By Topic

3D object recognition using perceptual components

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Xiuwen Liu ; Dept. of Comput. Sci., Florida State Univ., Tallahassee, FL, USA ; Srivastava, A.

We propose a representation for appearance-based 3D object recognition. Each 3D object is represented by the spectral histogram of 2D images at different conditions. The spectral histogram encodes implicitly all the images that are perceptually similar and thus each spectral histogram is called a perceptual component. Given a novel 2D image, the perceptual components of objects are used to determine if the target object is present and which one. Component pruning and filter selection, are studied. This representation is applied to the COIL-100 dataset and the experiment results are presented. Comparisons with other methods are also presented

Published in:

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on  (Volume:1 )

Date of Conference: