Logo image
Back
Many-to-many feature matching in object recognition: a review of three approaches
Journal article   Peer reviewed

Many-to-many feature matching in object recognition: a review of three approaches

A. Shokoufandeh, Y. Keselman, M. F. Demirci, D. Macrini and S. Dickinson
IET computer vision, v 6(6), pp 500-513
01 Nov 2012
DOI: https://doi.org/10.1049/iet-cvi.2012.0030

Abstract

Computer Science Computer Science, Artificial Intelligence Engineering Engineering, Electrical & Electronic Science & Technology Technology
The mainstream object categorisation community relies heavily on object representations consisting of local image features, due to their ease of recovery and their attractive invariance properties. Object categorisation is therefore formulated as finding, that is, 'detecting', a one-to-one correspondence between image and model features. This assumption breaks down for categories in which two exemplars may not share a single local image feature. Even when objects are represented as more abstract image features, a collection of features at one scale (in one image) may correspond to a single feature at a coarser scale (in the second image). Effective object categorisation therefore requires the ability to match features many-to-many. In this paper, we review our progress on three independent object categorisation problems, each formulated as a graph matching problem and each solving the many-to-many graph matching problem in a different way. First, we explore the problem of learning a shape class prototype from a set of class exemplars which may not share a single local image feature. Next, we explore the problem of matching two graphs in which correspondence exists only at higher levels of abstraction, and describe a low-dimensional, spectral encoding of graph structure that captures the abstract shape of a graph. Finally, we embed graphs into geometric spaces, reducing the many-to-many graph-matching problem to a weighted point matching problem, for which efficient many-to-many matching algorithms exist.

Metrics

11 Record Views
19 citations in Web of Science
25 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Industry collaboration
Domestic collaboration
International collaboration
Web of Science research areas
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Logo image