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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-03767-2_32 | CAIP |
Keywords | Field | DocType |
principal components analysis,bottom-up saliency,new model,multiscale low level feature,open access image dataset,human fixation,local responses,biologically plausible mechanism,t2 statistic,local response,contextual prior,bottom up,top down processing,principal component analysis | Fixation (psychology),Decorrelation,Salience (neuroscience),Computer science,Artificial intelligence,Optimal distinctiveness theory,Computer vision,Pattern recognition,Statistic,Top-down and bottom-up design,Prior probability,Machine learning,Principal component analysis | Conference |
Volume | ISSN | Citations |
5702 | 0302-9743 | 4 |
PageRank | References | Authors |
0.54 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Antón Garcia-Diaz | 1 | 131 | 6.78 |
Xosé R. Fdez-Vidal | 2 | 93 | 5.87 |
Xose Manuel Pardo | 3 | 126 | 13.25 |
Raquel Dosil | 4 | 145 | 10.37 |