No Cover Image

Conference Paper/Proceeding/Abstract 898 views

Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling

Robert Palmer, Gary Tam, Xianghua Xie Orcid Logo

IEEE Engineering in Medicine and Biology Society

Swansea University Author: Xianghua Xie Orcid Logo

Abstract

A statistical shape model that accurately generalizes a family of 3D shapes requires establishing correspondences across the set of shapes. However in 3D anatomical meshes, finding a sufficient number of landmarks to accurately describe the shape can be a challenge, and often only a few points are e...

Full description

Published in: IEEE Engineering in Medicine and Biology Society
Published: IEEE 2015
URI: https://cronfa.swan.ac.uk/Record/cronfa22236
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2015-07-02T02:07:56Z
last_indexed 2018-02-09T05:00:30Z
id cronfa22236
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2016-06-13T14:52:25.3934507</datestamp><bib-version>v2</bib-version><id>22236</id><entry>2015-07-01</entry><title>Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2015-07-01</date><deptcode>SCS</deptcode><abstract>A statistical shape model that accurately generalizes a family of 3D shapes requires establishing correspondences across the set of shapes. However in 3D anatomical meshes, finding a sufficient number of landmarks to accurately describe the shape can be a challenge, and often only a few points are easily identifiable due to the smooth nature of the object surface. Using a sparse set of landmarks, this paper finds a dense set of vertex correspondences across a set of 3D aortic root meshes. This is achieved by non-rigidly transforming a source mesh to a target mesh. Then, for every vertex on the target, a corresponding vertex on the deformed source is found, resulting in complete correspondence. A more accurate transformation results in better correspondence establishment, and our mesh registration experiments show an average Hausdorff distance of 3.65mm, and an average point-to-mesh distance of 0.41mm, i. e. within one voxel.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>IEEE Engineering in Medicine and Biology Society</journal><publisher>IEEE</publisher><keywords>Statistical shape model, shape analysis, registration, mesh processing</keywords><publishedDay>31</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2015</publishedYear><publishedDate>2015-08-31</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2016-06-13T14:52:25.3934507</lastEdited><Created>2015-07-01T10:32:44.3683555</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Robert</firstname><surname>Palmer</surname><order>1</order></author><author><firstname>Gary</firstname><surname>Tam</surname><order>2</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2016-06-13T14:52:25.3934507 v2 22236 2015-07-01 Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2015-07-01 SCS A statistical shape model that accurately generalizes a family of 3D shapes requires establishing correspondences across the set of shapes. However in 3D anatomical meshes, finding a sufficient number of landmarks to accurately describe the shape can be a challenge, and often only a few points are easily identifiable due to the smooth nature of the object surface. Using a sparse set of landmarks, this paper finds a dense set of vertex correspondences across a set of 3D aortic root meshes. This is achieved by non-rigidly transforming a source mesh to a target mesh. Then, for every vertex on the target, a corresponding vertex on the deformed source is found, resulting in complete correspondence. A more accurate transformation results in better correspondence establishment, and our mesh registration experiments show an average Hausdorff distance of 3.65mm, and an average point-to-mesh distance of 0.41mm, i. e. within one voxel. Conference Paper/Proceeding/Abstract IEEE Engineering in Medicine and Biology Society IEEE Statistical shape model, shape analysis, registration, mesh processing 31 8 2015 2015-08-31 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2016-06-13T14:52:25.3934507 2015-07-01T10:32:44.3683555 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Robert Palmer 1 Gary Tam 2 Xianghua Xie 0000-0002-2701-8660 3
title Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
spellingShingle Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
Xianghua Xie
title_short Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
title_full Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
title_fullStr Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
title_full_unstemmed Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
title_sort Finding Complete 3D Vertex Correspondence for Statistical Shape Modeling
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Robert Palmer
Gary Tam
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title IEEE Engineering in Medicine and Biology Society
publishDate 2015
institution Swansea University
publisher IEEE
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description A statistical shape model that accurately generalizes a family of 3D shapes requires establishing correspondences across the set of shapes. However in 3D anatomical meshes, finding a sufficient number of landmarks to accurately describe the shape can be a challenge, and often only a few points are easily identifiable due to the smooth nature of the object surface. Using a sparse set of landmarks, this paper finds a dense set of vertex correspondences across a set of 3D aortic root meshes. This is achieved by non-rigidly transforming a source mesh to a target mesh. Then, for every vertex on the target, a corresponding vertex on the deformed source is found, resulting in complete correspondence. A more accurate transformation results in better correspondence establishment, and our mesh registration experiments show an average Hausdorff distance of 3.65mm, and an average point-to-mesh distance of 0.41mm, i. e. within one voxel.
published_date 2015-08-31T03:26:28Z
_version_ 1763750957762478080
score 11.03559

Similar Items