Blood Vessel Extraction in Color Retinal Fundus Images with Enhancement Filtering and Unsupervised Classification

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/jhe/volume-2017/4897258/figures/4897258.fig.003a.svgz" name="4897258.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Original retinal fundus image from STARE</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/jhe/volume-2017/4897258/figures/4897258.fig.003b.svgz" name="4897258.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>The mask image of (a) labelled by hand</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/jhe/volume-2017/4897258/figures/4897258.fig.003c.svgz" name="4897258.fig.003c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>The mask image obtained with basic thresholding. The accuracy is 98.48%</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/jhe/volume-2017/4897258/figures/4897258.fig.003d.svgz" name="4897258.fig.003d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>The mask image obtained with proposed method. The accuracy is 99.21%</td></tr></table>

<div>An example of retinal region selection operation.</div>

Journal of Healthcare Engineering

fig3

Figure 3

Figure 3: Blood Vessel Extraction in Color Retinal Fundus Images with Enhancement Filtering and Unsupervised Classification 