A deep-learning-based approach for fast and robust steel surface defects classification

• Published in: Optics and lasers in engineering Vol. 121; pp. 397 - 405
• Main Authors: Fu, Guizhong, Sun, Peize, Zhu, Wenbin, Yang, Jiangxin, Cao, Yanlong, Yang, Michael Ying, Cao, Yanpeng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2019
• Subjects: Convolutional neural network; Defect classification; Feature extraction; Multi-receptive field; Surface inspection; Defect classification; Feature extraction; Multi-receptive field; Surface inspection; Convolutional neural network
• ISSN: 0143-8166; 1873-0302
• DOI: 10.1016/j.optlaseng.2019.05.005

•A novel end-to-end SqueezeNet-based model is proposed to achieve accurate recognition of steel surface defects.•Two effective techniques are presented to improve defect recognition accuracy of our proposed CNN model.•A diversity-enhanced testing dataset of steel surface defects is constructed to evaluate the robustness of classification models.•Our method runs in real-time and achieves significantly higher classification accuracy compared with the state-of-the-art defect classifiers. Automatic visual recognition of steel surface defects provides critical functionality to facilitate quality control of steel strip production. In this paper, we present a compact yet effective convolutional neural network (CNN) model, which emphasizes the training of low-level features and incorporates multiple receptive fields, to achieve fast and accurate steel surface defect classification. Our proposed method adopts the pre-trained SqueezeNet as the backbone architecture. It only requires a small amount of defect-specific training samples to achieve high-accuracy recognition on a diversity-enhanced testing dataset of steel surface defects which contains severe non-uniform illumination, camera noise, and motion blur. Moreover, our proposed light-weight CNN model can meet the requirement of real-time online inspection, running over 100 fps on a computer equipped with a single NVIDIA TITAN X Graphics Processing Unit (12G memory). Codes and a diversity-enhanced testing dataset will be made publicly available.