Affine image registration transformation estimation using a real coded genetic algorithm with SBX

Mosab Bazargani; António Anjos; Fernando Lobo; Ali Mollahosseini; Hamid Shahbazkia

doi:10.1145/2330784.2330990

Affine image registration transformation estimation using a real coded genetic algorithm with SBX

Mosab Bazargani
, António Anjos
, Fernando Lobo
, Ali Mollahosseini
, Hamid Shahbazkia

Universidade do Algarve, Faro
Instituto Superior Manuel Teixeira Gomes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We describe the application of a real coded genetic algorithm (GA) to align two or more 2-D images by means of image registration. The proposed search strategy is a transformation parameters-based approach involving the affine transform. The real coded GA uses Simulated Binary Crossover (SBX). In addition, we propose a new technique for matching points between a warped and static images by using a randomized ordering when visiting the points during the matching procedure. The results confirm the usefulness of the proposed noisy objective function and the suitability of SBX as a recombination operator for this type of problem.

Original language	English
Title of host publication	Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery
Pages	1459–1460
ISBN (Print)	9781450311786
DOIs	https://doi.org/10.1145/2330784.2330990
Publication status	Published - 7 Jul 2012
Externally published	Yes

Publication series

Name	GECCO '12
Publisher	Association for Computing Machinery

Keywords

affine transform
genetic algorithms
image registration
point-pattern matching
simulated binary crossover

Access to Document

10.1145/2330784.2330990

https://doi.org/10.1145/2330784.2330990

Cite this

Bazargani, M., Anjos, A., Lobo, F., Mollahosseini, A., & Shahbazkia, H. (2012). Affine image registration transformation estimation using a real coded genetic algorithm with SBX. In Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation (pp. 1459–1460). (GECCO '12). Association for Computing Machinery. https://doi.org/10.1145/2330784.2330990

@inproceedings{cdc10d93bccb4001af34eb73a580e440,

title = "Affine image registration transformation estimation using a real coded genetic algorithm with SBX",

abstract = "We describe the application of a real coded genetic algorithm (GA) to align two or more 2-D images by means of image registration. The proposed search strategy is a transformation parameters-based approach involving the affine transform. The real coded GA uses Simulated Binary Crossover (SBX). In addition, we propose a new technique for matching points between a warped and static images by using a randomized ordering when visiting the points during the matching procedure. The results confirm the usefulness of the proposed noisy objective function and the suitability of SBX as a recombination operator for this type of problem.",

keywords = "affine transform, genetic algorithms, image registration, point-pattern matching, simulated binary crossover",

author = "Mosab Bazargani and Ant{\'o}nio Anjos and Fernando Lobo and Ali Mollahosseini and Hamid Shahbazkia",

year = "2012",

month = jul,

day = "7",

doi = "10.1145/2330784.2330990",

language = "English",

isbn = "9781450311786",

series = "GECCO '12",

publisher = "Association for Computing Machinery",

pages = "1459–1460",

booktitle = "Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation",

}

Bazargani, M, Anjos, A, Lobo, F, Mollahosseini, A & Shahbazkia, H 2012, Affine image registration transformation estimation using a real coded genetic algorithm with SBX. in Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation. GECCO '12, Association for Computing Machinery, New York, NY, USA, pp. 1459–1460. https://doi.org/10.1145/2330784.2330990

Affine image registration transformation estimation using a real coded genetic algorithm with SBX. / Bazargani, Mosab; Anjos, António; Lobo, Fernando et al.
Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation. New York, NY, USA: Association for Computing Machinery, 2012. p. 1459–1460 (GECCO '12).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Affine image registration transformation estimation using a real coded genetic algorithm with SBX

AU - Bazargani, Mosab

AU - Anjos, António

AU - Lobo, Fernando

AU - Mollahosseini, Ali

AU - Shahbazkia, Hamid

PY - 2012/7/7

Y1 - 2012/7/7

N2 - We describe the application of a real coded genetic algorithm (GA) to align two or more 2-D images by means of image registration. The proposed search strategy is a transformation parameters-based approach involving the affine transform. The real coded GA uses Simulated Binary Crossover (SBX). In addition, we propose a new technique for matching points between a warped and static images by using a randomized ordering when visiting the points during the matching procedure. The results confirm the usefulness of the proposed noisy objective function and the suitability of SBX as a recombination operator for this type of problem.

AB - We describe the application of a real coded genetic algorithm (GA) to align two or more 2-D images by means of image registration. The proposed search strategy is a transformation parameters-based approach involving the affine transform. The real coded GA uses Simulated Binary Crossover (SBX). In addition, we propose a new technique for matching points between a warped and static images by using a randomized ordering when visiting the points during the matching procedure. The results confirm the usefulness of the proposed noisy objective function and the suitability of SBX as a recombination operator for this type of problem.

KW - affine transform

KW - genetic algorithms

KW - image registration

KW - point-pattern matching

KW - simulated binary crossover

U2 - 10.1145/2330784.2330990

DO - 10.1145/2330784.2330990

M3 - Conference contribution

SN - 9781450311786

T3 - GECCO '12

SP - 1459

EP - 1460

BT - Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation

PB - Association for Computing Machinery

CY - New York, NY, USA

ER -

Bazargani M, Anjos A, Lobo F, Mollahosseini A, Shahbazkia H. Affine image registration transformation estimation using a real coded genetic algorithm with SBX. In Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation. New York, NY, USA: Association for Computing Machinery. 2012. p. 1459–1460. (GECCO '12). doi: 10.1145/2330784.2330990

Affine image registration transformation estimation using a real coded genetic algorithm with SBX

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this