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

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, mu...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2019-09, Vol.9 (18), p.3900
Main Authors: Karabağ, Cefa, Verhoeven, Jo, Miller, Naomi Rachel, Reyes-Aldasoro, Constantino Carlos
Format: Article
Language:English
Subjects:
Algorithms
Basins
Deep learning
Filtration
Segmentation
Texture
Watersheds
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2076-3417
2076-3417
DOI:10.3390/app9183900