A fundus camera provides digitised data in the form of a fundus image that can be effectively used for the computerised automated detection of diabetic retinopathy. A completely automated screening system for the disease can largely reduces the burden of the specialist and saves cost. Noise and other disturbances that occur during image acquisition may lead to false detection of the disease and this is overcome by various image processing techniques. Following this different features are extracted which serves as the guideline to identify and grade the severity of the disease. Based on the extracted features classification of the retinal image as normal or abnormal is brought about. In literature various techniques for feature extraction and different types of classifiers have been used to improve sensitivity and specificity. FROC analysis and confusion matrix are used to evaluate the system performance. In this paper critical analysis of various algorithms and classifiers is done that have been used for the automated diagnosis.