Computer Aided Screening of Optic Disc in Retinal Images Using Binary Orientation Map

Abstract

Optic disc detection is an important step in retinal image screening process. This paper proposes an Automatic detection of an optic disc in retinal fundus images. The manual method graded by clinicians is a time consuming and resource-intensive process. Automatic retinal image analysis provides an immediate detection and characterization of retinal features prior to specialist inspection. This proposed a binary orientation technique to detect optic disc, which provides higher percentage of detection than the already existing methods. The method starts with converting the RGB image input into its LAB component. This image is smoothed using bilateral smoothing filter. Further, filtering is carried out using line operator. After which gray orientation and binary map orientation is carried out and then with the use of the resulting maximum image variation the area of the presence of the OD is found. The portions other than OD are blurred using 2D circular convolution. On applying mathematical steps like peak classification, concentric circles design and image difference calculation, OD is detected. The proposed method was implemented in MATLAB and tested by publically available retinal datasets such as STARE, DRIVE. The success percentage was found to be 98.34% and the comparison is done based on success percentage.

Pre-processing of Retinal Images for Removal of Outliers

“…Rana et al used min, max and median filters for removal of blood vessels in red and green color spaces of input retinal image for segmentation of optic disc and cup [32]. Murugan et al used lightness component of Lab color space with bilateral filter for pre-processing the input image [33]. Later, Mittapali et al performed elimination of blood vessels by using function of gaussian as a kernel of match filter to focus on the retinal vessels that create difficulties in extraction.…”