CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2009 vol.31 Issue No.05 - May
Issue No.05 - May (2009 vol.31)
Alex Graves , Technische Universität, München, Munich
Marcus Liwicki , Research Group Knowledge Management, DFKI-German Research Center for Artificial Intelligence, Kaiserslautern
Santiago Fernández , IDSIA, Switzerland
Roman Bertolami , Institute of Computer Science and Applied Mathematics, Research Group on Computer Vision and Artificial Intelligence, Bern
Horst Bunke , Institute of Computer Science and Applied Mathematics, Research Group on Computer Vision and Artificial Intelligence, Bern
Jürgen Schmidhuber , Technische Universität, München, Munich
Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and handwriting recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained handwriting databases, our approach achieves word recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance.
Handwriting recognition, online handwriting, offline handwriting, connectionist temporal classification, bidirectional long short-term memory, recurrent neural networks, hidden Markov model.
Alex Graves, Marcus Liwicki, Santiago Fernández, Roman Bertolami, Horst Bunke, Jürgen Schmidhuber, "A Novel Connectionist System for Unconstrained Handwriting Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 5, pp. 855-868, May 2009, doi:10.1109/TPAMI.2008.137