000002235 001__ 2235
000002235 005__ 20181109203536.0
000002235 022__ $$a1057-7149
000002235 0247_ $$2DOI$$a10.1109/TIP.2017.2655438
000002235 037__ $$aARTICLE
000002235 041__ $$aeng
000002235 245__ $$aSteerable wavelet machines (SWM) :$$blearning moving frames
000002235 260__ $$c2017
000002235 269__ $$a2017-04
000002235 300__ $$a11 p.
000002235 506__ $$avisible
000002235 520__ $$9eng$$aWe present texture operators encoding class-specific local organizations of image directions (LOIDs) in a rotation-invariant fashion. The LOIDs are key for visual understanding, and are at the origin of the success of the popular approaches, such as local binary patterns (LBPs) and the scale-invariant feature transform (SIFT). Whereas, LBPs and SIFT yield hand-crafted image representations, we propose to learn data-specific representations of the LOIDs in a rotation-invariant fashion. The image operators are based on steerable circular harmonic wavelets (CHWs), offering a rich and yet compact initial representation for characterizing natural textures. The joint location and orientation required to encode the LOIDs is preserved by using moving frames (MFs) texture representations built from locally-steered image gradients that are invariant to rigid motions. In a second step, we use support vector machines to learn a multi-class shaping matrix for the initial CHW representation, yielding data-driven MFs called steerable wavelet machines (SWMs). The SWM forward function is composed of linear operations (i.e., convolution and weighted combinations) interleaved with non-linear steermax operations. We experimentally demonstrate the effectiveness of the proposed operators for classifying natural textures. Our scheme outperforms recent approaches on several test suites of the Outex and the CUReT databases.
000002235 540__ $$aLa publication respecte les règles concernant l’utilisation du nom HES-SO
000002235 546__ $$aEnglish
000002235 592__ $$aHEG VS HES-SO Valais-Wallis - Haute Ecole de Gestion & Tourisme
000002235 592__ $$bInstitut Informatique de gestion
000002235 592__ $$cEconomie et Services
000002235 65017 $$aEconomie/gestion
000002235 6531_ $$9eng$$awavelet transforms
000002235 6531_ $$9eng$$aorganizations
000002235 6531_ $$9eng$$aharmonic analysis
000002235 6531_ $$9eng$$asupport vector machines
000002235 6531_ $$9eng$$aencoding
000002235 6531_ $$9eng$$aconvolution
000002235 655__ $$ascientifique
000002235 700__ $$aDepeursinge, Adrien$$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland
000002235 700__ $$aPüspöki, Zsuzsanna$$uBiomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland
000002235 700__ $$aWard, John Paul$$uBiomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland ; Department of Mathematics, University of North Carolina, USA
000002235 700__ $$aUnser, Michael$$uBiomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Switzerland
000002235 773__ $$gApril 2017, vol. 26, issue 4, pp. 1626-1636$$tIEEE transactions on image processing
000002235 8564_ $$s6151409$$uhttp://hesso.tind.io/record/2235/files/Depeursinge_2017_steerable_wavelet_machines.pdf
000002235 8564_ $$s3717443$$uhttp://hesso.tind.io/record/2235/files/Depeursinge_2017_steerable_wavelet_machines.pdf?subformat=pdfa$$xpdfa
000002235 906__ $$aGREEN
000002235 909CO $$ooai:hesso.tind.io:2235$$pDoc_type_Articles$$pHEG_ALL$$pGLOBAL_SET$$qEcole_hôtelière_de_Lausanne:Economie/gestion$$qHEG-GE:scientifique$$qDoc_type_Conferences$$qDoc_type_Rapport$$qHEG-GE:public_conference$$qDoc_type_Livres$$qDoc_type_Theses$$qDoc_type_Media$$qHEG-GE:professionnel$$qDoc_type_Chapitre_livre$$qDoc_type_Preprint$$qHEIG-VD:Economie/gestion$$qHEG-FR:Economie/gestion$$qHEG-Arc:Economie/gestion$$qHES-SO_Valais-Wallis:Economie/gestion$$qHEG-GE:Economie/gestion:Conferences$$qHEGGE_professionnels
000002235 950__ $$aI2
000002235 980__ $$ascientifique