Abstract:
Optic Disk (OD) detection plays an important role for fundus image analysis. In this paper, we propose an algorithm for detecting OD mainly based on a classifier model tr...Show MoreMetadata
Abstract:
Optic Disk (OD) detection plays an important role for fundus image analysis. In this paper, we propose an algorithm for detecting OD mainly based on a classifier model trained by structured learning. Then we use the model to achieve the edge map of OD. Thresholding is performed on the edge map to obtain a binary image. Finally, circle Hough transform is carried out to approximate the boundary of OD by a circle. The proposed algorithm has been evaluated on the public database and obtained promising results. The results (an area overlap and Dices coefficients of 0.8636 and 0.9196, respectively, an accuracy of 0.9770, and a true positive and false positive fraction of 0.9212 and 0.0106) show that the proposed method is a robust tool for the segmentation of OD and is very competitive with the stage-of-the-art methods.
Date of Conference: 06-09 December 2015
Date Added to IEEE Xplore: 25 February 2016
ISBN Information: