File Download
  Links for fulltext
     (May Require Subscription)

Conference Paper: Correspondenceless 3D-2D registration based on expectation conditional maximization

TitleCorrespondenceless 3D-2D registration based on expectation conditional maximization
Authors
Keywords3D-2D registration
Expectation conditional maximization
Mixture of Gaussian
Issue Date2011
PublisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://www.spie.org/app/Publications/index.cfm?fuseaction=proceedings
Citation
The SPIE Medical Imaging 2011, Lake Buena Vista, FL., 12-17 February 2011. In Progress in Biomedical Optics and Imaging, 2011, v. 7964, article no. 79642Z How to Cite?
Abstract3D-2D registration is a fundamental task in image guided interventions. Due to the physics of the X-ray imaging, however, traditional point based methods meet new challenges, where the local point features are indistinguishable, creating difficulties in establishing correspondence between 2D image feature points and 3D model points. In this paper, we propose a novel method to accomplish 3D-2D registration without known correspondences. Given a set of 3D and 2D unmatched points, this is achieved by introducing correspondence probabilities that we model as a mixture model. By casting it into the expectation conditional maximization framework, without establishing one-to-one point correspondences, we can iteratively refine the registration parameters. The method has been tested on 100 real X-ray images. The experiments showed that the proposed method accurately estimated the rotations (< 1°) and in-plane (X-Y plane) translations (< 1 mm). © 2011 SPIE.
DescriptionCum Laude Poster Award
Conference Theme: Visualization, Image-Guided Procedures, and Modeling
Persistent Identifierhttp://hdl.handle.net/10722/135986
ISSN
2023 SCImago Journal Rankings: 0.226
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorKang, Xen_HK
dc.contributor.authorTaylor, RHen_HK
dc.contributor.authorArmand, Men_HK
dc.contributor.authorOtake, Yen_HK
dc.contributor.authorYau, WPen_HK
dc.contributor.authorCheung, PYSen_HK
dc.contributor.authorHu, Yen_HK
dc.date.accessioned2011-07-27T02:00:51Z-
dc.date.available2011-07-27T02:00:51Z-
dc.date.issued2011en_HK
dc.identifier.citationThe SPIE Medical Imaging 2011, Lake Buena Vista, FL., 12-17 February 2011. In Progress in Biomedical Optics and Imaging, 2011, v. 7964, article no. 79642Zen_HK
dc.identifier.issn1605-7422en_HK
dc.identifier.urihttp://hdl.handle.net/10722/135986-
dc.descriptionCum Laude Poster Award-
dc.descriptionConference Theme: Visualization, Image-Guided Procedures, and Modeling-
dc.description.abstract3D-2D registration is a fundamental task in image guided interventions. Due to the physics of the X-ray imaging, however, traditional point based methods meet new challenges, where the local point features are indistinguishable, creating difficulties in establishing correspondence between 2D image feature points and 3D model points. In this paper, we propose a novel method to accomplish 3D-2D registration without known correspondences. Given a set of 3D and 2D unmatched points, this is achieved by introducing correspondence probabilities that we model as a mixture model. By casting it into the expectation conditional maximization framework, without establishing one-to-one point correspondences, we can iteratively refine the registration parameters. The method has been tested on 100 real X-ray images. The experiments showed that the proposed method accurately estimated the rotations (< 1°) and in-plane (X-Y plane) translations (< 1 mm). © 2011 SPIE.en_HK
dc.languageengen_US
dc.publisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://www.spie.org/app/Publications/index.cfm?fuseaction=proceedingsen_HK
dc.relation.ispartofProgress in Biomedical Optics & Imaging: Proceedings of SPIEen_HK
dc.rightsCopyright 2011 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited. This article is available online at https://doi.org/10.1117/12.878618-
dc.subject3D-2D registrationen_HK
dc.subjectExpectation conditional maximizationen_HK
dc.subjectMixture of Gaussianen_HK
dc.titleCorrespondenceless 3D-2D registration based on expectation conditional maximizationen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailYau, WP:peterwpy@hkucc.hku.hken_HK
dc.identifier.emailCheung, PYS:paul.cheung@hku.hken_HK
dc.identifier.emailHu, Y:yhud@hku.hken_HK
dc.identifier.authorityYau, WP=rp00500en_HK
dc.identifier.authorityCheung, PYS=rp00077en_HK
dc.identifier.authorityHu, Y=rp00432en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1117/12.878618en_HK
dc.identifier.scopuseid_2-s2.0-79955850020en_HK
dc.identifier.hkuros188669en_US
dc.identifier.hkuros208260-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-79955850020&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume7964en_HK
dc.identifier.isiWOS:000294224900101-
dc.publisher.placeUnited Statesen_HK
dc.description.otherThe SPIE Medical Imaging 2011, Lake Buena Vista, FL., 12-17 February 2011. In Progress in Biomedical Optics and Imaging, 2011, v. 7964, art. no. 79642Z-
dc.identifier.scopusauthoridKang, X=36844160400en_HK
dc.identifier.scopusauthoridTaylor, RH=7405756438en_HK
dc.identifier.scopusauthoridArmand, M=35236429300en_HK
dc.identifier.scopusauthoridOtake, Y=35771231600en_HK
dc.identifier.scopusauthoridYau, WP=7005822441en_HK
dc.identifier.scopusauthoridCheung, PYS=7202595335en_HK
dc.identifier.scopusauthoridHu, Y=7407116091en_HK
dc.customcontrol.immutablesml 170329 amended-
dc.identifier.issnl1605-7422-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats