You are in:Home/Publications/Integrated Features Based on Gray-Level and Hu Moment-Invariants with Ant Colony System for Retinal Blood Vessels Segmentation

Dr. Assoc. Prof. Ahmad Taher Azar :: Publications:

Title:
Integrated Features Based on Gray-Level and Hu Moment-Invariants with Ant Colony System for Retinal Blood Vessels Segmentation
Authors: Ahmed H. Asad, Ahmad Taher Azar, Aboul Ella Hassanien
Year: 2012
Keywords: Not Available
Journal: Not Available
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: International
Paper Link:
Full paper Not Available
Supplementary materials Not Available
Abstract:

Abnormality detection plays an important role in many real-life applications. Retinal vessel segmentation algorithms are the critical components of circulatory blood vessel Analysis systems for detecting the various abnormalities in retinal images. Traditionally, the vascular network is mapped by hand in a time-consuming process that requires both training and skill. Automating the process allows consistency, and most importantly, frees up the time that a skilled technician or doctor would normally use for manual screening. Several studies were carried out on the segmentation of blood vessels in general; however, only a small number of them were associated to retinal blood vessels. In this paper, an approach for segmenting retinal blood vessels is proposed using only ant colony system. Eight features are selected for the developed system; four are based on gray-level and the other features on Hu moment-invariants. The features are directly computed from values of image pixels, so they take about 90 seconds in computation. The performance of the proposed structure is evaluated in terms of accuracy, true positive rate (TPR) and false positive rate (FPR). The results showed that the overall accuracy and sensitivity of the presented approach achieved 90.28% and 74%, respectively.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus