To read this content please select one of the options below:

Automatic optical inspection system for IC solder joint based on local-to-global ensemble learning

Wenjie Chen (School of Information Engineering, Guangdong University of Technology, Guangzhou, China)
Nian Cai (School of Information Engineering, Guangdong University of Technology, Guangzhou, China)
Huiheng Wang (School of Information Engineering, Guangdong University of Technology, Guangzhou, China)
Jianfa Lin (Foshan Deeple Vision Technology Co.Ltd., Foshan, China)
Han Wang (School of Information Engineering, Guangdong University of Technology, Guangzhou, China)

Soldering & Surface Mount Technology

ISSN: 0954-0911

Article publication date: 9 July 2020

Issue publication date: 15 March 2021

173

Abstract

Purpose

Automatic optical inspection (AOI) systems have been widely used in many fields to evaluate the qualities of products at the end of the production line. The purpose of this paper is to propose a local-to-global ensemble learning method for the AOI system based on to inspect integrated circuit (IC) solder joints defects.

Design/methodology/approach

In the proposed method, the locally statistically modeling stage and the globally ensemble learning stage are involved to tackle the inspection problem. At the former stage, the improved visual background extraction–based algorithm is used for locally statistically modeling to grasp tiny appearance differences between the IC solder joints to achieve potential defect images for the subsequent stage. At the latter stage, mean unqualified probability is introduced based on a novel ensemble learning, in which an adaptive weighted strategy is proposed for revealing different contributions of the base classifier to the inspection performance.

Findings

Experimental results demonstrate that the proposed method achieves better inspection performance with an acceptable inspection time compared with some state-of-the-art methods.

Originality/value

The approach is a promising method for IC solder joint inspection, which can simultaneously grasp the local characteristics of IC solder joints and reveal inherently global relationships between IC solder joints.

Keywords

Acknowledgements

This work was in part supported by the National Natural Science Foundation of China (Nos 91648108 and 51875108), the Key Laboratory Construction Projects in Guangdong (No. 2017B030314178), the Project of Jihua Laboratory (No. X190071UZ190) the Science and Technology Program of Foshan, China (No. 1920001001367) and the Science and Technology Program of Guangzhou, China (No. 201802020010).

Citation

Chen, W., Cai, N., Wang, H., Lin, J. and Wang, H. (2021), "Automatic optical inspection system for IC solder joint based on local-to-global ensemble learning", Soldering & Surface Mount Technology, Vol. 33 No. 2, pp. 65-74. https://doi.org/10.1108/SSMT-03-2020-0011

Publisher

:

Emerald Publishing Limited

Copyright © 2020, Emerald Publishing Limited

Related articles