Indexing using a spectral encoding of topological structure

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 domain...

Full description

Saved in:
Bibliographic Details
Main Authors: Shokoufandeh, A., Dickinson, S.J., Siddiqi, K., Zucker, S.W.
Format: Conference Proceeding
Language:English
Subjects:
Computational biology
Computer graphics
Computer vision
Eigenvalues and eigenfunctions
Encoding
Feature extraction
Indexing
Information retrieval
Object recognition
Tree graphs
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.1999.784726