Edge and Corner Detection by Photometric Quasi-Invariants

Abstract : Feature detection is used in many computer vision applications such as image segmentation, object recognition, and image retrieval. For these applications, robustness with respect to shadows, shading, and specularities is desired. Features based on derivatives of photometric invariants, which we is called full invariants, provide the desired robustness. However, because computation of photometric invariants involves nonlinear transformations, these features are unstable and, therefore, impractical for many applications. We propose a new class of derivatives which we refer to as quasi-invariants. These quasi-invariants are derivatives which share with full photometric invariants the property that they are insensitive for certain photometric edges, such as shadows or specular edges, but without the inherent instabilities of full photometric invariants. Experiments show that the quasi-invariant derivatives are less sensitive to noise and introduce less edge displacement than full invariant derivatives. Moreover, quasi-invariants significantly outperform the full invariant derivatives in terms of discriminative power.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2005, 27 (4), pp.625--630. 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1401914〉. 〈10.1109/TPAMI.2005.75〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548526
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:07
Dernière modification le : mercredi 5 janvier 2011 - 16:02:26

Identifiants

Citation

Joost Van de Weijer, Theo Gevers. Edge and Corner Detection by Photometric Quasi-Invariants. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2005, 27 (4), pp.625--630. 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1401914〉. 〈10.1109/TPAMI.2005.75〉. 〈inria-00548526〉

Partager

Métriques

Consultations de la notice

17