Image Matching Using Dimensionally Reduced Embedded Earth Mover’s Distance

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="749429.fig.002a" src="https://static.hindawi.com/articles/jam/volume-2013/749429/figures/749429.fig.002a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Input images</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="749429.fig.002b" src="https://static.hindawi.com/articles/jam/volume-2013/749429/figures/749429.fig.002b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>EMD flow</td></tr></table></td></tr></table>

<table>Computation of dissimilarity between two input images in Euclidean space and their corresponding EMD flow.</table>

Journal of Applied Mathematics

fig2

Figure 2

Figure 2: Image Matching Using Dimensionally Reduced Embedded Earth Mover’s Distance 