Hierarchical Shape Recognition Based on 3-D Multiresolution Analysis
Abstract
This paper introduces a method to create a hierarchical description of smooth curved surfaces based on scale-space analysis. We extend the scale-space method used in 1-D signal analysis to 3-D object. A 3-D scale-space images are segmented by zero-crossings of surface curvatures at each scale and then linked between consecutive scales based on topological changes (KH-description). The KH-description is, then, parsed and translated into the PS-tree which contains the number and distribution of subregions required for shape matching. The KH-description contains coarse-to-fine shape information of the object and the PS-tree is suitable for shape matching. A hierarchical matching algorithm using the descriptions is proposed and examples show that the symbolic description is suitable for efficient coarse-to-fine 3-D shape matching.
Cite
Text
Morita et al. "Hierarchical Shape Recognition Based on 3-D Multiresolution Analysis." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_97Markdown
[Morita et al. "Hierarchical Shape Recognition Based on 3-D Multiresolution Analysis." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/morita1992eccv-hierarchical/) doi:10.1007/3-540-55426-2_97BibTeX
@inproceedings{morita1992eccv-hierarchical,
title = {{Hierarchical Shape Recognition Based on 3-D Multiresolution Analysis}},
author = {Morita, Satoru and Kawashima, Toshio and Aoki, Yoshinao},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {843-851},
doi = {10.1007/3-540-55426-2_97},
url = {https://mlanthology.org/eccv/1992/morita1992eccv-hierarchical/}
}