Diabetic Retinopathy is an eye disease found in people having high blood sugar. It can lead to loss of vision, if it is not treated properly. There is an increase in number of patients in comparison to ophthalmologists. In this scenario there is a need for a system to aid the ophthalmologists for faster and easy diagnosis. In an automated detection of diabetic retinopathy, the images of retina obtained by fundus camera are processed to determine the features such as Microaneurysms, Haemorrhages Exudates and cotton wools. These are the signs of severity of Diabetic Retinopathy. The various stages in this process of detection include preprocessing, feature detection and classification. In this paper, various methods used by researchers for each of these steps are explored. Different fundus image databases available have been discussed. The different parameters used for evaluation of developed systems have been presented. The research work done in this field for last five years has been reviewed for this purpose.