Per accedir als documents amb el text complet, si us plau, seguiu el següent enllaç: http://hdl.handle.net/2117/15198

Títol:	Deformation and illumination invariant feature point descriptor
Autor/a:	Moreno-Noguer, Francesc
Altres autors:	Institut de Robòtica i Informàtica Industrial; Universitat Politècnica de Catalunya. VIS - Visió Artificial i Sistemes Intel.ligents
Abstract:	Recent advances in 3D shape recognition have shown that kernels based on diffusion geometry can be effectively used to describe local features of deforming surfaces. In this paper, we introduce a new framework that allows using these kernels on 2D local patches, yielding a novel feature point descriptor that is both invariant to non-rigid image deformations and illumination changes. In order to build the descriptor, 2D image patches are embedded as 3D surfaces, by multiplying the intensity level by an arbitrarily large and constant weight that favors anisotropic diffusion and retains the gradient magnitude information. Patches are then described in terms of a heat kernel signature, which is made invariant to intensity changes, rotation and scaling. The resulting feature point descriptor is proven to be significantly more discriminative than state of the art ones, even those which are specifically designed for describing non-rigid image deformations.
Matèries:	-Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes -Pattern recognition systems -Reconeixement de formes (Informàtica) / Imatges -- Processament -Classificació INSPEC::Pattern recognition
Drets:	Attribution-NonCommercial-NoDerivs 3.0 Spain http://creativecommons.org/licenses/by-nc-nd/3.0/es/
Tipus de document:	Article - Versió presentada Objecte de conferència
Compartir:

Mostra el registre complet del document