Feature Selection for Enhanced Spectral Shape Comparison

Marini, Simone; Patané, Giuseppe; Spagnuolo, Michela; Falcidieno, Bianca

Feature Selection for Enhanced Spectral Shape Comparison

Files

031-038.pdf (1.56 MB)

Date

2010

Authors

Marini, Simone
Patané, Giuseppe
Spagnuolo, Michela
Falcidieno, Bianca

Publisher

The Eurographics Association

Abstract

In 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.

        @inproceedings{:10.2312/3DOR/3DOR10/031-038
,
booktitle = {Eurographics Workshop on 3D Object Retrieval
},
editor = {Mohamed Daoudi and Tobias Schreck
},
title = {{Feature Selection for Enhanced Spectral Shape Comparison
}},
author = {Marini, Simone and 
Patané, Giuseppe and 
Spagnuolo, Michela and 
Falcidieno, Bianca
},
year = {2010
},
publisher = {The Eurographics Association
},
ISSN = {1997-0471
},
ISBN = {978-3-905674-22-4
},
DOI = {/10.2312/3DOR/3DOR10/031-038
}
}