Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
A Learning Approach to 3D Object Representation for Classification
 

Summary: A Learning Approach to 3D Object
Representation for Classification
Indriyati Atmosukarto and Linda G. Shapiro
University of Washington,
Department of Computer Science and Engineering,Seattle, WA, USA
{indria,shapiro}@cs.washington.edu
Abstract. In this paper we describe our 3D object signature for 3D
object classification. The signature is based on a learning approach that
finds salient points on a 3D object and represent these points in a 2D
spatial map based on a longitude-latitude transformation. Experimen-
tal results show high classification rates on both pose-normalized and
rotated objects and include a study on classification accuracy as a func-
tion of number of rotations in the training set.
Key words: 3D Object Classification, 3D Object Signature
1 Introduction
Advancement in technology for digital acquisition of 3D models has led to an
increase in the number of 3D objects available in specific application databases
and across the World Wide Web. This has motivated recent research in two
major areas. The first research area is 3D object retrieval where the goal is to
retrieve 3D objects from a database that are similar in shape to a given 3D

  

Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle

 

Collections: Computer Technologies and Information Sciences