Automatic detection and classification of manufacturing defects in metal boxes using deep neural networks

Essid, O., Laga, H.ORCID: 0000-0002-4758-7510 and Samir, C. (2018) Automatic detection and classification of manufacturing defects in metal boxes using deep neural networks. PLoS ONE, 13 (11). e0203192.

Abstract

This paper develops a new machine vision framework for efficient detection and classification of manufacturing defects in metal boxes. Previous techniques, which are based on either visual inspection or on hand-crafted features, are both inaccurate and time consuming. In this paper, we show that by using autoencoder deep neural network (DNN) architecture, we are able to not only classify manufacturing defects, but also localize them with high accuracy. Compared to traditional techniques, DNNs are able to learn, in a supervised manner, the visual features that achieve the best performance. Our experiments on a database of real images demonstrate that our approach overcomes the state-of-the-art while remaining computationally competitive.

Item Type:	Journal Article
Murdoch Affiliation(s):	School of Engineering and Information Technology
Publisher:	Public Library of Science
Copyright:	© 2018 Essid et al.
URI:	http://researchrepository.murdoch.edu.au/id/eprint/42651

Item Control Page

Downloads