This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Writer Adaptation for Online Handwriting Recognition
March 2002 (vol. 24 no. 3)
pp. 329-346

Writer-adaptation is the process of converting a writer-independent handwriting recognition system, which models the characteristics of a large group of writers, into a writer-dependent system, which is tuned for a particular writer. This adaptation has the potential of greatly increasing recognition accuracies, provided adequate models can be constructed for a particular writer. The limited amount of data a writer is willing to provide during the training phase constrains the complexity of these models. We show how the appropriate use of writer-independent models is important for the adaptation process. Our approach to writer-adaptation makes use of writer-independent writing style models (called lexemes), to identify the styles present in a particular writer's training data. These models are then updated using the writer's data. Lexemes that are present in the writer's data, but for which an inadequate number of training examples is available, are replaced with the writer-independent models. We demonstrate the feasibility of this approach on both isolated handwritten character recognition and unconstrained word recognition tasks. Our results show an average reduction in error rate of 16.3 percent for lowercase characters as compared against representing each of the writer's character classes with a single model. In addition, an average error rate reduction of 9.2 percent is shown on handwritten words using only a small amount of data for adaptation.

[1] http://www.vision.caltech.edu/mariomu/thesis/ thesis.ps.gzhttp:/www.apple.com, 2001.
[2] L.R. Bahl, F. Jelinek, and L.R. Mercer, “A Maximum Likelihood Approach to Continuous Speech Recognition,” IEEE Trans. Pattern Anaylsis and Machine Intelligence, vol. 5, pp. 179-190, May 1983.
[3] H.S.M. Beigi, K. Nathan, G.J. Clary, and J. Subrahmonia, “Size Normalization in On-Line Unconstrained Handwriting Recognition,” Proc. Int'l Conf. Image Processing, (ICIP '94), pp. 169-173, Nov. 1994.
[4] E.J. Bellegarda, J.R. Bellegarda, D. Nahamoo, and K.S. Nathan, “A Probabilistic Framework For On-Line Handwriting Recognition,” Proc. Third Ann. Int'l Workshop Fontiers of Handwriting Recognition, (IWFHR III), pp. 225-234, May 1993.
[5] S. Bercu and G. Lorette, “On-Line Handwritten Word Recognition: An Approach Based on Hidden Markov Models,” Proc. Third Ann. Int'l Workshop Fontiers of Handwriting Recognition, (IWFHR III), pp. 385-390, May 1993.
[6] K.F. Chan and D.Y. Yeung, “Elastic Structural Matching for On-Line Handwritten Alphanumeric Character Recognition,” Proc. 14th Int'l Conf. Pattern Recognition, vol. 2, pp. 1,121-1,123, Brisbane, Australia, Aug. 1998.
[7] S.D. Connell, “Online Handwriting Recognition Using Multiple Pattern Class Models,” PhD thesis, Dept. of Computer Science and Engineering, Michigan State Univ., May 2000.
[8] S.D. Connell and A.K. Jain, Learning Prototypes for On-Line Handwriting Digits Proc. 12th Int'l Conf. Pattern Recognition, pp. 182-184, 1994.
[9] S. Connell and A.K. Jain, “Template-Based Online Character Recognition,” Pattern Recognition. vol. 34, no. 1, pp. 1-14, Jan. 2001.
[10] http://www.research.ibm.comelectricInk, 2001.
[11] D.L. Davies and D.W. Bouldin, “A Cluster Separation Measure,” IEEE Trans. Pattern Anaylsis and Machine Intelligence, vol. 1, no. 2, pp. 224-227, Apr. 1979.
[12] G. D. Forney, “The Viterbi Algorithm,” Proc. IEEE, vol. 61, pp. 268-278, Mar. 1973,
[13] I. Guyon, P. Albrecht, Y. Le Cun, J.S. Denker, and W. Hubbard, “Design of a Neural Network Character Recognizer for a Touch Terminal,” Pattern Recognition, vol. 24, no. 2, pp. 105-119, 1991.
[14] J. Hu, A.S. Rosenthal, and M.K. Brown, “Combining High-Level Features with Sequential Local Features for On-Line Handwriting Recognition,” Proc. Italian Image Process. Conf., pp. 647-654, Sept. 1997.
