Indexing hierarchical structures using graph spectra |
| |
Authors: | Shokoufandeh Ali Macrini Diego Dickinson Sven Siddiqi Kaleem Zucker Steven W |
| |
Affiliation: | Dept. of Comput. Sci., College of Eng., Philadelphia, PA, USA; |
| |
Abstract: | Hierarchical image structures are abundant in computer vision and have been used to encode part structure, scale spaces, and a variety of multiresolution features. In this paper, we describe a framework for indexing such representations that embeds the topological structure of a directed acyclic graph (DAG) into a low-dimensional vector space. Based on a novel spectral characterization of a DAG, this topological signature allows us to efficiently retrieve a promising set of candidates from a database of models using a simple nearest-neighbor search. We establish the insensitivity of the signature to minor perturbation of graph structure due to noise, occlusion, or node split/merge. To accommodate large-scale occlusion, the DAG rooted at each nonleaf node of the query "votes" for model objects that share that "part," effectively accumulating local evidence in a model DAG's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of view-based 3D object recognition using shock graphs. |
| |
Keywords: | |
本文献已被 PubMed 等数据库收录! |
|