Feature Selection for Enhanced Spectral Shape Comparison

Simple item page
dc.contributor.authorMarini, Simoneen_US
dc.contributor.authorPatané, Giuseppeen_US
dc.contributor.authorSpagnuolo, Michelaen_US
dc.contributor.authorFalcidieno, Biancaen_US
dc.contributor.editorMohamed Daoudi and Tobias Schrecken_US
dc.date.accessioned2013-10-21T16:10:01Z
dc.date.available2013-10-21T16:10:01Z
dc.date.issued2010en_US
dc.description.abstractIn the context of shape matching, this paper proposes a framework for selecting the Laplacian eigenvalues of 3D shapes that are more relevant for shape comparison and classification. Three approaches are compared to identify a specific set of eigenvalues such that they maximise the retrieval and/or the classification performance on the input benchmark data set: the first k eigenvalues, by varying k over the cardinality of the spectrum; the Hill Climbing technique; and the AdaBoost algorithm. In this way, we demonstrate that the information coded by the whole spectrum is unnecessary and we improve the shape matching results using only a set of selected eigenvalues. Finally, we test the efficacy of the selected eigenvalues by coupling shape classification and retrieval.en_US
dc.description.seriesinformationEurographics Workshop on 3D Object Retrievalen_US
dc.identifier.isbn978-3-905674-22-4en_US
dc.identifier.issn1997-0471en_US
dc.identifier.urihttps://doi.org/10.2312/3DOR/3DOR10/031-038en_US
dc.publisherThe Eurographics Associationen_US
dc.titleFeature Selection for Enhanced Spectral Shape Comparisonen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
031-038.pdf
Size:
1.56 MB
Format:
Adobe Portable Document Format
Download
Collections
3DOR 10