An Improved Method for Optic Disc Localization

Abstract

An accurate approach for localization and segmentation of an optic disk (OD) in the retinal images is one of the most imperative tasks in an automated screening system. The retinal fundus images analysis is extensively used in the diagnosis and treatment of several eye diseases such as glaucoma and diabetic retinopathy. This research brings out a new algorithm that has not been used before to detect and segment the optic disk in all categories of retinal images, specifically healthy retinal images plus anomalous, or in other words fundus images affected due to diseases. The technique adopted for the separation of the optic disk is centered on histogram specification, mathematical morphological operations includes erosion as well as dilation along with proper thresholding and detection of circles using the Hough Transform technique. The proposed procedure has been tested on standard databases provided for ophthalmic image processing researches on internet, Diaretdb0, Diaretdb1 and local databases collected from the National Eye Hospital and the Vision Care (Pvt) Ltd. The proposed algorithm is able to locate the OD in 90% of all tested images.

Optic Disc Detection in Fundus Eye Images – A Detailed Survey

“…The IMAGERET database consists of two sub-databases, DIARETDB0 [2][6] and DIARETDB1 [1][6] [23]. DIARETDB0 has 130 images of which 20 are normal images and the remaining have pathologies such as exudates and hemorrhages.…”

Deteksi Dini Retinopati Diabetik dengan Pengolahan Citra Berbasis Morfologi Matematika

“…Modifikasi dilakukan pada tahap preprocessing yakni dengan menggunakan kanal merah untuk mendeteksi optical disk karena pada kanal tersebut optical disk terlihat jelas [10]. Serta akan dilakukan enhancement dengan menggunakan histogram spesifikasi.…”