Next Article in Journal
Adaptive Leader-Follower Formation Control of Under-actuated Surface Vessels with Model Uncertainties and Input Constraints
Next Article in Special Issue
An Improved MB-LBP Defect Recognition Approach for the Surface of Steel Plates
Previous Article in Journal
Polymers and Polymer Nanocomposites for Cancer Therapy
Previous Article in Special Issue
A Bounded Scheduling Method for Adaptive Gradient Methods
Open AccessArticle

Texture Segmentation: An Objective Comparison between Five Traditional Algorithms and a Deep-Learning U-Net Architecture

Department of Electrical and Electronic Engineering, Research Centre for Biomedical Engineering, School of Mathematics, Computer Science and Engineering, City, University of London, London EC1V 0HB, UK
School of Health Sciences, Division of Language & Communication Science, Phonetics Laboratory, University of London, London EC1R 1UW, UK
Department of Linguistics CLIPS, University of Antwerp, 2000 Antwerp, Belgium
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(18), 3900;
Received: 30 July 2019 / Revised: 22 August 2019 / Accepted: 10 September 2019 / Published: 17 September 2019
(This article belongs to the Special Issue Texture and Colour in Image Analysis)
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. View Full-Text
Keywords: texture; segmentation; deep learning texture; segmentation; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Karabağ, C.; Verhoeven, J.; Miller, N.R.; Reyes-Aldasoro, C.C. Texture Segmentation: An Objective Comparison between Five Traditional Algorithms and a Deep-Learning U-Net Architecture. Appl. Sci. 2019, 9, 3900.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Search more from Scilit
Back to TopTop