Multi-scale Feature Extraction on Point-Sampled Surfaces
No Thumbnail Available
Date
2003
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Blackwell Publishers, Inc and the Eurographics Association
Abstract
We present a new technique for extracting line-type features on point-sampled geometry. Given an unstructuredpoint cloud as input, our method first applies principal component analysis on local neighborhoods toclassify points according to the likelihood that they belong to a feature. Using hysteresis thresholding, we thencompute a minimum spanning graph as an initial approximation of the feature lines. To smooth out the featureswhile maintaining a close connection to the underlying surface, we use an adaptation of active contour models.Central to our method is a multi-scale classification operator that allows feature analysis at multiplescales, using the size of the local neighborhoods as a discrete scale parameter. This significantly improves thereliability of the detection phase and makes our method more robust in the presence of noise. To illustrate theusefulness of our method, we have implemented a non-photorealistic point renderer to visualize point-sampledsurfaces as line drawings of their extracted feature curves.
Description
@article{10.1111:1467-8659.00675,
journal = {Computer Graphics Forum},
title = {{Multi-scale Feature Extraction on Point-Sampled Surfaces}},
author = {Pauly, Mark and Keiser, Richard and Gross, Markus},
year = {2003},
publisher = {Blackwell Publishers, Inc and the Eurographics Association},
ISSN = {1467-8659},
DOI = {10.1111/1467-8659.00675}
}