Image Analysis of Fundus by Using Filter Bank with the Performance Evaluation Function Based on the Significance by SOM

Abstract

Attempts to detect the early stages of glaucoma by image processing techniques have been proposed. In real medical data, differences in classes may exceed the differences between classes, and the selection of feature and the preprocessing become important. In this paper, we propose a new method for fundus image analysis by using filter bank with the performance evaluation function based on the significance by SOM. With using of the significance by SOM, we will clarify the effect of filtering affecting the classification performance of fundus image analysis using filter bank.