Background and Noise Extraction from Colored Retinal Images

Retinal images are used for automated diagnosis of Diabetic Retinopathy. Preprocessing of retinal image is required prior to detection of features and abnormalities. The objective of preprocessing segmentation is to separate the background and noisy area from the overall image to enhance the quality of acquired retinal image. We present a method for colored retinal image preprocessing and enhancement. Our technique creates a binary mask to preprocess the retinal image using morphological operations.The preprocessing technique is tested on standard retinal images databases Diaretdb0 and Diaretdb1. The validity of our technique is checked against the experimental results.