Please use this identifier to cite or link to this item: https://hdl.handle.net/1959.11/9656
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPervouchine, Vladimiren
dc.contributor.authorLeedham, Grahamen
local.source.editorEditor(s): Horst Bunke, A Lawrence Spitzen
dc.date.accessioned2012-03-12T11:56:00Z-
dc.date.issued2006-
dc.identifier.citationDocument Analysis Systems VII: Proceedings of the 7th International Workshop, DAS 2006, p. 196-207en
dc.identifier.isbn9783540321408en
dc.identifier.isbn3540321403en
dc.identifier.urihttps://hdl.handle.net/1959.11/9656-
dc.description.abstractThis paper presents a study of 25 structural features extracted from samples of grapheme 'th' that correspond to features commonly used by forensic document examiners. Most of the features are extracted using vector skeletons produced by a specially developed skeletonisation algorithm. The methods of feature extraction are presented along with the results. Analysis of the usefulness of the features was conducted and three categories of features were identified: indispensable, partially relevant and irrelevant for determining the authorship of genuine unconstrained handwriting. The division was performed based on searching the optimal feature sets using the wrapper method. A constructive neural network was used as a classifier and a genetic algorithm was used to search for optimal feature sets. It is shown that structural micro features similar to those used in forensic document analysis do possess discriminative power. The results are also compared to those obtained in our preceding study, and it is shown that use of the vector skeletonisation allows both extraction of more structural features and improvement the feature extraction accuracy from 87% to 94%.en
dc.languageenen
dc.publisherSpringeren
dc.relation.ispartofDocument Analysis Systems VII: Proceedings of the 7th International Workshop, DAS 2006en
dc.relation.ispartofseriesLecture Notes in Computer Scienceen
dc.relation.isversionof1en
dc.titleExtraction and Analysis of Document Examiner Features from Vector Skeletons of Grapheme 'th'en
dc.typeBook Chapteren
dc.identifier.doi10.1007/11669487_18en
dc.subject.keywordsPattern Recognition and Data Miningen
dc.subject.keywordsExpert Systemsen
dc.subject.keywordsComputer Visionen
local.contributor.firstnameVladimiren
local.contributor.firstnameGrahamen
local.subject.for2008080105 Expert Systemsen
local.subject.for2008080109 Pattern Recognition and Data Miningen
local.subject.for2008080104 Computer Visionen
local.subject.seo2008890205 Information Processing Services (incl. Data Entry and Capture)en
local.subject.seo2008890299 Computer Software and Services not elsewhere classifieden
local.subject.seo2008890301 Electronic Information Storage and Retrieval Servicesen
local.identifier.epublicationsvtls086615484en
local.profile.schoolSchool of Science and Technologyen
local.profile.emailcleedham@une.edu.auen
local.output.categoryB1en
local.record.placeauen
local.record.institutionUniversity of New Englanden
local.identifier.epublicationsrecordune-20110909-122835en
local.publisher.placeBerlin, Germanyen
local.identifier.totalchapters33en
local.format.startpage196en
local.format.endpage207en
local.identifier.scopusid33745526432en
local.series.number3872en
local.contributor.lastnamePervouchineen
local.contributor.lastnameLeedhamen
dc.identifier.staffune-id:cleedhamen
local.profile.roleauthoren
local.profile.roleauthoren
local.identifier.unepublicationidune:9847en
dc.identifier.academiclevelAcademicen
local.title.maintitleExtraction and Analysis of Document Examiner Features from Vector Skeletons of Grapheme 'th'en
local.output.categorydescriptionB1 Chapter in a Scholarly Booken
local.relation.urlhttp://trove.nla.gov.au/work/19460408en
local.relation.urlhttp://books.google.com.au/books?id=Sz1fVXynE0oC&lpg=PR2&pg=PA196en
local.search.authorPervouchine, Vladimiren
local.search.authorLeedham, Grahamen
local.uneassociationUnknownen
local.year.published2006en
Appears in Collections:Book Chapter
Files in This Item:
3 files
File Description SizeFormat 
Show simple item record

SCOPUSTM   
Citations

5
checked on Dec 7, 2024

Page view(s)

988
checked on Mar 7, 2023
Google Media

Google ScholarTM

Check

Altmetric


Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.