文章基本信息

标题：Retinal Blood Vessels Detection
本地全文：下载
作者：Aastha Agarwal ; Nandita Gauri ; Fezul Hasan 等
期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2021
卷号：3
期号：6
页码：2388-2392
DOI：10.35629/5252-030619741982
语种：English
出版社：IJAEM JOURNAL
摘要：A major health problem among the old and the elderly people is eye diseases. One of the most important internal components of the eye is called the retina. The retina at the back of the eye is not only an important part of human vision; it also contains valuable information that can be used for biometric security applications or to diagnose certain diseases. Quantitative analysis of the vascular structure of the retina helps to monitor the effects of glaucoma and diabetic retinopathy. Several morphologic characteristics of the retinal veins and arteries, such as diameter, length, ramus angle, and curvature, are diagnostically relevant and can be used to monitor disease progression. In this work, we detect blood vessels and diseases such as glaucoma and diabetic retinopathy. We use resized images to obtain traces of blood vessels. We propose a method to detect blood vessels, including three stages, pre-processing, training, and blood vessel detection. In addition, we propose a Keras model for disease detection in retinal images ,including four main steps: pre-processing, model training, disease detection and Classification. Once classified and detected any disease, our system will also provide corresponding remedial measures. It also shows the details of the result in percentage. The performance of the Keras model is compared and analyzed in the database. The working method of the system is completely divided into five main modules: -  Input retinal image  pre-processing  Model training  Disease detection  Classification.
关键词：Retinal image;pre- processing;Model training;attribute extraction;disease detection;classification