oru.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Texture features for object salience
School of Computer Science, University of St Andrews, Scotland, United Kingdom; Department of Electronic Engineering and Computer Science, University of the Algarve, Portugal.
Örebro University, School of Science and Technology. Department of Electronic Engineering and Computer Science, University of the Algarve, Portugal. (Centre for Applied Autonomous Sensor Systems)
Department of Electronic Engineering and Computer Science, University of the Algarve, Portugal.
2017 (English)In: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 67, p. 43-51Article in journal (Refereed) Published
Abstract [en]

Although texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset.

Place, publisher, year, edition, pages
Elsevier, 2017. Vol. 67, p. 43-51
Keywords [en]
Texture, Colour, Salience, Attention, Benchmark
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-62841DOI: 10.1016/j.imavis.2017.09.007ISI: 000414883800004Scopus ID: 2-s2.0-85030120053OAI: oai:DiVA.org:oru-62841DiVA, id: diva2:1160536
Note

Funding Agencies:

EU  ICT-2009.2.1-270247 

FCT  LarSYS UlD/EEA/50009/2013  EXPL/EEI-SII/1982/2013 

Available from: 2017-11-27 Created: 2017-11-27 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Krishna, Sai

Search in DiVA

By author/editor
Krishna, Sai
By organisation
School of Science and Technology
In the same journal
Image and Vision Computing
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 66 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf