Charge Density-Based 3D Model Retrieval Using Bag-of-Feature

Alizadeh, Fattah; Sutherland, Alistair

Charge Density-Based 3D Model Retrieval Using Bag-of-Feature

Files

097-100.pdf (366.9 KB)

Date

2013

Authors

Alizadeh, Fattah
Sutherland, Alistair

Publisher

The Eurographics Association

Abstract

As the number of 3D models is growing on the internet and other domain-specific datasets, the search and retrieval of such models are attracting a lot of attention. A shape descriptor it plays critical roles in the retrieval quality enhancement. In this paper we propose a new robust shape descriptor based on the distribution of charge density on the surface of a 3D model. After calculating the charge density for each triangular face of each model as local features, we utilize the Bag-of-Features framework to perform global matching using the local features. Our experiments on the McGill and PSB datasets show that the proposed descriptor is robust to a variety of modifications and transformations and offers a higher retrieving quality compared to other well-known approaches.

        @inproceedings{:10.2312/3DOR/3DOR13/097-100
,
booktitle = {Eurographics Workshop on 3D Object Retrieval
},
editor = {Umberto Castellani and Tobias Schreck and Silvia Biasotti and Ioannis Pratikakis and Afzal Godil and Remco Veltkamp
},
title = {{Charge Density-Based 3D Model Retrieval Using Bag-of-Feature
}},
author = {Alizadeh, Fattah and 
Sutherland, Alistair
},
year = {2013
},
publisher = {The Eurographics Association
},
ISSN = {1997-0463
},
ISBN = {978-3-905674-44-6
},
DOI = {/10.2312/3DOR/3DOR13/097-100
}
}