Color and Hyperspectral Image Segmentation for Historical Documents

Simple item page
dc.contributor.authorCiortan, Irina Mihaelaen_US
dc.contributor.authorDeborah, Hildaen_US
dc.contributor.authorGeorge, Sonyen_US
dc.contributor.authorHardeberg, Jon Yngveen_US
dc.contributor.editorGabriele Guidi and Roberto Scopigno and Pere Bruneten_US
dc.date.accessioned2016-01-06T08:15:27Z
dc.date.available2016-01-06T08:15:27Z
dc.date.issued2015en_US
dc.description.abstractSeveral historical documents from the collection of the National Library of Oslo were acquired using a hyperspectral scanner. While each of the documents has its specific characteristics, requiring different image preprocessing steps, the common goal for all documents is to increase their legibility. The aim of this study is to show the advantage of hyperspectral imaging compared to traditional color imaging, in particular for the task of ink separation using distance-based classification method.en_US
dc.description.sectionheadersFull Papers - Multispectral Imaging & Renderingen_US
dc.description.seriesinformationInternational Congress on Digital Heritage - Theme 2 - Computer Graphics And Interactionen_US
dc.identifier.doi10.1109/DigitalHeritage.2015.7413872en_US
dc.identifier.isbn978-1-5090-0048-7en_US
dc.identifier.urihttps://doi.org/10.1109/DigitalHeritage.2015.7413872en_US
dc.publisherIEEEen_US
dc.subjecthyperspectral imagingen_US
dc.subjectcultural heritageen_US
dc.subjecthistorical documentsen_US
dc.subjectclassificationen_US
dc.subjectsegmentationen_US
dc.subjectdistance functionen_US
dc.titleColor and Hyperspectral Image Segmentation for Historical Documentsen_US
Files
Collections
DH2015 - Track 2