• P. Hari Chandana
• Dr. G. Umamaheswara Reddy

Exudates are in the form of a fluid that has leaked out of blood vessels and closely resembles blood plasma. It is a major complication of causing blindness in Diabetic Retinopathy (DR) patients. The main objective of this study is to develop a novel method to finding the exudates with high accuracy and classify exactly what are mild and severe exudates based on color indication with complete and distinguished patient information in color retinal images by using a saliency map algorithm. The Proposed approach starts with a normalization of retinal image, contrast enhancement, noise removal, and the localization of Optical Disc (OD). Then, a segmentation method by using Saliency map to detect only exudates regions. Finally, classification using the support vector machine (SVM) is applied to detect what type of exudated retinal image based on color indication with patient information. Based on a comparison between the results and ground truth images, the proposed method obtained an accuracy for detecting exudates as 98.50%, 98.35% and 98.15% respectively.

Retinal images, Exudates, Saliency map, Support vector machine (SVM), Optical Disc (OD).

"Automatic Detection of Exudates in Retinal Images using Saliency Map Method", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 12, page no.306-310, December-2020, Available :http://www.jetir.org/papers/JETIR2012043.pdf

"Automatic Detection of Exudates in Retinal Images using Saliency Map Method", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 12, page no. pp306-310, December-2020, Available at : http://www.jetir.org/papers/JETIR2012043.pdf