The SMT Solder Joint Quality Inspection Based on Image Surface Visual Restoration
- DOI
- 10.2991/mbdasm-19.2019.27How to use a DOI?
- Keywords
- SMT solder joint; illumination model; shape from shading; three-dimensional quality information
- Abstract
The emergence of surface mount technology (SMT) has created new challenges. The most challenging is the need for more capable system to monitor the product quality. Currently, the most popular method is based on machine vision for automated optical inspection (AOI). But they generally only work in 2D testing mode, cannot make a more objective assessment for solder joints. This paper describes a three-dimensional (3D) inspection system based on recovery of the surface of solder joints. Contents include four parts: combinate wavelet packet image denoising, and different filtering methods, the mixed denoising method of SMT solder joint image is studied; the 3D illumination model suitable for SMT solder joint reconstruction is presented; based on SFS technology, the 3D reconstruction technology of solder joint was studied; the 3D solid model and morphological parameters of solder joint were obtained. This paper resolved the problem of SMT solder joint 3D quality information automatic extraction. The results can provide 3D quality information for SMT solder joint quality comparison, analysis and intelligence discrimination of solder joint quality.
- Copyright
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Nan Yu AU - Jing Zhang PY - 2019/10 DA - 2019/10 TI - The SMT Solder Joint Quality Inspection Based on Image Surface Visual Restoration BT - Proceedings of the 2019 International Conference on Mathematics, Big Data Analysis and Simulation and Modelling (MBDASM 2019) PB - Atlantis Press SP - 119 EP - 122 SN - 2352-538X UR - https://doi.org/10.2991/mbdasm-19.2019.27 DO - 10.2991/mbdasm-19.2019.27 ID - Yu2019/10 ER -