Saliency estimation using a non-parametric low-level vision model
Murray, Naila (Centre de Visió per Computador (Bellaterra, Catalunya))
Vanrell i Martorell, Maria Isabel (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Otazu Porter, Xavier (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Parraga, Carlos Alejandro (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Publicación:	Colorado Springs : IEEE, 2011
Descripción:	8 pàg.
Resumen:	Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. However, integrating spatial information and justifying the choice of various parameter values remain open problems. In this paper we show that an efficient model of color appearance in human vision, which contains a principled selection of parameters as well as an innate spatial pooling mechanism, can be generalized to obtain a saliency model that outperforms state-of-the-art models. Scale integration is achieved by an inverse wavelet transform over the set of scale-weighted center-surround responses. The scale-weighting function (termed ECSF) has been optimized to better replicate psychophysical data on color appearance, and the appropriate sizes of the center-surround inhibition windows have been determined by training a Gaussian Mixture Model on eye-fixation data, thus avoiding ad-hoc parameter selection. Additionally, we conclude that the extension of a color appearance model to saliency estimation adds to the evidence for a common low-level visual front-end for different visual tasks.
Ayudas:	Ministerio de Ciencia e Innovación TIN2010-21771-C02-1 Ministerio de Educación y Ciencia 2010-CSD2007-00018 Ministerio de Educación y Ciencia RYC-2007-00484
Derechos:	Tots els drets reservats.
Lengua:	Anglès
Documento:	Capítol de llibre ; recerca ; Versió acceptada per publicar
Materia:	Image color analysis ; Computational modeling ; Wavelet transforms ; Predictive models ; Visualization ; Brightness
Publicado en:	IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2011, p. 433-440, ISBN 9781457703942

DOI: 10.1109/CVPR.2011.5995506

Postprint 9 p, 800.2 KB

El registro aparece en las colecciones:
Libros y colecciones > Capítulos de libros