Detection of Diabetic Retinopathy in Retinal Images using MLP classifier

The rising situation in the developing world suggests diabetic retinopathy may soon be a major problem in the clinical world [1]. Hence, detection of diabetic retinopathy is important. This paper focuses on Multi Layer Perception Neural Network (MLPNN) to detect diabetic retinopathy in retinal images. In this paper the MLPNN classifier is presented to classify retinal images as normal and abnormal. A feature vector is formed with 64-point Discrete Cosine Transform (DCT) with different 09 statistical parameters namely Entropy, mean, standard deviation, average, Euler number, contrast, correlation, energy and homogeneity. The Train N Times method was used to train the MLPNN to find best feature subset. The training and cross validation rates by the MLP NN are 100% for detection of normal and abnormal retinal images.