City Research Online

Abstract

<jats:p>This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Husøy were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.</jats:p>

Publication Type:	Article
Additional Information:	© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open accessarticle distributed under the terms and conditions of the Creative Commons Attribution(CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Publisher Keywords:	texture; segmentation; deep learning
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Departments:	School of Health & Psychological Sciences > Language & Communication Science School of Science & Technology > Computer Science > giCentre School of Science & Technology > Engineering
SWORD Depositor:	Symplectic Administrator

Export

Downloads