Symbolic Image Matching by Simulated Annealing

Abstract : In this paper we suggest an optimisation approach to visual matching. We assume that the information available in an image may be conveniently represented symbolically in a relational graph. We concentrate on the problem of matching two such graphs. First we derive a cost function associated with graph matching and more precisely associated with subgraph isomorphism and with maximum subgraph matching. This cost function is well suited for optimization methods such as simulated annealing. We show how the graph matching problem is easily cast into a simulated annealing algorithm. Finally we show some preliminary experimental results and discuss the utility of this graph matching method in computer vision in general.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00589994
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 8:28:52 AM
Last modification on : Monday, February 25, 2019 - 4:34:18 PM
Long-term archiving on: Thursday, August 4, 2011 - 2:35:26 AM

File

HeraultHoraudBMVC90.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00589994, version 1

Collections

CEA | IMAG | CNRS | INRIA | UGA | DRT | LETI | CEA-GRE

Citation

Laurent Hérault, Radu Horaud, Françoise Veillon, Jean-Jacques Niez. Symbolic Image Matching by Simulated Annealing. 4th British Machine Vision Conference (BMVC '90), Sep 1990, Oxford, United Kingdom. pp.319--324. ⟨inria-00589994⟩

Share

Metrics

Record views

519

Files downloads

209