System-on-chip based Automated Optic Disk Segmentation in Retinal Images

Abstract

In this paper a novel technique on automated optical disk (OD) segmentation is proposed. The proposed OD algorithm depends on morphological based algorithm. This technique is assessed on openly accessible standard data sets DRIONS. The average accuracy rate of proposed segmented technique is 97.6% on DRIONS database. The proposed algorithm achieved Average Sensitivity, Average Specificity and Average Overlap of 93.1 %, 98.4% and 86.3% respectively on DRIONS data sets. Test results shows the algorithm is superior with comparable execution time over existing OD algorithms. Further, the algorithm has been implemented in System-on-chip (Zync-7000) kit.