使ECA-DCN-Lite-BiFPN-CARAFEYOLOv5PCB

Zhenxia Wang1,2, Nurulazlina Ramli1, Tzer Hwai Gilbert Thio1

  • 1Centre for Sustainability in Advanced Electrical and Electronics Systems (CSAEES), Faculty of Engineering, Built Environment and Information Technology, SEGi University, Petaling Jaya 47810, Malaysia.

PubMed
概括

本研究介绍了一种增强的YOLOv5模型,用于印刷电路板 (PCB) 缺陷检测. 改进的探测器实现了更高的准确性和效率,特别是在有限的数据,支持智能制造.