1. Ktisis Cyprus University of Technology
  2. Cyprus University of Technology (Research Output)
  3. Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/29346
DC FieldValueLanguage
dc.contributor.authorLanitis, Andreas-
dc.contributor.authorSozou, Peter D.-
dc.contributor.authorTaylor, Chris J.-
dc.contributor.authorCootes, Timothy F.-
dc.contributor.authorDi Mauro, E. C.-
dc.date.accessioned2023-06-16T13:10:17Z-
dc.date.available2023-06-16T13:10:17Z-
dc.date.issued1996-08-25-
dc.identifier.citationProceedings of 13th International Conference on Pattern Recognition, 1996, pp. 266-270en_US
dc.identifier.urihttps://hdl.handle.net/20.500.14279/29346-
dc.description.abstractObjects of the same class often exhibit variation in shape. This shape variation has previously been modelled by means of point distribution models (PDMs) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. Here we present a new form of PDM, which uses a multilayer perceptron (MLP) to carry out nonlinear principal component analysis. We demonstrate that MLP-PDMs can model the shape variability in classes of object for which the linear model fails. We describe the use of MLP-PDMs in image search and present quantitative results for a practical application (face recognition), demonstrating the ability to locate image structures accurately starting from a very poor initial approximation to their pose and shape. © 1996 IEEE.en_US
dc.language.isoenen_US
dc.rights© Copyright IEEEen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/-
dc.subjectShapeen_US
dc.subjectPrincipal component analysisen_US
dc.subjectBiomedical imagingen_US
dc.subjectDeformable modelsen_US
dc.subjectMultilayer perceptronsen_US
dc.subjectTelluriumen_US
dc.subjectBiophysicsen_US
dc.subjectEducational institutionsen_US
dc.subjectEaren_US
dc.subjectFace recognitionen_US
dc.titleA general non-linear method for modelling shape and locating image objectsen_US
dc.typeConference Papersen_US
dc.collaborationUniversity College Londonen_US
dc.collaborationThe University of Manchesteren_US
dc.subject.categoryComputer and Information Sciencesen_US
dc.subject.categorySOCIAL SCIENCESen_US
dc.subject.categoryDesignen_US
dc.countryUnited Kingdomen_US
dc.subject.fieldEngineering and Technologyen_US
dc.subject.fieldSocial Sciencesen_US
dc.relation.conference13th International Conference on Pattern Recognitionen_US
dc.identifier.doi10.1109/ICPR.1996.547428en_US
dc.identifier.scopus2-s2.0-0001840218en
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/0001840218en
cut.common.academicyear1996-1997en_US
dc.identifier.external0001840218en
dc.identifier.spage266en_US
dc.identifier.epage270en_US
item.languageiso639-1en-
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.openairetypeconferenceObject-
item.openairecristypehttp://purl.org/coar/resource_type/c_c94f-
crisitem.author.deptDepartment of Multimedia and Graphic Arts-
crisitem.author.facultyFaculty of Fine and Applied Arts-
crisitem.author.orcid0000-0001-6841-8065-
crisitem.author.parentorgFaculty of Fine and Applied Arts-
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
CORE Recommender
Show simple item record

SCOPUSTM   
Citations 10

5
checked on Mar 14, 2024

Page view(s)

146
Last Week
1
Last month
2
checked on Oct 8, 2024

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons