Indexing Using a Spectral Encoding of Topological Structure
Abstract
In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.
Cite
Text
Shokoufandeh et al. "Indexing Using a Spectral Encoding of Topological Structure." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784726Markdown
[Shokoufandeh et al. "Indexing Using a Spectral Encoding of Topological Structure." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/shokoufandeh1999cvpr-indexing/) doi:10.1109/CVPR.1999.784726BibTeX
@inproceedings{shokoufandeh1999cvpr-indexing,
title = {{Indexing Using a Spectral Encoding of Topological Structure}},
author = {Shokoufandeh, Ali and Dickinson, Sven J. and Siddiqi, Kaleem and Zucker, Steven W.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1999},
pages = {2491-2497},
doi = {10.1109/CVPR.1999.784726},
url = {https://mlanthology.org/cvpr/1999/shokoufandeh1999cvpr-indexing/}
}