The University of Southampton
University of Southampton Institutional Repository

Semantics of texture

Semantics of texture
Semantics of texture
In this thesis we investigate means by which the semantic and visual spaces of texture may be tied together, and argue for the importance of explicit semantic modelling inhuman-centred texture analysis tasks such as retrieval, annotation, synthesis, and zeroshot learning.

We take a new approach to semantic texture labelling by adopting a pairwise comparison framework robust to human biases, and within a semantic space consisting of attributes,low-level visual features acting as building blocks for more expressive semantic ontologies. We crowdsource a dataset of approximately 140;000 pairwise comparisons across 319 classes of texture and 98 attributes | to our knowledge the largest of its kind.

To aid in learning from sparsely labelled pairwise comparison datasets such as this we derive a new Bayesian probabilistic approach, providing a natural framework in which to incorporate prior knowledge and to measure uncertainty, and outperforming the often used Ranking SVM on incomplete and unreliable data. We demonstrate how the error variance present in our pairwise comparison data may be precisely quantified, allowing us to identify and discard rogue responses in a principled way.

Existing texture descriptors are then assessed in terms of their correspondence to the attributes comprising the semantic space. Textures with strong presence of attributes connoting randomness and complexity are shown to be poorly modelled by existing descriptors. These effects are likely due to disparities between human perception of what texture entails, and definitions adopted prior to (or, sometimes, after) the design of computational texture analysis systems.

Despite the decifiencies of the visual descriptors they are based upon, we demonstrate the benefit of semantically enriched descriptors in a retrieval experiment. Semantic modelling of texture is shown to provide considerable value in both feature selection and in analysis tasks.
University of Southampton
Matthews, Tim
f41aa009-4f12-4887-8427-50d344d5d9b3
Matthews, Tim
f41aa009-4f12-4887-8427-50d344d5d9b3
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12

Matthews, Tim (2016) Semantics of texture. University of Southampton, Doctoral Thesis, 103pp.

Record type: Thesis (Doctoral)

Abstract

In this thesis we investigate means by which the semantic and visual spaces of texture may be tied together, and argue for the importance of explicit semantic modelling inhuman-centred texture analysis tasks such as retrieval, annotation, synthesis, and zeroshot learning.

We take a new approach to semantic texture labelling by adopting a pairwise comparison framework robust to human biases, and within a semantic space consisting of attributes,low-level visual features acting as building blocks for more expressive semantic ontologies. We crowdsource a dataset of approximately 140;000 pairwise comparisons across 319 classes of texture and 98 attributes | to our knowledge the largest of its kind.

To aid in learning from sparsely labelled pairwise comparison datasets such as this we derive a new Bayesian probabilistic approach, providing a natural framework in which to incorporate prior knowledge and to measure uncertainty, and outperforming the often used Ranking SVM on incomplete and unreliable data. We demonstrate how the error variance present in our pairwise comparison data may be precisely quantified, allowing us to identify and discard rogue responses in a principled way.

Existing texture descriptors are then assessed in terms of their correspondence to the attributes comprising the semantic space. Textures with strong presence of attributes connoting randomness and complexity are shown to be poorly modelled by existing descriptors. These effects are likely due to disparities between human perception of what texture entails, and definitions adopted prior to (or, sometimes, after) the design of computational texture analysis systems.

Despite the decifiencies of the visual descriptors they are based upon, we demonstrate the benefit of semantically enriched descriptors in a retrieval experiment. Semantic modelling of texture is shown to provide considerable value in both feature selection and in analysis tasks.

Text
thesis_tim_matthews_jul_161 - Version of Record
Available under License University of Southampton Thesis Licence.
Download (5MB)

More information

Published date: July 2016

Identifiers

Local EPrints ID: 418003
URI: http://eprints.soton.ac.uk/id/eprint/418003
PURE UUID: 9e77a2f6-9dc4-42e6-973a-94a9248c90cb
ORCID for Mark Nixon: ORCID iD orcid.org/0000-0002-9174-5934

Catalogue record

Date deposited: 20 Feb 2018 17:30
Last modified: 14 Mar 2019 01:56

Export record

Contributors

Author: Tim Matthews
Thesis advisor: Mark Nixon ORCID iD

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×