Improved YOLOv5 with BiFPN on PCB Defect Detection

Abstract

As an image classification technology, target detection also needs to identify specific locations of predefined categories. Therefore, target detection is not only to solve the problem of recognizing what objects exactly, but also points out locations. The development of YOLO series has greatly improved speed and accuracy in target detection technology. However, it performs not so good as detecting normal objects when targets are quite small. Thus, this paper proposes to fuse BIFPN network and set smaller and denser anchors to improve this, and then public PCB defect detection data set is used to test and verify effect of refined method. Experimental results show that improved method shifts [email protected] from 0.968 to 0.979 and [email protected]:0.95 from 0.494 to 0.501, as well as deducts confusion rate. With the improved method, the training cost also decrases significantly.