Image registration based on genetic algorithm and weighted feature correspondences

Zhi Yuan, Alireza Ahrary, Peimin Yan, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Super resolution is a technique of enhancing image resolution by combining information from multiple images. It is widely applied in fields like camera surveillance, satellite imaging, pattern recognition, etc. One challenging problem of super resolution is its high demand on image registration accuracy. This paper introduces a high accuracy registration approach for the purpose of super resolution. It is invariant to translation, scaling, rotation, and noise, and can be used to automatically obtain the Maximize a Likelihood Estimation (MLE) of image homography (registration result) using information only contained within the images themselves. An effective Genetic Algorithm based approach is used to filter out all the mismatches. Comparison with RANSAC and Keren's method will be given to prove the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationDigest of Technical Papers - IEEE International Conference on Consumer Electronics
Pages42-46
Number of pages5
DOIs
Publication statusPublished - 2009
Event2009 IEEE 13th International Symposium on Consumer Electronics, ISCE 2009 - Kyoto
Duration: 2009 May 252009 May 28

Other

Other2009 IEEE 13th International Symposium on Consumer Electronics, ISCE 2009
CityKyoto
Period09/5/2509/5/28

Fingerprint

Image registration
Genetic algorithms
Optical resolving power
Image resolution
Pattern recognition
Cameras
Satellites
Imaging techniques

Keywords

  • Backward projection
  • Genetic Algorithm
  • Image registration
  • RANSAC (Random Sampling Consensus)
  • SIFT (Scale Invairant Feature Transform)
  • Super resolution

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Yuan, Z., Ahrary, A., Yan, P., & Kamata, S. (2009). Image registration based on genetic algorithm and weighted feature correspondences. In Digest of Technical Papers - IEEE International Conference on Consumer Electronics (pp. 42-46). [5157002] https://doi.org/10.1109/ISCE.2009.5157002

Image registration based on genetic algorithm and weighted feature correspondences. / Yuan, Zhi; Ahrary, Alireza; Yan, Peimin; Kamata, Seiichiro.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009. p. 42-46 5157002.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yuan, Z, Ahrary, A, Yan, P & Kamata, S 2009, Image registration based on genetic algorithm and weighted feature correspondences. in Digest of Technical Papers - IEEE International Conference on Consumer Electronics., 5157002, pp. 42-46, 2009 IEEE 13th International Symposium on Consumer Electronics, ISCE 2009, Kyoto, 09/5/25. https://doi.org/10.1109/ISCE.2009.5157002
Yuan Z, Ahrary A, Yan P, Kamata S. Image registration based on genetic algorithm and weighted feature correspondences. In Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009. p. 42-46. 5157002 https://doi.org/10.1109/ISCE.2009.5157002
Yuan, Zhi ; Ahrary, Alireza ; Yan, Peimin ; Kamata, Seiichiro. / Image registration based on genetic algorithm and weighted feature correspondences. Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009. pp. 42-46
@inproceedings{30ea1c576e3e427b931628f610aec053,
title = "Image registration based on genetic algorithm and weighted feature correspondences",
abstract = "Super resolution is a technique of enhancing image resolution by combining information from multiple images. It is widely applied in fields like camera surveillance, satellite imaging, pattern recognition, etc. One challenging problem of super resolution is its high demand on image registration accuracy. This paper introduces a high accuracy registration approach for the purpose of super resolution. It is invariant to translation, scaling, rotation, and noise, and can be used to automatically obtain the Maximize a Likelihood Estimation (MLE) of image homography (registration result) using information only contained within the images themselves. An effective Genetic Algorithm based approach is used to filter out all the mismatches. Comparison with RANSAC and Keren's method will be given to prove the effectiveness of the proposed method.",
keywords = "Backward projection, Genetic Algorithm, Image registration, RANSAC (Random Sampling Consensus), SIFT (Scale Invairant Feature Transform), Super resolution",
author = "Zhi Yuan and Alireza Ahrary and Peimin Yan and Seiichiro Kamata",
year = "2009",
doi = "10.1109/ISCE.2009.5157002",
language = "English",
isbn = "9781424429769",
pages = "42--46",
booktitle = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

}

TY - GEN

T1 - Image registration based on genetic algorithm and weighted feature correspondences

AU - Yuan, Zhi

AU - Ahrary, Alireza

AU - Yan, Peimin

AU - Kamata, Seiichiro

PY - 2009

Y1 - 2009

N2 - Super resolution is a technique of enhancing image resolution by combining information from multiple images. It is widely applied in fields like camera surveillance, satellite imaging, pattern recognition, etc. One challenging problem of super resolution is its high demand on image registration accuracy. This paper introduces a high accuracy registration approach for the purpose of super resolution. It is invariant to translation, scaling, rotation, and noise, and can be used to automatically obtain the Maximize a Likelihood Estimation (MLE) of image homography (registration result) using information only contained within the images themselves. An effective Genetic Algorithm based approach is used to filter out all the mismatches. Comparison with RANSAC and Keren's method will be given to prove the effectiveness of the proposed method.

AB - Super resolution is a technique of enhancing image resolution by combining information from multiple images. It is widely applied in fields like camera surveillance, satellite imaging, pattern recognition, etc. One challenging problem of super resolution is its high demand on image registration accuracy. This paper introduces a high accuracy registration approach for the purpose of super resolution. It is invariant to translation, scaling, rotation, and noise, and can be used to automatically obtain the Maximize a Likelihood Estimation (MLE) of image homography (registration result) using information only contained within the images themselves. An effective Genetic Algorithm based approach is used to filter out all the mismatches. Comparison with RANSAC and Keren's method will be given to prove the effectiveness of the proposed method.

KW - Backward projection

KW - Genetic Algorithm

KW - Image registration

KW - RANSAC (Random Sampling Consensus)

KW - SIFT (Scale Invairant Feature Transform)

KW - Super resolution

UR - http://www.scopus.com/inward/record.url?scp=70350241783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350241783&partnerID=8YFLogxK

U2 - 10.1109/ISCE.2009.5157002

DO - 10.1109/ISCE.2009.5157002

M3 - Conference contribution

AN - SCOPUS:70350241783

SN - 9781424429769

SP - 42

EP - 46

BT - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

ER -