FPGA and MATLAB Based Solution for Retinal Exudate Detection
Vasanthi Satyananda1, Narayanaswamy K. V.2, Karibasappa3
1Vasanthi Satyananda*, Associate Professor, Department of ECE, Atria Institute of Technology, Bangalore; Research Scholar, Visvesvaraya Technological University, Karnataka, India.
2Narayanaswamy K V, Principal, Atria Institute of Technology, Bangalore, India.
3Karibasappa, Director, Dayanand Sagar University, Bangalore, India.
Manuscript received on February 02, 2020. | Revised Manuscript received on February 10, 2020. | Manuscript published on March 30, 2020. | PP: 727-734 | Volume-8 Issue-6, March 2020. | Retrieval Number: F7153038620/2020©BEIESP | DOI: 10.35940/ijrte.F7153.038620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Now-a-days, image processing is extensively used for analysis of several biomedical images to identify the complications in one’s health. Most of the solutions offered are based on application software. Since these solutions are expensive, an embedded system approach is being explored in the recent years, considering its cost-effectiveness. This paper propounds an embedded system approach to identify exudates in retinal images. These exudates are often identified as indicators of a medical disorder known as Diabetic Retinopathy, which is one of the medical complications that arise due to high blood sugar levels. The algorithm employs statistical analysis using histogram to enhance the contrast of the images, thus assisting in extracting exudates by utilising the elementary concepts of image processing. Since the pixel characteristics of exudates and optic disk match, it becomes inevitable to first eliminate optic disk from retinal images, and then extract exudates. The prototype has been developed on MATLAB and is downloaded on an Artix 7 FPGA with minimal usage of its resources. The system proposed in this paper results in an accuracy of 90%.
Keywords: Diabetic Retinopathy, Exudates, FPGA, Image Processing, Histogram, Labeling, Optic Disc, Elimination, MATLAB.
Scope of the Article: FPGAs.