Accurate image registration method for PCB defects detection

The Journal of Engineering

Guoliang Hua¹  Hong Liu²  Weipeng Huang³ 

[1] College of Electronic Information and Optical Engineering, Nankai University , Tianjin , People'Key Laboratory of Machine Perception , Peking University, Shenzhen Graduate School , Shenzhen , People's Republic of China

关键词: automatic optical inspection system;    computer vision system;    first-registered image;    PCB defects detection;    lower root-mean-square error;    printed circuit board defects;    accurate image registration method;    PCB defect detection;    feature detector;    reference image;    robust feature descriptor;   

DOI  :  10.1049/joe.2018.8272

学科分类：工程和技术（综合）

来源: IET

【 摘 要 】

Image registration technology has been widely used in many parts of the computer vision system such as the automatic optical inspection system which is used to detect the printed circuit board (PCB) defects. The accuracy of the image registration will deeply influence the system's performance, so this study proposed an accurate image registration algorithm and applied it to the PCB defect detection. Good features to track feature detector and speeded up robust feature descriptor are combined to extract efficient features to achieve the first accurate image registration. Afterwards, cross-correlation functions were used to compute the shift between the reference image and the first-registered image for further accurate registration. Experimental results show that the authors’ algorithm performs a much better registration, with a lower root-mean-square error value between the reference image and transformed image. What is more, they applied it to detect the defects of PCB with a high accuracy.

【 授权许可】

CC BY