Low-level spatiochromatic grouping for saliency estimation
Murray, Naila (Xerox Research Centre Europe (France))
Vanrell i Martorell, Maria Isabel (Centre de Visió per Computador (Bellaterra, Catalunya))
Otazu Porter, Xavier (Centre de Visió per Computador (Bellaterra, Catalunya))
Parraga, Carlos Alejandro (Centre de Visió per Computador (Bellaterra, Catalunya))

Date:	2013
Abstract:	We propose a saliency model termed SIM (saliency by induction mechanisms), which is based on a low-level spatiochromatic model that has successfully predicted chromatic induction phenomena. In so doing, we hypothesize that the low-level visual mechanisms that enhance or suppress image detail are also responsible for making some image regions more salient. Moreover, SIM adds geometrical grouplets to enhance complex low-level features such as corners, and suppress relatively simpler features such as edges. Since our model has been fitted on psychophysical chromatic induction data, it is largely nonparametric. SIM outperforms state-of-the-art methods in predicting eye fixations on two datasets and using two metrics.
Grants:	Ministerio de Ciencia e Innovación TIN2010-21771-C02-1 Ministerio de Educación y Ciencia CSD2007-00018 Ministerio de Educación y Ciencia RYC-2007-00484
Rights:	Tots els drets reservats.
Language:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Subject:	Computational models of vision ; Color ; Hierarchical image representation
Published in:	IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 11 (November 2013) , p. 2810-2816, ISSN 0162-8828

DOI: 10.1109/TPAMI.2013.108

Postprint 10 p, 3.7 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles