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

Guizhong Fu, Peize Sun, Wenbin Zhu, Jiangxin Yang, Yanlong Cao, Michael Ying Yang, Yanpeng Cao*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

47 Citations (Scopus)
60 Downloads (Pure)


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.

Original languageEnglish
Pages (from-to)397-405
Number of pages9
JournalOptics and Lasers in Engineering
Early online date15 May 2019
Publication statusPublished - 1 Oct 2019


  • Convolutional neural network
  • Defect classification
  • Feature extraction
  • Multi-receptive field
  • Surface inspection


Dive into the research topics of 'A deep-learning-based approach for fast and robust steel surface defects classification'. Together they form a unique fingerprint.

Cite this