A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="654787.fig.005a" src="https://static.hindawi.com/articles/jam/volume-2014/654787/figures/654787.fig.005a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>“Normalized Vertical Transition” feature for English digits</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="654787.fig.005b" src="https://static.hindawi.com/articles/jam/volume-2014/654787/figures/654787.fig.005b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>“Aspect Ratio” feature for Arabic/Farsi digits</td></tr></table></td></tr></table>

<table>1D_MM spectrum distribution diagrams.</table>

Journal of Applied Mathematics

fig5

Figure 5

Figure 5: A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals 