Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition

This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.

[1]  Rohit Prasad,et al.  Multi-lingual Offline Handwriting Recognition Using Hidden Markov Models: A Script-Independent Approach , 2006, SACH.

[2]  Heiga Zen,et al.  Decision tree-based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling , 2003, INTERSPEECH.

[3]  Ch. Choisy.  Dynamic Handwritten Keyword Spotting Based on the NSHP-HMM , 2007 .

[4]  Kay-Fu Lee,et al.  Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition , 1990, IEEE Trans. Acoust. Speech Signal Process..

[5]  Salvador España Boquera,et al.  Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Haikal El Abed,et al.  ICDAR 2009 Handwriting Recognition Competition , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[7]  Juergen Luettin,et al.  A new normalization technique for cursive handwritten words , 2001, Pattern Recognit. Lett..

[8]  Nobuyuki Otsu,et al.  ATlreshold Selection Method fromGray-Level Histograms , 1979 .

[9]  Gernot A. Fink,et al.  On the Use of Context-Dependent Modeling Units for HMM-Based Offline Handwriting Recognition , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[10]  Chafic Mokbel,et al.  Combination of HMM-Based Classifiers for the Recognition of Arabic Handwritten Words , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[11]  Richard M. Schwartz,et al.  An Omnifont Open-Vocabulary OCR System for English and Arabic , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Horst Bunke,et al.  Automatic segmentation of the IAM off-line database for handwritten English text , 2002, Object recognition supported by user interaction for service robots.

[14]  Steve Young,et al.  The HTK book version 3.4 , 2006 .

[15]  Ching Y. Suen,et al.  Bank check processing system , 1996 .

[16]  Volkmar Frinken,et al.  Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network , 2009, CAIP.

[17]  Robert P. W. Duin,et al.  The combining classifier: to train or not to train? , 2002, Object recognition supported by user interaction for service robots.

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

[19]  Torsten Caesar,et al.  Sophisticated topology of hidden Markov models for cursive script recognition , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[20]  Chafic Mokbel,et al.  Combining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Emmanuel Augustin,et al.  RIMES evaluation campaign for handwritten mail processing , 2006 .

[22]  Ciprian Chelba,et al.  Mutual information phone clustering for decision tree induction , 2002, INTERSPEECH.

[23]  B. Juang,et al.  Context-dependent Phonetic Hidden Markov Models for Speaker-independent Continuous Speech Recognition , 2008 .

[24]  Gernot A. Fink,et al.  Markov models for offline handwriting recognition: a survey , 2009, International Journal on Document Analysis and Recognition (IJDAR).

[25]  C. Sirat.  Handwriting and the Writing Hand , 1994 .

[26]  Samy Bengio,et al.  Offline recognition of unconstrained handwritten texts using HMMs and statistical language models , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  H. Niemann,et al.  A HMM–based System for Recognition of Handwritten Address Words , 1999 .

[28]  Marc-Peter Schambach.  Model length adaptation of an HMM based cursive word recognition system , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[29]  Chafic Mokbel,et al.  Recognition of Arabic handwritten words using contextual character models , 2008, Electronic Imaging.

[30]  F. Perronnin,et al.  Local gradient histogram features for word spotting in unconstrained handwritten documents , 2008 .

[31]  Kai-Fu Lee,et al.  Context-independent phonetic hidden Markov models for speaker-independent continuous speech recognition , 1990 .

[32]  Fuad Rahman,et al.  Multiple classifier decision combination strategies for character recognition: A review , 2003, Document Analysis and Recognition.

[33]  Adam Krzyzak,et al.  A new courtesy amount recognition module of a Check Reading System , 2008, 2008 19th International Conference on Pattern Recognition.

[34]  Alejandro Héctor Toselli,et al.  Reconocimiento de texto manuscrito continuo , 2004 .

[35]  Nikos Fakotakis,et al.  An unconstrained handwriting recognition system , 2002, International Journal on Document Analysis and Recognition.

[36]  Christopher Kermorvant,et al.  Context-dependent HMM modeling using tree-based clustering for the recognition of handwritten words , 2010, Electronic Imaging.

[37]  Torsten Caesar,et al.  Preprocessing and feature extraction for a handwriting recognition system , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[38]  Volker Märgner.  Reject Rules And Combination Methods to Improve Arabic , 2008 .

[39]  Yves Lecourtier,et al.  Automatic reading of the literal amount of bank checks , 2005, Machine Vision and Applications.

[40]  Amar Gupta,et al.  Handwritten Bank Check Recognition of Courtesy Amounts , 2004 .

[41]  Réjean Plamondon,et al.  The generation of handwriting with delta-lognormal synergies , 1998, Biological Cybernetics.

[42]  Gernot A. Fink,et al.  Toward automatic video-based whiteboard reading , 2004, International Journal of Document Analysis and Recognition (IJDAR).

[43]  S. J. Young,et al.  Tree-based state tying for high accuracy acoustic modelling , 1994 .

[44]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[45]  Chafic Mokbel,et al.  Arabic handwriting recognition using baseline dependant features and hidden Markov modeling , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).