An Enhanced Exudate Segmentation in Fundus Images Using Ant Colony Optimization and Decision Based Median Filtering

The leading cause of new blindness and vision defects in working-age people, diabetic retinopathy is a serious public health problem in developed countries. Automatic identification of diabetic retinopathy lesions, such as exudates, in fundus images can contribute to early diagnosis. Currently, many studies in the literature have reported on segmenting exudates, but none of the methods performs as needed. Moreover, segment exudates with a new unsupervised approach based on the ant colony optimization algorithm has shown better results but it suffers from the effect of the noise. So in order to overcome this limitation this research work has proposed a new decision based median filtering based technique to reduce the effect of the noise. The proposed technique seems to be justifiable as decision based median filtering has ability to reduce the effect of the high density of the noise. Due to non- availability of actual environment, the proposed technique has been designed and implemented in the MATLAB2013a using image processing toolbox.