%0 Journal Article
%T Context-aware features and robust image representations
%A Pedro Martins
%A Paulo Carvalho
%A Carlo Gatta
%J Journal of Visual Communication and Image Representation
%D 2014
%V 25
%N 2
%F Pedro Martins2014
%O LAMP; 600.079;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2467), last updated on Mon, 27 Jun 2016 17:50:36 +0200
%X Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation.
%U http://refbase.cvc.uab.es/files/MCG2014.pdf
%U http://dx.doi.org/10.1016/j.jvcir.2013.10.006
%P 339-348