摘要
The estimation of Arterio-Venous ratio (AVR) is an important phase in diagnosing various vascular diseases e.g. Diabetic Retinopathy. For calculating this value, it is essential to differentiate the vessels into arteries and veins. This paper presents a novel structural and automated method for artery/vein vessels classification in retinal images. Our method is tested on DRIVE database and the classification accuracy is 88.7% for pixels and 89.07% for vessel lines, respectively, which demonstrate the effectives of our approach. Our method will help to achieve the fundus disease surveillance on mobile and remote medical treatment. It has a remarkable social significance.
- 出版日期2016
- 单位University of LIVERPOOL; The University of Liverpool