Halton Sampling for Image Registration Based on Mutual Information
Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We sho...
Ausführliche Beschreibung
Autor*in: |
Thévenaz, Philippe [verfasserIn] Bierlaire, Michel [verfasserIn] Unser, Michael [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2008 |
---|
Anmerkung: |
© Sampling Publishing 2008 |
---|
Übergeordnetes Werk: |
Enthalten in: Sampling theory, signal processing, and data analysis - [Cham] : Birkhäuser, 2021, 7(2008), 2 vom: 01. Mai, Seite 141-171 |
---|---|
Übergeordnetes Werk: |
volume:7 ; year:2008 ; number:2 ; day:01 ; month:05 ; pages:141-171 |
Links: |
---|
DOI / URN: |
10.1007/BF03549492 |
---|
Katalog-ID: |
SPR043388272 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | SPR043388272 | ||
003 | DE-627 | ||
005 | 20220112055043.0 | ||
007 | cr uuu---uuuuu | ||
008 | 210303s2008 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/BF03549492 |2 doi | |
035 | |a (DE-627)SPR043388272 | ||
035 | |a (SPR)BF03549492-e | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 510 |a 004 |q ASE |
082 | 0 | 4 | |a 510 |q ASE |
100 | 1 | |a Thévenaz, Philippe |e verfasserin |4 aut | |
245 | 1 | 0 | |a Halton Sampling for Image Registration Based on Mutual Information |
264 | 1 | |c 2008 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a © Sampling Publishing 2008 | ||
520 | |a Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. | ||
700 | 1 | |a Bierlaire, Michel |e verfasserin |4 aut | |
700 | 1 | |a Unser, Michael |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Sampling theory, signal processing, and data analysis |d [Cham] : Birkhäuser, 2021 |g 7(2008), 2 vom: 01. Mai, Seite 141-171 |w (DE-627)1735681601 |w (DE-600)3041928-1 |x 2730-5724 |7 nnns |
773 | 1 | 8 | |g volume:7 |g year:2008 |g number:2 |g day:01 |g month:05 |g pages:141-171 |
856 | 4 | 0 | |u https://dx.doi.org/10.1007/BF03549492 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_SPRINGER | ||
951 | |a AR | ||
952 | |d 7 |j 2008 |e 2 |b 01 |c 05 |h 141-171 |
author_variant |
p t pt m b mb m u mu |
---|---|
matchkey_str |
article:27305724:2008----::atnapigoiaeeitainaeom |
hierarchy_sort_str |
2008 |
publishDate |
2008 |
allfields |
10.1007/BF03549492 doi (DE-627)SPR043388272 (SPR)BF03549492-e DE-627 ger DE-627 rakwb eng 510 004 ASE 510 ASE Thévenaz, Philippe verfasserin aut Halton Sampling for Image Registration Based on Mutual Information 2008 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Sampling Publishing 2008 Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. Bierlaire, Michel verfasserin aut Unser, Michael verfasserin aut Enthalten in Sampling theory, signal processing, and data analysis [Cham] : Birkhäuser, 2021 7(2008), 2 vom: 01. Mai, Seite 141-171 (DE-627)1735681601 (DE-600)3041928-1 2730-5724 nnns volume:7 year:2008 number:2 day:01 month:05 pages:141-171 https://dx.doi.org/10.1007/BF03549492 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 7 2008 2 01 05 141-171 |
spelling |
10.1007/BF03549492 doi (DE-627)SPR043388272 (SPR)BF03549492-e DE-627 ger DE-627 rakwb eng 510 004 ASE 510 ASE Thévenaz, Philippe verfasserin aut Halton Sampling for Image Registration Based on Mutual Information 2008 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Sampling Publishing 2008 Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. Bierlaire, Michel verfasserin aut Unser, Michael verfasserin aut Enthalten in Sampling theory, signal processing, and data analysis [Cham] : Birkhäuser, 2021 7(2008), 2 vom: 01. Mai, Seite 141-171 (DE-627)1735681601 (DE-600)3041928-1 2730-5724 nnns volume:7 year:2008 number:2 day:01 month:05 pages:141-171 https://dx.doi.org/10.1007/BF03549492 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 7 2008 2 01 05 141-171 |
allfields_unstemmed |
10.1007/BF03549492 doi (DE-627)SPR043388272 (SPR)BF03549492-e DE-627 ger DE-627 rakwb eng 510 004 ASE 510 ASE Thévenaz, Philippe verfasserin aut Halton Sampling for Image Registration Based on Mutual Information 2008 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Sampling Publishing 2008 Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. Bierlaire, Michel verfasserin aut Unser, Michael verfasserin aut Enthalten in Sampling theory, signal processing, and data analysis [Cham] : Birkhäuser, 2021 7(2008), 2 vom: 01. Mai, Seite 141-171 (DE-627)1735681601 (DE-600)3041928-1 2730-5724 nnns volume:7 year:2008 number:2 day:01 month:05 pages:141-171 https://dx.doi.org/10.1007/BF03549492 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 7 2008 2 01 05 141-171 |
allfieldsGer |
10.1007/BF03549492 doi (DE-627)SPR043388272 (SPR)BF03549492-e DE-627 ger DE-627 rakwb eng 510 004 ASE 510 ASE Thévenaz, Philippe verfasserin aut Halton Sampling for Image Registration Based on Mutual Information 2008 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Sampling Publishing 2008 Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. Bierlaire, Michel verfasserin aut Unser, Michael verfasserin aut Enthalten in Sampling theory, signal processing, and data analysis [Cham] : Birkhäuser, 2021 7(2008), 2 vom: 01. Mai, Seite 141-171 (DE-627)1735681601 (DE-600)3041928-1 2730-5724 nnns volume:7 year:2008 number:2 day:01 month:05 pages:141-171 https://dx.doi.org/10.1007/BF03549492 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 7 2008 2 01 05 141-171 |
allfieldsSound |
10.1007/BF03549492 doi (DE-627)SPR043388272 (SPR)BF03549492-e DE-627 ger DE-627 rakwb eng 510 004 ASE 510 ASE Thévenaz, Philippe verfasserin aut Halton Sampling for Image Registration Based on Mutual Information 2008 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Sampling Publishing 2008 Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. Bierlaire, Michel verfasserin aut Unser, Michael verfasserin aut Enthalten in Sampling theory, signal processing, and data analysis [Cham] : Birkhäuser, 2021 7(2008), 2 vom: 01. Mai, Seite 141-171 (DE-627)1735681601 (DE-600)3041928-1 2730-5724 nnns volume:7 year:2008 number:2 day:01 month:05 pages:141-171 https://dx.doi.org/10.1007/BF03549492 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 7 2008 2 01 05 141-171 |
language |
English |
source |
Enthalten in Sampling theory, signal processing, and data analysis 7(2008), 2 vom: 01. Mai, Seite 141-171 volume:7 year:2008 number:2 day:01 month:05 pages:141-171 |
sourceStr |
Enthalten in Sampling theory, signal processing, and data analysis 7(2008), 2 vom: 01. Mai, Seite 141-171 volume:7 year:2008 number:2 day:01 month:05 pages:141-171 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
dewey-raw |
510 |
isfreeaccess_bool |
false |
container_title |
Sampling theory, signal processing, and data analysis |
authorswithroles_txt_mv |
Thévenaz, Philippe @@aut@@ Bierlaire, Michel @@aut@@ Unser, Michael @@aut@@ |
publishDateDaySort_date |
2008-05-01T00:00:00Z |
hierarchy_top_id |
1735681601 |
dewey-sort |
3510 |
id |
SPR043388272 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR043388272</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220112055043.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210303s2008 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/BF03549492</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR043388272</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)BF03549492-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="a">004</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Thévenaz, Philippe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Halton Sampling for Image Registration Based on Mutual Information</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2008</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Sampling Publishing 2008</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bierlaire, Michel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Unser, Michael</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Sampling theory, signal processing, and data analysis</subfield><subfield code="d">[Cham] : Birkhäuser, 2021</subfield><subfield code="g">7(2008), 2 vom: 01. Mai, Seite 141-171</subfield><subfield code="w">(DE-627)1735681601</subfield><subfield code="w">(DE-600)3041928-1</subfield><subfield code="x">2730-5724</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:7</subfield><subfield code="g">year:2008</subfield><subfield code="g">number:2</subfield><subfield code="g">day:01</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:141-171</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/BF03549492</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">7</subfield><subfield code="j">2008</subfield><subfield code="e">2</subfield><subfield code="b">01</subfield><subfield code="c">05</subfield><subfield code="h">141-171</subfield></datafield></record></collection>
|
author |
Thévenaz, Philippe |
spellingShingle |
Thévenaz, Philippe ddc 510 Halton Sampling for Image Registration Based on Mutual Information |
authorStr |
Thévenaz, Philippe |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)1735681601 |
format |
electronic Article |
dewey-ones |
510 - Mathematics 004 - Data processing & computer science |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
springer |
remote_str |
true |
illustrated |
Not Illustrated |
issn |
2730-5724 |
topic_title |
510 004 ASE 510 ASE Halton Sampling for Image Registration Based on Mutual Information |
topic |
ddc 510 |
topic_unstemmed |
ddc 510 |
topic_browse |
ddc 510 |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
Sampling theory, signal processing, and data analysis |
hierarchy_parent_id |
1735681601 |
dewey-tens |
510 - Mathematics 000 - Computer science, knowledge & systems |
hierarchy_top_title |
