Share Email Print

Proceedings Paper

Multiscale edge- and region-based segmentation of range images
Author(s): Hong Minh Cung; Paul Cohen; Pierre Boulanger
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a multiscale edge- and region-based segmentation scheme for range images which leads to a rich representation in terms of focused edges and constant-sign curvature regions. At a given scale the edge detection scheme extracts the discontinuities in surface depth and orientation. The extraction is accomplished by first detecting the presence of significant edges at that scale and then determining their precise location by tracking them over decreasing scale down to the finest scale at which they are most accurately positioned. At the same scale the region-based segmentation scheme consists of applying anisotropic filtering to the regions delimited by the previously detected edges and segmenting these regions into surface primitives of constant Gaussian and mean curvature signs. Experimental results are presented for both synthetic and real images and a comparison is done with some recently published techniques. 1.

Paper Details

Date Published: 1 September 1990
PDF: 12 pages
Proc. SPIE 1297, Hybrid Image and Signal Processing II, (1 September 1990); doi: 10.1117/12.21321
Show Author Affiliations
Hong Minh Cung, Ecole Polytechnique de Montrea (Canada)
Paul Cohen, Ecole Polytechnique de Montrea (Canada)
Pierre Boulanger, National Research Council of C (Canada)

Published in SPIE Proceedings Vol. 1297:
Hybrid Image and Signal Processing II
David P. Casasent; Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top