DMCA
Shape Spectrum Based View Grouping and Matching of 3D Free-Form Objects (1997)
| Venue: | IEEE Trans. Pattern Analysis and Machine Intelligence |
| Citations: | 22 - 1 self |
BibTeX
@ARTICLE{Dorai97shapespectrum,
author = {Chitra Dorai and Anil K. Jain},
title = {Shape Spectrum Based View Grouping and Matching of 3D Free-Form Objects},
journal = {IEEE Trans. Pattern Analysis and Machine Intelligence},
year = {1997},
volume = {19},
pages = {1139--1146}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We address the problem of constructing view aspects of 3D free-form objects for efficient matching during recognition. We introduce a novel view representation based on "shape spectrum" features, and propose a general and powerful technique for organizing multiple views of objects of complex shape and geometry into compact and homogeneous clusters. Our view grouping technique obviates the need for surface segmentation and edge detection. Experiments on 6,400 synthetically generated views of 20 free-form objects and 100 real range images of 10 sculpted objects demonstrate the good performance of our shape spectrum based model view selection technique.
Keyphrases
free-form object shape spectrum view grouping real range image good performance edge detection surface segmentation sculpted object model view selection technique homogeneous cluster powerful technique view grouping technique shape spectrum feature view aspect novel view representation generated view multiple view complex shape
