Scribal Attribution using a Novel 3-D Quill-Curvature Feature Histogram
2014 (English)In: 14th International Conference on Frontiers in Handwriting Recognition (ICFHR 2014), IEEE conference proceedings, 2014, p. 732-737Conference paper, Published paper (Refereed)
Abstract [en]
In this paper, we propose a novel pipeline for automated scribal attribution based on the Quill feature: 1) We compensate the Quill feature histogram for pen changes and page warping. 2) We add curvature as a third dimension in the feature histogram, to better separate characteristics like loops and lines. 3) We also investigate the use of several dissimilarity measures between the feature histograms. 4) We propose and evaluate semi-supervised learning for classification, to reduce the need of labeled samples. Our evaluation is performed on 1104 pages from a 15th century Swedish manuscript. It was chosen because it represents a significant part of Swedish manuscripts of said period. Our results show that only a few percent of the material need labelling for average precisions above 95%. Our novel curvature and registration extensions, together with semi-supervised learning, outperformed the current Quill feature.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2014. p. 732-737
Series
Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, ISSN 2167-6445 ; 2014 - December
Keywords [en]
Quill features, palaeography, classification, historical manuscripts, semi-supervised learning, writer identification
National Category
Computer and Information Sciences History and Archaeology
Identifiers
URN: urn:nbn:se:hig:diva-16607DOI: 10.1109/ICFHR.2014.128ISI: 000392822500120Scopus ID: 2-s2.0-84942246716ISBN: 978-1-4799-4335-7 (print)OAI: oai:DiVA.org:hig-16607DiVA, id: diva2:715439
Conference
14th International Conference on Frontiers in Handwriting Recognition (ICFHR), September 1-4, 2014, Crete, Greece
Projects
Sökning och informationsutvinning i stora samlingar av historiska handskrivna dokument
Funder
Swedish Research Council2014-05-052014-05-052018-03-22Bibliographically approved