extraction is created. In this brightness structure, special brightness patterns for the OD and macula are formed using applying the introduced functor in multiple directions on each pixel of the retinal image. The low contrast retinal images demand for a pre-processing step which the eye components can be distinguished easily from the image background. For this purpose, an effective pre-processing step based on Curvelet transform and a nonlinear adaptive function is utilized. The proposed algorithm is evaluated on available images of the STARE database. The experimental results indicate that the proposed algorithm obtains accuracy rate of 97.5% and 98.7% for the OD and macula extractions on STARE database, respectively.

Keywords


Optical disc and macula extraction, Curvelet transform, intensity equalizer function, multi-directional functor, retinal image.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.