Affiliations: Institute of Automation, Chinese Academy of Sciences,
Beijing, 100190, P.R. China | Life Science Center, Xidian University, Xian, Shanxi,
710071, P.R. China
Note: [] Corresponding author. Jie Tian, Institute of Automation, Chinese
Academy of Sciences, Zhongguancun East Rd. 95, Haidian Dist., Beijing, 100190,
P.R. China. Tel.: +86 10 82628760; Fax: +86 10 62527995; E-mail: tian@ieee.org
Abstract: In order to extract the low contrast vessels in retinal images, we
propose a novel enhancement algorithm based on directional field and develop a
robust retinal vessel extraction framework. The proposed enhancement algorithm
can significantly improve the contrast of vasculature especially the slim
vessels and low contrast vessels. In our framework, we first enhance the
vasculature by the proposed enhancement algorithm, and extract the vessels from
the enhanced image by a local extraction method. Secondly, we apply a series of
modified top-hat transform to original image, and use a binary morphological
reconstruction to extract the large size vessels. Finally, the whole
vasculature is provided by an organic combination algorithm. The first step
extracts the slim vessels and low contrast vessels well but misses some
bifurcations and cross pixels. On the other hand, the second step preserves the
bifurcations and cross pixels but misses some slim vessels and low contrast
vessels. Therefore, the combination of the two methods can provide satisfactory
extraction of vasculature. Experimental results show that our method
outperforms existing algorithms in terms of sensitivity and accuracy when
testing on 'DRIVE' and 'STARE' databases.
