Xinrong Cao

Papers

Total Citations

H-Index

About

Xinrong Cao is a researcher specializing in computer vision and industrial automation, with a particular focus on defect detection in printed circuit boards (PCBs). Their most notable contribution is the development of an improved RetinaNet-based method for PCB defect detection, published in 2023. This work addresses critical challenges in automated quality control by enhancing the accuracy and efficiency of identifying manufacturing flaws, such as shorts, opens, and solder defects. While still early in its citation impact—with 2 citations to date—the research demonstrates a practical application of deep learning to real-world industrial problems, bridging the gap between advanced object detection algorithms and manufacturing needs. Cao's approach refines the RetinaNet architecture to better handle the small, dense, and varied defects typical in PCB inspection, offering a scalable solution for electronics production. This work positions Cao as a contributor to the growing field of AI-driven quality assurance, where their methods could reduce manual inspection costs and improve yield rates. For students and researchers in computer vision and industrial engineering, Cao’s work exemplifies how state-of-the-art neural networks can be tailored for domain-specific tasks, highlighting the potential for further innovation in automated defect detection systems.