Annals of Advanced Biomedical Sciences ISSN: 2641-9459 Automated Segmentation of Optic Disc and Cup in Color Fundus Images Ann Adv Biomed Sci Automated Segmentation of Optic Disc and Cup in Color Fundus Images Vijay M Mane* and Rahul Bal Vishwakarma Institute of Technology, Pune, Maharashtra, India *Corresponding author: Vijay M Mane, Vishwakarma Institute of Technology, Pune, Maharashtra, India, Tel: 9822550134; Email: manevijaym@gmail.com Abstract An automatic Optic disc and Optic cup detection technique which is an important step in developing systems for computer-aided eye disease diagnosis is presented in this paper. This paper presents an algorithm for localization and segmentation of optic disc from digital retinal images. OD localization is achieved by circular Hough transform using morphological preprocessing and segmentation is achieved by watershed transformation. Optic cup segmentation is achieved by marker controlled watershed transformation. The optic disc to cup ratio (CDR) is calculated which is an important parameter for glaucoma diagnosis. The presented algorithm is evaluated against publically available DRIVE dataset. The presented methodology achieved 88% average sensitivity and 80% average overlap. The average CDR detected is 0.1983. Keywords: Image processing; retina; optic disc; optic cup; glaucoma Introduction An optic disc (OD) is one of the most important structures of human retina [1] and their detection is an important step in computer aided diagnosis of various eye diseases [2]. In color fundus image, OD appears as a round bright yellowish or white region having shape more or less circular as shown in Figure 1. Optic cup plays an important role in glaucoma detection [3], the enlargement of which with respect to OD is an indicator of glaucoma. Figure 1: OD and OC regions in retina image. Literature Review Chaum, et al. [1] proposed a method based on Bayesian classifier to extract OD. By obtaining confidence image map, the point with highest value represents OD center. Cook, et al. [2] proposed a method based on intensity variation as OD has higher intensity variation than other regions in the retina image. Jin, et al. [3] proposed a method to locate OD based on mathematical morphology. Grisan, et al. [4] located OD region based on optimization technique. Convergence point of blood vessels is identified as OD center. Ghalwash, et al. [5] Detected OD using matched directional filters. Rinton, et al. [6] proposed a genetic algorithm to detect OD boundary. Tegolo, et al. [7] proposed regression based method to find OD boundary. Barmanb, et al. [8] used morphological approach to segment OD. Ginneken, et al. [9] Segmented OD based on point distribution model by using optimized cost function. Basu, et al. [10] Research Article Volume 2 Issue 1 Received Date: November 22, 2018 Published Date: January 09, 2019 DOI: 10.23880/aabsc-16000111