A Set of Geometric Features for Neural Network-Based Textile Defect Classification

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td align="left">Class</td><td align="center">Testing result (accuracy)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td align="left">Color yarn</td><td align="center">100%</td></tr><tr><td align="left">Vertical missing yarn</td><td align="center">100%</td></tr><tr><td align="left">Horizontal missing yarn</td><td align="center">100%</td></tr><tr><td align="left">Hole</td><td align="center">100%</td></tr><tr><td align="left">Spot</td><td align="center">94.44%</td></tr><tr><td align="left">Defect-free</td><td align="center">100%</td></tr><tr><td align="center" colspan="2"><hr/></td></tr><tr><td align="left">Total</td><td align="center">98.99%</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Defect detection performance for Experiment V.

International Scholarly Research Notices

tab3

Table 3

Table 3: A Set of Geometric Features for Neural Network-Based Textile Defect Classification 