TY  - CONF
AU  - Naila Murray
AU  - Maria Vanrell
AU  - Xavier Otazu
AU  - C. Alejandro Parraga
A2  - CVPR
PY  - 2011//
TI  - Saliency Estimation Using a Non-Parametric Low-Level Vision Model
BT  - IEEE conference on Computer Vision and Pattern Recognition
SP  - 433
EP  - 440
KW  - Gaussian mixture model
KW  - ad hoc parameter selection
KW  - center-surround inhibition windows
KW  - center-surround mechanism
KW  - color appearance model
KW  - convolution
KW  - eye-fixation data
KW  - human vision
KW  - innate spatial pooling mechanism
KW  - inverse wavelet transform
KW  - low-level visual front-end
KW  - nonparametric low-level vision model
KW  - saliency estimation
KW  - saliency map
KW  - scale integration
KW  - scale-weighted center-surround response
KW  - scale-weighting function
KW  - visual task
KW  - Gaussian processes
KW  - biology
KW  - biology computing
KW  - colour vision
KW  - computer vision
KW  - visual perception
KW  - wavelet transforms
N2  - 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.
SN  - 1063-6919
SN  - 978-1-4577-0394-2
UR  - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5995506
L1  - http://refbase.cvc.uab.es/files/MVO2011.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2011.5995506
N1  - CIC
ID  - Naila Murray2011
ER  -