Abstract: | The aim of this project was to design and implement a non-invasive, automated method for the examination and follow-up of the arteriosclerotic changes due to hypertension, with the help of digital image processing of the retinal vessels. This would help a lot in evaluating the efficacy of various treatments on the regression and reversion of arteriosclerotic lesions. We develop a method for segmenting vessels from fundus images ;using ridge detection. An algorithm is devised and implemented. Once the vessels are segmented we move on to measurements of vessel width, thickness of the wall, length of the vessels and tortuosity index. All our methods are automatic and do not depend on any image specific thresholds or other parameters.
|