A Novel Connectionist System for Unconstrained Handwriting Recognition

作者: A. Graves , M. Liwicki , S. Fernandez , R. Bertolami , H. Bunke

DOI: 10.1109/TPAMI.2008.137

关键词: Machine learningHandwritingRecurrent neural networkArtificial neural networkLanguage modelArtificial intelligenceComputer scienceIntelligent character recognitionSpeech recognitionImage segmentationHidden Markov modelHandwriting recognitionSequence labelingWord recognitionCursive

摘要: … The offline data used in our experiments consists of gray… data, the normalizations for the offline data are applied to entire … of window positions in offline handwriting) are difficult to model …

参考文章(54)
SJ Young, NH Russell, Jhs Thornton, Token passing: a simple conceptual model for connected speech recognition systems University of Cambridge: Department of Engineering. ,(1989)
Darren Moore, The IDIAP Smart Meeting Room IDIAP. ,(2002)
Roger Garside, Eric Atwell, Stig Johansson, Geoffrey Leech, The tagged LOB Corpus : user's manual Norwegian Computing Center for the Humanities. ,(1986)
Gerhard Rigoll, Joachim Schenk, Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition international conference on frontiers in handwriting recognition. ,(2006)
A. Graves, J. Schmidhuber, Framewise phoneme classification with bidirectional LSTM networks international joint conference on neural network. ,vol. 4, pp. 2047- 2052 ,(2005) , 10.1109/IJCNN.2005.1556215
Herve A. Bourlard, Nelson Morgan, Connectionist Speech Recognition: A Hybrid Approach Kluwer Academic Publishers. ,(1993)
Jürgen Schmidhuber, Alex Graves, Santiago Fernández, Bidirectional LSTM networks for improved phoneme classification and recognition international conference on artificial neural networks. pp. 799- 804 ,(2005) , 10.1007/11550907_126