Number of the records: 1  

Quality Improvement of Multispectral Images for Ancient Document Analysis

  1. 1.
    SYSNO ASEP0349637
    Document TypeC - Proceedings Paper (int. conf.)
    R&D Document TypeConference Paper
    TitleQuality Improvement of Multispectral Images for Ancient Document Analysis
    Author(s) Bianco, G. (IT)
    Bruno, F. (IT)
    Salerno, E. (IT)
    Tonazzini, A. (IT)
    Zitová, Barbara (UTIA-B) RID, ORCID
    Šroubek, Filip (UTIA-B) RID, ORCID
    Number of authors6
    Source TitleEUROMED 2010, 3rd International Conference dedicated on Digital Heritage. - Budapest : ARCHAEOLINGUA, 2010 / Ioannides M. ; Fellner D. ; Georgopoulos A. ; Hadjimitsis D. - ISBN 978-963-9911-16-1
    Pagess. 29-34
    Number of pages6 s.
    Action3rd International Conference dedicated on Digital Heritage
    Event date08.11.2010-13.11.2010
    VEvent locationLimasol
    CountryCY - Cyprus
    Event typeWRD
    Languageeng - English
    CountryHU - Hungary
    Keywordsdocument analysis ; deblurring ; image registration ; multispectral imaging ; blind source deconvolution
    Subject RIVJD - Computer Applications, Robotics
    R&D Projects1M0572 GA MŠMT - Ministry of Education, Youth and Sports (MEYS)
    GA102/08/1593 GA ČR - Czech Science Foundation (CSF)
    CEZAV0Z10750506 - UTIA-B (2005-2011)
    AnnotationIn this paper we will present a methodology to preliminarily register multispectral images od ancient documents in order to correct geometrical misalignments, and apply deblurring techniques to improve image quality for further document analysis, where sharper images are needed. Deblurring is performed with a multichannel approach, adapted to the case of multispectral acquisition. Statistical techniques of decorrelation are applied to improve the legibility of documents or to restore degraded features, extract individual context parts of the document, separate patterns as the main text from the background, or attenuate interferences due to the seeping of ink from verso-to-recto.
    WorkplaceInstitute of Information Theory and Automation
    ContactMarkéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
    Year of Publishing2011
Number of the records: 1  

  This site uses cookies to make them easier to browse. Learn more about how we use cookies.