Saliency Based on Decorrelation and Distinctiveness of Local Responses

  • Authors:

  • Antón Garcia-Diaz;Xosé R. Fdez-Vidal;Xosé M. Pardo;Raquel Dosil

  • Affiliations:

  • Departamento de Electrónica e Computación, Universidade de Santiago de Compostela, Grupo de Visión Artificial, Santiago de Compostela, Spain 15782;Departamento de Electrónica e Computación, Universidade de Santiago de Compostela, Grupo de Visión Artificial, Santiago de Compostela, Spain 15782;Departamento de Electrónica e Computación, Universidade de Santiago de Compostela, Grupo de Visión Artificial, Santiago de Compostela, Spain 15782;Departamento de Electrónica e Computación, Universidade de Santiago de Compostela, Grupo de Visión Artificial, Santiago de Compostela, Spain 15782

  • Venue:
  • CAIP '09 Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we validate a new model of bottom-up saliency based in the decorrelation and the distinctiveness of local responses. The model is simple and light, and is based on biologically plausible mechanisms. Decorrelation is achieved by applying principal components analysis over a set of multiscale low level features. Distinctiveness is measured using the Hotelling's T2 statistic. The presented approach provides a suitable framework for the incorporation of top-down processes like contextual priors, but also learning and recognition. We show its capability of reproducing human fixations on an open access image dataset and we compare it with other recently proposed models of the state of the art.