System for PCB Defect Detection Using Visual Computing and Deep Learning for Production Optimization

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_center" colspan="2">Defect detection results</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Mean accuracy</td><td class="align_center">90.87%</td></tr><tr><td class="align_left">False alarm rate</td><td class="align_center">5.31%</td></tr><tr><td class="align_left">Analysis time</td><td class="align_center">8.57 s (1 PCB image)</td></tr><tr><td class="align_left">Training time</td><td class="align_center">About 20 hr</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

IET Circuits, Devices & Systems

tab4

Table 4

Table 4: System for PCB Defect Detection Using Visual Computing and Deep Learning for Production Optimization 