Full metadata record
DC FieldValueLanguage
dc.contributor.authorCao, Huaigu-
dc.contributor.authorManohar, Vasant-
dc.contributor.authorNatarajan, Prem-
dc.contributor.authorPrasad, Rohit-
dc.contributor.authorSubramanian, Krishna-
dc.description.abstractIn this paper, we describe several experiments in which we use a stochastic segment model (SSM) to improve offline handwriting recognition (OHR) performance. We use the SSM to re-rank (re-score) multiple decoder hypotheses. Then, a probabilistic multi-class SVM is trained to model stochastic segments obtained from force aligning transcriptions with the underlying image. We extract multiple features from the stochastic segments that are sensitive to larger context span to train the SVM. Our experiments show that using confidence scores from the trained SVM within the SSM framework can significantly improve OHR performance. We also show that OHR performance can be improved by using a combination of character-based and parts-of-Arabic-words (PAW)-based SSMs.en
dc.relation.ispartofFirst International Workshop on Frontiers in Arabic Handwritng Recognition, 2010en
dc.subjectConfidence scoresen
dc.subjectHidden Markov Modelingen
dc.subjectOptical Character Recognitionen
dc.subjectStochastic Segment Modelingen
dc.titleSubword-based Stochastic Segment Modeling for Offline Arabic Handwriting Recognitionen
dcterms.accessRightsopen access-
Appears in Collections:2010 - First International Workshop on Frontiers in Arabic Handwriting Recognition

Files in This Item:
File Description SizeFormat 
Subramanian.pdfDNB280.97 kBAdobe PDFView/Open

This item is protected by original copyright

Items in Eldorado are protected by copyright, with all rights reserved, unless otherwise indicated.