Steerable wavelet machines (SWM) : learning moving frames

Depeursinge, Adrien (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland) ; Püspöki, Zsuzsanna (Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland) ; Ward, John Paul (Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland ; Department of Mathematics, University of North Carolina, USA) ; Unser, Michael (Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland)

We present texture operators encoding class-specific local organizations of image directions (LOIDs) in a rotation-invariant fashion. The LOIDs are key for visual understanding, and are at the origin of the success of the popular approaches, such as local binary patterns (LBPs) and the scale-invariant feature transform (SIFT). Whereas, LBPs and SIFT yield hand-crafted image representations, we propose to learn data-specific representations of the LOIDs in a rotation-invariant fashion. The image operators are based on steerable circular harmonic wavelets (CHWs), offering a rich and yet compact initial representation for characterizing natural textures. The joint location and orientation required to encode the LOIDs is preserved by using moving frames (MFs) texture representations built from locally-steered image gradients that are invariant to rigid motions. In a second step, we use support vector machines to learn a multi-class shaping matrix for the initial CHW representation, yielding data-driven MFs called steerable wavelet machines (SWMs). The SWM forward function is composed of linear operations (i.e., convolution and weighted combinations) interleaved with non-linear steermax operations. We experimentally demonstrate the effectiveness of the proposed operators for classifying natural textures. Our scheme outperforms recent approaches on several test suites of the Outex and the CUReT databases.


Mots-clés:
Type d'article:
scientifique
Faculté:
Economie et Services
Ecole:
HEG-VS
Institut:
Institut Informatique de gestion
Classification:
Economie/gestion
Date:
2017
Pagination:
11 p.
Publié dans
IEEE transactions on image processing
Numérotation (vol. no.):
April 2017, vol. 26, issue 4, pp. 1626-1636
DOI:
ISSN:
1057-7149
Le document apparaît dans:



 Notice créée le 2017-11-19, modifiée le 2018-12-11

Fichiers:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)