Graph Matching Techniques for Computer Vision

Graph Matching Techniques for Computer Vision

Mario Vento, Pasquale Foggia
DOI: 10.4018/978-1-4666-1891-6.ch001
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Many computer vision applications require a comparison between two objects, or between an object and a reference model. When the objects or the scenes are represented by graphs, this comparison can be performed using some form of graph matching. The aim of this chapter is to introduce the main graph matching techniques that have been used for computer vision, and to relate each application with the techniques that are most suited to it.
Chapter Preview
Top

Graph Matching Algorithms

In this section we will present a short introduction to the most commonly used graph matching techniques. The techniques are grouped on the basis of how the matching problem is formulated, giving rise to the following categories:

  • Exact Graph Matching Algorithms: Have strict requirements on the preservation of the structure of the graphs across the mapping

  • Inexact Graph Matching Algorithms: Tolerant about structure differences in the parts of the graphs being matched

  • Graph Embeddings and Graph Kernels: Techniques to apply algorithms developed for vectorial representations to the graph domain; such techniques are gaining a growing interest in the recent literature

  • Other Matching Techniques: The structure of the graphs plays only a minor role

Complete Chapter List

Search this Book:
Reset