A Robust Residual Shrinkage Balanced Network for Image Recognition from Japanese Historical Documents

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static-preview.hindawi.com/articles/js/volume-2023/8316638/figures/8316638.fig.008a.svgz" name="8316638.fig.008a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Raw data</td></tr><tr class="fig-image" id="b"><td><object data="https://static-preview.hindawi.com/articles/js/volume-2023/8316638/figures/8316638.fig.008b.svgz" name="8316638.fig.008b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Extracted hierachical features</td></tr></table>

<div>The visualization results of the raw data and the high-level features.</div>

Journal of Sensors

fig8

Figure 8

Figure 8: A Robust Residual Shrinkage Balanced Network for Image Recognition from Japanese Historical Documents 