The aim of this thesis is to automatically detect exudates in fundus images. To achieve the goal, the proposed method first preprocesses to improve the quality of fundus image, and then OD is detected and eliminated to prevent the interference to the result of exudate detection. Next, exudates are detected by filtering out the bright pixels from the result of OD region eliminated. Since the result contains some noises which appear randomly so the post processing is applied to improve the result of false positive. Finally, exudates are extracted by using Morphological Reconstruction (MR).
The proposed technique has been tested on 1579 images from a hospital. Experimental results show that the best performance is 85 % of exudate detection correctly.