Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network

Handwritten word recognition has received a substantial amount of attention in the past. Neural Networks as well as discriminatively trained Maximum Margin Hidden Markov Models have emerged as cutting-edge alternatives to the commonly used Hidden Markov Models. In this paper, we analyze the combination of these classifiers with respect to their potential for improving recognition performance. It is shown that a significant improvement can in fact be achieved, although the individual recognizers are highly optimized state-of-the-art systems. Also, it is demonstrated that the diversity of the recognizers has a profound impact on the improvement that can be achieved by the combination.

[1]  Horst Bunke,et al.  Using a Statistical Language Model to Improve the Performance of an HMM-Based Cursive Handwriting Recognition System , 2001, Int. J. Pattern Recognit. Artif. Intell..

[2]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[3]  Lawrence K. Saul,et al.  Large Margin Hidden Markov Models for Automatic Speech Recognition , 2006, NIPS.

[4]  Li Deng,et al.  Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition , 2007 .

[5]  Horst Bunke,et al.  The IAM-database: an English sentence database for offline handwriting recognition , 2002, International Journal on Document Analysis and Recognition.

[6]  Paul D. Gader,et al.  Fusion of multiple handwritten word recognition techniques , 2001, Pattern Recognit. Lett..

[7]  Gyeonghwan Kim,et al.  An architecture for handwritten text recognition systems , 1999, International Journal on Document Analysis and Recognition.

[8]  Alessandro Vinciarelli,et al.  A survey on off-line Cursive Word Recognition , 2002, Pattern Recognit..

[9]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[10]  Gerhard Rigoll,et al.  Handwritten Address Recognition Using Hidden Markov Models , 2004, Reading and Learning.

[11]  Markus Junker,et al.  Reading and Learning , 2004, Lecture Notes in Computer Science.

[12]  Yong Sun,et al.  An Efficient Multimodal Language Processor for Parallel Input Strings in Multimodal Input Fusion , 2007 .

[13]  Ludmila I. Kuncheva,et al.  Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy , 2003, Machine Learning.

[14]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[15]  Thierry Artières,et al.  Large margin training for hidden Markov models with partially observed states , 2009, ICML '09.

[16]  Gerhard Rigoll,et al.  Combination of multiple classifiers for handwritten word recognition , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[17]  Horst Bunke,et al.  Ensembles of classifiers for handwritten word recognition , 2003, Document Analysis and Recognition.

[18]  Thierry Artières,et al.  2009 10th International Conference on Document Analysis and Recognition MAXIMUM MARGIN TRAINING OF GAUSSIAN HMMS FOR HANDWRITRING RECOGNITION , 2022 .