Detection and Classification of Exudates by Extracting the Area from RGB Fundus Images
Mohammed Shafeeq Ahmed1, B. Indira2
1Mohammed Shafeeq Ahmed, Department of Computer Science, Gulbarga University, Kalaburagi, Kalaburagi, India.
2Dr. B. Indira, Department of Computer Science, Chaitanya Bharathi Institute of Technology, Hyderabad, India.
Manuscript received on 11 April 2019 | Revised Manuscript received on 19 May 2019 | Manuscript published on 30 May 2019 | PP: 2282-2287 | Volume-8 Issue-1, May 2019 | Retrieval Number: A1240058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A technique for exudate detection in fundus image is been presented in this paper. Due to diabetic retinopathy, an abnormality is caused known as exudates. The loss of vision can be prevented by detecting the exudates as early as possible. The work mainly aims at detecting exudates which have been present in the green channel of the RGB image by applying few preprocessing steps, 2D-DWT and feature extraction. The extracted features are fed to three different classifiers such as KNN, SVM, and NN. Based on the classifiers result the exudate is classified as normal, soft exudate and hard exudate, if exudate is present the extraction of ROI of exudate is done based on canny edge detection followed by morphological operations. The severity of the exudates is established in the area of the detected exudate. The NN, with ROI, was smeared on RGB fundus images for location of exudate. The NN was castoff with image processing methods by which we achieved a 100% success rate.
Index Terms: Exudates, Canny Edge Detection, Diabetic Retinopathy, DWT, Fundus Image, KNN, Morphological Operations, NN, SVM.
Scope of the Article: Classification