Visual and Textual Analysis for Image Trustworthiness Assessment within Online News

<table class="fixed-width table-group" id="tab3"><tr><td><table class="table"><colgroup><col style="width:10.74em"/><col style="width:4.77em"/><col style="width:6.12em"/><col style="width:3.43em"/></colgroup><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left"> </td><td class="align_center"> Classical </td><td class="align_center"> Splicebuster </td><td class="align_center"> CNN </td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Image Forensics</td><td class="align_center"> 64%</td><td class="align_center"> 65%</td><td class="align_center"> 66%</td></tr><tr><td class="align_left">Textual Analysis</td><td class="align_center"> 73%</td><td class="align_center"> 73%</td><td class="align_center"> 73%</td></tr><tr><td class="align_left">Combination 40%-60%</td><td class="align_center"> 74%</td><td class="align_center"> 74%</td><td class="align_center"> 73%</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Results obtained on <i>MediaEval2016</i> for Random Forest Classifier for FS3.</div>

Security and Communication Networks

tab3

Table 3

Table 3: Visual and Textual Analysis for Image Trustworthiness Assessment within Online News 