hh.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Exploiting Character Class Information in Forensic Writer Identification
Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain. (ATVS/Biometric Recognition Group)ORCID-id: 0000-0002-1400-346X
Universidad Autonoma de Madrid, Spain.
Universidad Autonoma de Madrid, Spain.
Universidad Autonoma de Madrid, Spain.
2011 (Engelska)Ingår i: Computational forensics: 4th International Workshop, IWCF 2010 Tokyo, Japan, November 11-12, 2010 : revised selected papers, Berlin: Springer Berlin/Heidelberg, 2011, s. 31-42Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Questioned document examination is extensively used by forensic specialists for criminal identification. This paper presents a writer recognition system based on contour features operating in identification mode (one-to-many) and working at the level of isolated characters. Individual characters of a writer are manually segmented and labeled by an expert as pertaining to one of 62 alphanumeric classes (10 numbers and 52 letters, including lowercase and uppercase letters), being the particular setup used by the forensic laboratory participating in this work. Three different scenarios for identity modeling are proposed, making use to a different degree of the class information provided by the alphanumeric samples. Results obtained on a database of 30 writers from real forensic documents show that the character class information given by the manual analysis provides a valuable source of improvement, justifying the significant amount of time spent in manual segmentation and labeling by the forensic specialist. © 2011 Springer-Verlag Berlin Heidelberg.

Ort, förlag, år, upplaga, sidor
Berlin: Springer Berlin/Heidelberg, 2011. s. 31-42
Serie
Lecture Notes in Computer Science, ISSN 0302-9743 ; 6540
Nationell ämneskategori
Signalbehandling
Identifikatorer
URN: urn:nbn:se:hh:diva-21232DOI: 10.1007/978-3-642-19376-7_3ISI: 000296680900003Scopus ID: 2-s2.0-79952259378ISBN: 978-364219375-0 OAI: oai:DiVA.org:hh-21232DiVA, id: diva2:589360
Konferens
4th International Workshop on Computational Forensics, IWCF 2010, Tokyo, Japan, 11-12 November, 2010
Tillgänglig från: 2013-01-17 Skapad: 2013-01-17 Senast uppdaterad: 2015-09-29Bibliografiskt granskad

Open Access i DiVA

fulltext(752 kB)1031 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 752 kBChecksumma SHA-512
b3c4d4b3853299daef0b65cf6f02b81bc00c88ae05199c598adea43854ea1ef0fe0a07f90734bf5d82f1603219d8896d7f16f49e98256db8b39d1ffdc8820993
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Person

Alonso-Fernandez, Fernando

Sök vidare i DiVA

Av författaren/redaktören
Alonso-Fernandez, Fernando
Signalbehandling

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 1031 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 378 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf