Une nouvelle mesure de complexité pour les images basée sur l'attention visuelle

Abstract : Digital images can be analyzed at wide range of levels going from pixel arrangement to semantics. As a consequence, finding a visual complexity estimator is a difficult task. In this article we propose a definition of attention based perceptual complexity. We study the performance of human eye movements and of different models of computational attention against a ground-truth of image complexity based on the observation time of an image description task. The results obtained show that besides it's lack of semantic processing, attentional behavior is a good estimator of image complexity.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00695751
Contributor : Matthieu Perreira da Silva <>
Submitted on : Wednesday, May 9, 2012 - 5:19:11 PM
Last modification on : Wednesday, September 11, 2019 - 11:00:13 AM
Long-term archiving on : Friday, August 10, 2012 - 2:27:29 AM

File

Article_GRETSI.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00695751, version 1

Citation

Matthieu Perreira da Silva, Vincent Courboulay. Une nouvelle mesure de complexité pour les images basée sur l'attention visuelle. XXIIIème coloque GRETSI - Bordeaux, Sep 2011, Bordeaux, France. pp.ID40. ⟨hal-00695751⟩

Share

Metrics

Record views

368

Files downloads

494