Segmentation-based Decision Networks for Steel Surface Defect Detection

Zhongqin Bi,
Qiancong Wu,
Meijing Shan,
Wei Zhong,


With the advent of the Industrial 4.0 era, deep learning has been continuously applied to the task of surface defect detection, and effective progress has been made. However, the limited number of training samples and high labelling costs are considerable obstacles to the vigorous development of this task. Thus, we explore the use of different numbers of labels with various accuracies during training to achieve the maximum detection accuracy with the lowest cost. Our proposed method includes improved segmentation and decision networks. An attention mechanism is integrated into the segmentation subnetwork. Moreover, atrous convolutions are used in the segmentation and decision subnetworks. In addition, the original loss function is improved. Several experiments are carried out on the Severstal Steel Defect dataset collected in Germany, and the results show that each component improves the detection accuracy by 1% to 2%. Finally, when we add an appropriate number of pixel-level labels in the weakly supervised learning mode, the detection accuracy reaches that of the fully supervised mode with a significantly reduced annotation cost.


Quality control, Deep-learning Industrial 4.0, Surface defect detection

Citation Format:
Zhongqin Bi, Qiancong Wu, Meijing Shan, Wei Zhong, "Segmentation-based Decision Networks for Steel Surface Defect Detection," Journal of Internet Technology, vol. 23, no. 6 , pp. 1405-1416, Nov. 2022.

Full Text:



  • There are currently no refbacks.

Published by Executive Committee, Taiwan Academic Network, Ministry of Education, Taipei, Taiwan, R.O.C
JIT Editorial Office, Office of Library and Information Services, National Dong Hwa University
No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 974301, Taiwan, R.O.C.
Tel: +886-3-931-7314  E-mail: