Quaternion Potential Functions for a colour image completion method using markov random fields

Huy Tho Ho, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

An exemplar-based algorithm has been proposed recently to solve the image completion problem by using a discrete global optimisation strategy based on Markov Random Fields. We can apply this algorithm to the task of completing colour images by processing the three colour channels separately and combining the results. However, this approach does not capture the correlations across the colour layers and, thus, may miss out on information important to the completion process. In this paper, we introduce the use of quaternions or hypercomplex numbers in estimating the potential functions for the image completion algorithm. The potential functions are calculated by correlating quaternion image patches based on the recently developed concepts of quaternion Fourier transform and quaternion correlation. Experimental results are presented for image completion which evidence improvements of the proposed approach over the monochromatic model.
Original languageEnglish
Title of host publicationProceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 )
Place of PublicationAustralia
PublisherAPRS
Pages324-331
Number of pages8
ISBN (Electronic)978-0-7695-3067-3
ISBN (Print) 0-7695-3067-2
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventDigital Image Computing Techniques Digital Image Computing Techniques and Applications DICTA 2007 - Glenelg, Adelaide, Australia
Duration: 3 Dec 20075 Dec 2007

Conference

ConferenceDigital Image Computing Techniques Digital Image Computing Techniques and Applications DICTA 2007
Abbreviated titleDICTA 2007
CountryAustralia
CityAdelaide
Period3/12/075/12/07

Fingerprint

Color
Global optimization
Fourier transforms
Processing

Cite this

Ho, H. T., & Goecke, R. (2007). Quaternion Potential Functions for a colour image completion method using markov random fields. In Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 ) (pp. 324-331). Australia: APRS. https://doi.org/10.1109/DICTA.2007.4426814
Ho, Huy Tho ; Goecke, Roland. / Quaternion Potential Functions for a colour image completion method using markov random fields. Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 ). Australia : APRS, 2007. pp. 324-331
@inproceedings{18229f3daf044e2484b48a6157a95fba,
title = "Quaternion Potential Functions for a colour image completion method using markov random fields",
abstract = "An exemplar-based algorithm has been proposed recently to solve the image completion problem by using a discrete global optimisation strategy based on Markov Random Fields. We can apply this algorithm to the task of completing colour images by processing the three colour channels separately and combining the results. However, this approach does not capture the correlations across the colour layers and, thus, may miss out on information important to the completion process. In this paper, we introduce the use of quaternions or hypercomplex numbers in estimating the potential functions for the image completion algorithm. The potential functions are calculated by correlating quaternion image patches based on the recently developed concepts of quaternion Fourier transform and quaternion correlation. Experimental results are presented for image completion which evidence improvements of the proposed approach over the monochromatic model.",
author = "Ho, {Huy Tho} and Roland Goecke",
year = "2007",
doi = "10.1109/DICTA.2007.4426814",
language = "English",
isbn = "0-7695-3067-2",
pages = "324--331",
booktitle = "Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 )",
publisher = "APRS",

}

Ho, HT & Goecke, R 2007, Quaternion Potential Functions for a colour image completion method using markov random fields. in Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 ). APRS, Australia, pp. 324-331, Digital Image Computing Techniques Digital Image Computing Techniques and Applications DICTA 2007, Adelaide, Australia, 3/12/07. https://doi.org/10.1109/DICTA.2007.4426814

Quaternion Potential Functions for a colour image completion method using markov random fields. / Ho, Huy Tho; Goecke, Roland.

Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 ). Australia : APRS, 2007. p. 324-331.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Quaternion Potential Functions for a colour image completion method using markov random fields

AU - Ho, Huy Tho

AU - Goecke, Roland

PY - 2007

Y1 - 2007

N2 - An exemplar-based algorithm has been proposed recently to solve the image completion problem by using a discrete global optimisation strategy based on Markov Random Fields. We can apply this algorithm to the task of completing colour images by processing the three colour channels separately and combining the results. However, this approach does not capture the correlations across the colour layers and, thus, may miss out on information important to the completion process. In this paper, we introduce the use of quaternions or hypercomplex numbers in estimating the potential functions for the image completion algorithm. The potential functions are calculated by correlating quaternion image patches based on the recently developed concepts of quaternion Fourier transform and quaternion correlation. Experimental results are presented for image completion which evidence improvements of the proposed approach over the monochromatic model.

AB - An exemplar-based algorithm has been proposed recently to solve the image completion problem by using a discrete global optimisation strategy based on Markov Random Fields. We can apply this algorithm to the task of completing colour images by processing the three colour channels separately and combining the results. However, this approach does not capture the correlations across the colour layers and, thus, may miss out on information important to the completion process. In this paper, we introduce the use of quaternions or hypercomplex numbers in estimating the potential functions for the image completion algorithm. The potential functions are calculated by correlating quaternion image patches based on the recently developed concepts of quaternion Fourier transform and quaternion correlation. Experimental results are presented for image completion which evidence improvements of the proposed approach over the monochromatic model.

U2 - 10.1109/DICTA.2007.4426814

DO - 10.1109/DICTA.2007.4426814

M3 - Conference contribution

SN - 0-7695-3067-2

SP - 324

EP - 331

BT - Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 )

PB - APRS

CY - Australia

ER -

Ho HT, Goecke R. Quaternion Potential Functions for a colour image completion method using markov random fields. In Proceedings: Digital Image Computing Techniques and Applications: 9th Biennial Conference of the Australian Pattern Recognition Society (DICTA 2007 ). Australia: APRS. 2007. p. 324-331 https://doi.org/10.1109/DICTA.2007.4426814