Detection of Lesions and Feature Extraction for Diabetic Retinopathy

Detection of Diabetic Retinopathy (DR) in early stage is essential to avoid complete blindness. The retinal fundus images of the patients are procured by capturing the fundus of the eye with a digital fundus camera. Fundus Images should be pre-processed to remove the noise, preserve the edges of an image, and enhance the image quality for carrying out further image analysis. This paper provides various pre-processing techniques for detection of DR. The abnormalities in retinal fundus images due to DR are Lesions which includes Microaneurysms, Hemorrhages, exudates and blood vessels. In this study canny’s edge detector is used for detection of Lesions and features are extracted. KeywordsFundus, Lesions, Canny’s edge detector, Median filter.