Normalization of Active Appearance Models for  Fish Species Identification

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="103293.fig.005a" src="https://static.hindawi.com/articles/isrn/volume-2011/103293/figures/103293.fig.005a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Feature points of the Amphiprion Akindynos</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="103293.fig.005b" src="https://static.hindawi.com/articles/isrn/volume-2011/103293/figures/103293.fig.005b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>Feature points of the Acanthurus Tennenti</td></tr></table></td></tr></table>

<table>Illustration of the feature points for two different species. Computing a shape model from shape representations that have different numbers of feature points is impossible. For this reason, normalization of shapes is necessary to build an AAM from different species.</table>

International Scholarly Research Notices

fig5

Figure 5

Figure 5: Normalization of Active Appearance Models for  Fish Species Identification 