Description

Abstract

Here we propose a quantitative assessment of Diabetic Macular Edema (DME) from Fundus image sequences. We present a method for processing Fundus images to generate a fluorescein leakage map that can be used for quantitative gauge of DME. Model the spatial distribution of the image intensity within the macula is the initial process in our method. Shape features play an important role in computer vision, image processing and pattern recognition.  We introduce a novel method of using SVM (Support Vector machine) classifier shape feature. Finally detect normal or abnormal from fundus image.