Handwriting automatic classification: Application to ancient Greek inscriptions

Papaodysseus, C; Rousopoulos, P; Arabadjis, D; Panopoulou, F; Panagopoulos, M

dc.contributor.author	Papaodysseus, C	en
dc.contributor.author	Rousopoulos, P	en
dc.contributor.author	Arabadjis, D	en
dc.contributor.author	Panopoulou, F	en
dc.contributor.author	Panagopoulos, M	en
dc.date.accessioned	2014-03-01T02:46:49Z
dc.date.available	2014-03-01T02:46:49Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32872
dc.subject	Ancient Greek inscription classification	en
dc.subject	Archaeology	en
dc.subject	Feature modeling	en
dc.subject	Handwriting analysis	en
dc.subject	Handwriting classification	en
dc.subject	Pattern recognition	en
dc.subject	Writer identification	en
dc.subject.other	Ancient Greeks	en
dc.subject.other	Archaeology	en
dc.subject.other	Feature modeling	en
dc.subject.other	Handwriting analysis	en
dc.subject.other	Handwriting classification	en
dc.subject.other	Writer identification	en
dc.subject.other	Feature extraction	en
dc.subject.other	History	en
dc.subject.other	Intelligent systems	en
dc.subject.other	Maximum likelihood	en
dc.subject.other	Statistical tests	en
dc.subject.other	Character recognition	en
dc.title	Handwriting automatic classification: Application to ancient Greek inscriptions	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/AIS.2010.5547045	en
heal.identifier.secondary	5547045	en
heal.identifier.secondary	http://dx.doi.org/10.1109/AIS.2010.5547045	en
heal.publicationDate	2010	en
heal.abstract	In this paper a new approach is presented for automatic writer identification. The approach is applied to the identification of the writer of ancient Greek inscriptions that in turn may offer precise and objective dating of the inscriptions content. Such a dating is crucial for the correct history writing. The methodology is based on the idea of creating an ideal representative of each alphabet symbol in each inscription, via proper fitting of all realizations of the specific symbol in this inscription. Next, geometric features for the ideal representative for each alphabet symbol are defined and extracted and corresponding statistical processing follows based on the computation of the mean value and variance of these characteristics. The decision for writer identification is made via pair-wise, feature based comparisons of the ideal representatives of the inscriptions. Each comparison is implemented by means of multiple statistical tests and an introduced maximum likelihood approach. The system was applied to 33 Athenian inscriptions of classical era which were correctly attributed to 8 different hands, namely with 100% success rate. © 2010 IEEE.	en
heal.journalName	IEEE 2010 International Conference on Autonomous and Intelligent Systems, AIS 2010	en
dc.identifier.doi	10.1109/AIS.2010.5547045	en