ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection

Damacharla, P and Achuth Rao, MV and Ringenberg, J and Javaid, AY (2021) TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection. In: 2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021, 19-21 May 2021, Halden.

[img] PDF
ICAPAI _2021.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
Official URL: https://doi.org/10.1109/ICAPAI49758.2021.9462060

Abstract

Visual steel surface defect detection is an essential step in steel sheet manufacturing. Several machine learning-based automated visual inspection (AVI) methods have been studied in recent years. However, most steel manufacturing industries still use manual visual inspection due to training time and inaccuracies involved with AVI methods. Automatic steel defect detection methods could be useful in less expensive and faster quality control and feedback. But preparing the annotated training data for segmentation and classification could be a costly process. In this work, we propose to use the Transfer Learning-based U-Net (TLU-Net) framework for steel surface defect detection. We use a U-Net architecture as the base and explore two kinds of encoders: ResNet and DenseNet. We compare these nets' performance using random initialization and the pre-trained networks trained using the ImageNet data set. The experiments are performed using Severstal data. The results demonstrate that the transfer learning performs 5 (absolute) better than that of the random initialization in defect classification. We found that the transfer learning performs 26 (relative) better than that of the random initialization in defect segmentation. We also found the gain of transfer learning increases as the training data decreases, and the convergence rate with transfer learning is better than that of the random initialization. © 2021 IEEE.

Item Type: Conference Paper
Publication: 2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords: Classification (of information); Defects; Manufacture; Surface defects; Transfer learning, Annotated training data; Automated visual inspection; Convergence rates; Defect classification; Learning approach; NET architecture; Steel manufacturing; Visual inspection, Deep learning
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 03 Dec 2021 06:47
Last Modified: 03 Dec 2021 06:47
URI: http://eprints.iisc.ac.in/id/eprint/70095

Actions (login required)

View Item View Item