Back to articles
Volume: 19 | Article ID: art00030
Fast Colour Vesselness
  DOI :  10.2352/CIC.2011.19.1.art00030  Published OnlineJanuary 2011

Vesselness in an image is a map that conveys the extent to which certain image structures resemble blood vessels. The standard approach to this problem uses greyscale images. An earlier algorithm [1] derives a vesselness map for a colour image from the Hessian of a pure quaternion whose components are the colour channels. As an alternative to that method, we here divide the vesselness task into two parts: Convert the colour image to a grey image using the Fast Color2Grey algorithm [2, 3], and then use the traditional Frangi Hessian method [4] on that grey image to produce the vesselness map. Compared with the quaternion-based algorithm, the method proposed here is more accurate in identifying retinal blood vessels and also operates 104 times as fast.

Subject Areas :
Views 3
Downloads 0
 articleview.views 3
 articleview.downloads 0
  Cite this article 

Mark S. Drew, Ali Alsam, Ali Madooei, Michael H. Brill, "Fast Colour Vesselnessin Proc. IS&T 19th Color and Imaging Conf.,  2011,  pp 146 - 151,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2011
Color and Imaging Conference
color imaging conf
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA