Diabetic Macular Edema (DME) is a symptom of diabetic retinopathy which is a threatening complication of diabetic retinopathy. Severity of DME can be assessed by detecting exudates (a type of bright lesions) in color fundus images. In this, disease severity is assessed by using rotational asymmetry metric. The method in this project is based on an algorithm which can able to detect exudates with some attached confidence level without the use of machine learning methods to separate false positives from true positives, on a color space analysis and on new methods to characterize the lesions by the means of wavelet analysis. Here we use SVM classifier to classify the input image whether it was normal or abnormal.