Image registration using non-linear diffusion

Michele Ceccarelli, M. Di Bisceglie, C. Galdi, G. Giangregorio, S. L. Ullo

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

2 Citations (Scopus)

Abstract

An image registration algorithm based on mutual information maximization and non-linear diffusion is presented. It relies on a non-parametric estimation of the degree of dependency between the reference image and the template to be registered, which is intrinsically more robust against possible deformations due to imaging geometry and propagation disturbances. The approach based on non linear diffusion, nonetheless, has the advantage of producing a non-parametric discrete warping model which does not rely on a particular set of basis functions, and is therefore as much general as possible. The experimental results on simulated images have quantitatively shown the accuracy of the proposed method.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume5
Edition1
DOIs
Publication statusPublished - 1 Dec 2008
Externally publishedYes
Event2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings - Boston, MA, United States
Duration: 6 Jul 200811 Jul 2008

Other

Other2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings
CountryUnited States
CityBoston, MA
Period6/7/0811/7/08

Fingerprint

Image registration
Imaging techniques
disturbance
geometry
Geometry
image registration
method

Keywords

  • Image registration
  • Non linear diffusion

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)
  • Computer Science Applications

Cite this

Ceccarelli, M., Di Bisceglie, M., Galdi, C., Giangregorio, G., & Ullo, S. L. (2008). Image registration using non-linear diffusion. In International Geoscience and Remote Sensing Symposium (IGARSS) (1 ed., Vol. 5). [4780067] https://doi.org/10.1109/IGARSS.2008.4780067

Image registration using non-linear diffusion. / Ceccarelli, Michele; Di Bisceglie, M.; Galdi, C.; Giangregorio, G.; Ullo, S. L.

International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 5 1. ed. 2008. 4780067.

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

Ceccarelli, M, Di Bisceglie, M, Galdi, C, Giangregorio, G & Ullo, SL 2008, Image registration using non-linear diffusion. in International Geoscience and Remote Sensing Symposium (IGARSS). 1 edn, vol. 5, 4780067, 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings, Boston, MA, United States, 6/7/08. https://doi.org/10.1109/IGARSS.2008.4780067
Ceccarelli M, Di Bisceglie M, Galdi C, Giangregorio G, Ullo SL. Image registration using non-linear diffusion. In International Geoscience and Remote Sensing Symposium (IGARSS). 1 ed. Vol. 5. 2008. 4780067 https://doi.org/10.1109/IGARSS.2008.4780067
Ceccarelli, Michele ; Di Bisceglie, M. ; Galdi, C. ; Giangregorio, G. ; Ullo, S. L. / Image registration using non-linear diffusion. International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 5 1. ed. 2008.
@inproceedings{f33e71cf81084eb5a3db3cd25662e3dc,
title = "Image registration using non-linear diffusion",
abstract = "An image registration algorithm based on mutual information maximization and non-linear diffusion is presented. It relies on a non-parametric estimation of the degree of dependency between the reference image and the template to be registered, which is intrinsically more robust against possible deformations due to imaging geometry and propagation disturbances. The approach based on non linear diffusion, nonetheless, has the advantage of producing a non-parametric discrete warping model which does not rely on a particular set of basis functions, and is therefore as much general as possible. The experimental results on simulated images have quantitatively shown the accuracy of the proposed method.",
keywords = "Image registration, Non linear diffusion",
author = "Michele Ceccarelli and {Di Bisceglie}, M. and C. Galdi and G. Giangregorio and Ullo, {S. L.}",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/IGARSS.2008.4780067",
language = "English",
isbn = "9781424428083",
volume = "5",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",
edition = "1",

}

TY - GEN

T1 - Image registration using non-linear diffusion

AU - Ceccarelli, Michele

AU - Di Bisceglie, M.

AU - Galdi, C.

AU - Giangregorio, G.

AU - Ullo, S. L.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - An image registration algorithm based on mutual information maximization and non-linear diffusion is presented. It relies on a non-parametric estimation of the degree of dependency between the reference image and the template to be registered, which is intrinsically more robust against possible deformations due to imaging geometry and propagation disturbances. The approach based on non linear diffusion, nonetheless, has the advantage of producing a non-parametric discrete warping model which does not rely on a particular set of basis functions, and is therefore as much general as possible. The experimental results on simulated images have quantitatively shown the accuracy of the proposed method.

AB - An image registration algorithm based on mutual information maximization and non-linear diffusion is presented. It relies on a non-parametric estimation of the degree of dependency between the reference image and the template to be registered, which is intrinsically more robust against possible deformations due to imaging geometry and propagation disturbances. The approach based on non linear diffusion, nonetheless, has the advantage of producing a non-parametric discrete warping model which does not rely on a particular set of basis functions, and is therefore as much general as possible. The experimental results on simulated images have quantitatively shown the accuracy of the proposed method.

KW - Image registration

KW - Non linear diffusion

UR - http://www.scopus.com/inward/record.url?scp=67649803652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649803652&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2008.4780067

DO - 10.1109/IGARSS.2008.4780067

M3 - Conference contribution

SN - 9781424428083

VL - 5

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

ER -