Clustering Technique for Segmentation of Exudates in Fundus Image

Exudates are a category of lipid retinal lesions visible through optical fundus imaging, and indicative of diabetic retinopathy. we tend to propose a clustering-based methodology to phase exudates, using multi-space clustering, and colorspace options. The tactic was evaluated on a group of eighty nine pictures from a publically obtainable dataset, and achieves an accuracy of 89.7% and positive prophetical price of 87%.