Sampling theory, signal processing, and data analysis |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)1735681601 (DE-600)3041928-1 |
title |
Halton Sampling for Image Registration Based on Mutual Information |
ctrlnum |
(DE-627)SPR043388272 (SPR)BF03549492-e |
title_full |
Halton Sampling for Image Registration Based on Mutual Information |
author_sort |
Thévenaz, Philippe |
journal |
Sampling theory, signal processing, and data analysis |
journalStr |
Sampling theory, signal processing, and data analysis |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
500 - Science 000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2008 |
contenttype_str_mv |
txt |
container_start_page |
141 |
author_browse |
Thévenaz, Philippe Bierlaire, Michel Unser, Michael |
container_volume |
7 |
class |
510 004 ASE 510 ASE |
format_se |
Elektronische Aufsätze |
author-letter |
Thévenaz, Philippe |
doi_str_mv |
10.1007/BF03549492 |
dewey-full |
510 004 |
author2-role |
verfasserin |
title_sort |
halton sampling for image registration based on mutual information |
title_auth |
Halton Sampling for Image Registration Based on Mutual Information |
abstract |
Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. © Sampling Publishing 2008 |
abstractGer |
Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. © Sampling Publishing 2008 |
abstract_unstemmed |
Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time. © Sampling Publishing 2008 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
container_issue |
2 |
title_short |
Halton Sampling for Image Registration Based on Mutual Information |
url |
https://dx.doi.org/10.1007/BF03549492 |
remote_bool |
true |
author2 |
Bierlaire, Michel Unser, Michael |
author2Str |
Bierlaire, Michel Unser, Michael |
ppnlink |
1735681601 |
mediatype_str_mv |
c |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/BF03549492 |
up_date |
2024-07-03T18:21:01.420Z |
_version_ |
1803583080548532225 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR043388272</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220112055043.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210303s2008 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/BF03549492</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR043388272</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)BF03549492-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="a">004</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">510</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Thévenaz, Philippe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Halton Sampling for Image Registration Based on Mutual Information</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2008</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Sampling Publishing 2008</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Mutual information is a widely used similarity measure for aligning multimodal medical images. At its core it relies on the computation of a discrete joint histogram, which itself requires image samples for its estimation. In this paper we study the influence of the sampling process. We show that quasi-random sampling based on Halton sequences outperforms methods based on regular sampling or on random sampling. Our results suggest that sampling itself—and not interpolation, as was previously believed—is the source of two major problems associated with mutual information: the grid effect, whereby grid-aligning transformations are favored, and the overlap problem, whereby the similarity measure exhibits discontinuities. Both defects tend to impede the accuracy of registration; they also result in reduced robustness because of the presence of local optima. By estimating the joint histogram by quasi-random sampling, we solve both issues at the same time.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bierlaire, Michel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Unser, Michael</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Sampling theory, signal processing, and data analysis</subfield><subfield code="d">[Cham] : Birkhäuser, 2021</subfield><subfield code="g">7(2008), 2 vom: 01. Mai, Seite 141-171</subfield><subfield code="w">(DE-627)1735681601</subfield><subfield code="w">(DE-600)3041928-1</subfield><subfield code="x">2730-5724</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:7</subfield><subfield code="g">year:2008</subfield><subfield code="g">number:2</subfield><subfield code="g">day:01</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:141-171</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/BF03549492</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">7</subfield><subfield code="j">2008</subfield><subfield code="e">2</subfield><subfield code="b">01</subfield><subfield code="c">05</subfield><subfield code="h">141-171</subfield></datafield></record></collection>
|
score |
7.400161 |