期刊
NEUROCOMPUTING
卷 408, 期 -, 页码 112-120出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.09.107
关键词
Defect detection; Convolutional neural network; Transfer learning; Multi-model ensemble; Generative adversarial nets(GANs)
资金
- Open Fund of State Key Laboratory of Intelligent Manufacturing System Technology, Natural Science Foundation of Shanghai [18ZR1420100]
- National Natural Science Foundation of China [61703274]
Quality management is a fundamental component of a manufacturing process. In this paper, we propose a promising learning-based approach for automatic defect detection based on small image datasets. With the help of Wasserstein generative adversarial nets (WGANs), feature-extraction-based transfer learning techniques, and multi-model ensemble framework, our approach is able to deal with imbalanced and severely rare images with defects successfully, which is practically useful to the manufacturing industry. In addition, we reduce the false negative rate (FNR) as much as possible. Extensive experiments of defect detection on decorative sheets and welding joints achieve FNR accuracy results as 0.47% and 1.9% respectively, while traditional vision methods using in the production line can only achieve FNR results at about 20% under the similar circumstance, thus substantiating the proposed approach is quite effective for surface defect detection. (c) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据