Enhanced Forest Microexpression Recognition Based on Optical Flow Direction Histogram and Deep Multiview Network

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">Pose category</td><td class="align_center">Accuracy rate (%)</td><td class="align_center">STD</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">MDMO</td><td class="align_center">9</td><td class="align_center">79.49</td><td class="align_center">1.4</td></tr><tr><td class="align_left">DFER-MVAD</td><td class="align_center">9</td><td class="align_center">77.63</td><td class="align_center">0.9</td></tr><tr><td class="align_left">DiSTLBP-RIP</td><td class="align_center">9</td><td class="align_center">77.71</td><td class="align_center">1.3</td></tr><tr><td class="align_left">The proposed method</td><td class="align_center">9</td><td class="align_center">86.63</td><td class="align_center">0.7</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Performance comparison of several methods on CASME II microexpression dataset.</div>

Mathematical Problems in Engineering

tab3

Table 3

Table 3: Enhanced Forest Microexpression Recognition Based on Optical Flow Direction Histogram and Deep Multiview Network 