[15] A.K. Jain and R.C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, N.J.: Prentice Hall, 1988.
[16] C.J. Leggetter and P. Woodland, “Speaker Adaptation of Continuous Density HMMs Using Multivariate Linear Regression,” Proc. Int'l Conf. Spoken Language Processing, (ICSLP '94), pp. 451-454, 1994.
[17] S. Madhvanath and V. Govindaraju, “Serial Classifier Combination for Handwritten Word Recognition,” Proc. Third Int'l Conf. Document Analysis and Recognition (ICDAR 95), Montreal, Canada, pp. 911-914, Aug. 1995.
[18] S. Manke, M. Finke, and A. Waibel, “NPen++: A Writer Independent, Large Vocabulary On-Line Cursive Handwriting Recognition System,” Proc. Third Int'l Conf. Document Analysis and Recognition (ICDAR '95), pp. 403-408, Montreal, Aug. 1995.
[19] S. Manke and U. Bodenhausen, “A Connectionist Recognizer for On-Line Cursive Handwriting Recognition,” Proc. Int'l Conf. Acoustics, Speech and Signal Processing (ICASSP '94) vol. 2, pp. 633-636, 1994.
[20] K. Mohiuddin and J. Mao, “A Comparative Study of Different Classifiers For Handprinted Character Recognition,” Pattern Recognition in Practice IV, E.S. Gelsema and L.N. Kanal, eds., pp. 437-448, The Netherlands: Elsevier Science, 1994.
[21] K.S. Nathan, H.S.M. Beigi, J. Subrahmonia, G.J. Clary, and H. Maruyama, “Realtime On-Line Unconstrained Handwriting Recognition Using Statistical Methods,” Proc. Int'l Conf. Accoustics, Speech, and Signal Processing, pp. 2,619-2,622, Detroit, 1995.
[22] K.S. Nathan, J.R. Bellegarda, D. Namahoo, and E.J. Bellegarda, “On-Line handwriting Recognition Using Continuous Parameter Hidden Markov Models,” Proc. Int'l Conf. Acoustics, Speech and Signal Processing (ICASSP '93), vol. 5, pp. 121-124, 1993.
[23] http:/www.paragraph.com, 2001.
[24] M.P. Perrone and S.D. Connell, “K-Means Clustering For Hidden Markov Models,” Proc. Seventh Int'l Workshop Fontiers of Handwriting Recognition, Sept. 2000.
[25] R. Plamondon and F.J. Maarse, “An Evaluation of Motor Models of Handwriting,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 5, pp. 1,060-1,072, 1989.
[26] R. Plamondon and S.N. Srihari, On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 63-84, Jan. 2000.
[27] L. Prevost and M. Milgram, “Automatic Allograph Selection and Multiple Classification for Totally Unconstrained Handwritten Character Recognition,” Proc. 14th Int'l Conf. Pattern Recognition (ICPR), pp. 381-383, Aug. 1998.
[28] G. Rigoll, A. Kosmala, and D. Willett, “A New Hybrid Approach to Large Vocabulary Cursive Handwriting Recognition,” Proc. 14th Int'l Conf. Pattern Recognition, vol. 2, pp. 1,512-1,514, Brisbane, Australia, Aug. 1998.
[29] P. Scattolin and A. Krzyzak, “Weighted Elastic Matching Method for Recognition of Handwritten Numerals,” Proc. Conf. Vision Interface '94, pp. 178-185, 1994.
[30] M. Schenkel, I. Guyon, and D. Henderson, "On-Line Cursive Script Recognition Using Time Delay Neural Networks and Hidden Markov Models," Int'l Conf. Acoustics, Speech and Signal Processing, vol. 2, pp. 637-640, 1994.
[31] L.R.B. Schomaker, E.H. Helsper, H.L. Teulings, and G.H. Abbink, “Adaptive Recognition of Online, Cursive Handwriting,” Proc. Sixth Int'l Conf. Handwriting and Drawing (ICOHD '93), pp. 19-21, July 1993.
[32] G. Seni, R.K. Srihari, and N. Nasrabadi, “Large Vocabulary Recognition of On-Line Handwritten Cursive Words,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 7, pp. 757-762, July 1996.
[33] A.W. Senior, J. Subrahmonia, and K. Nathan, “Duration Modeling Results For An On-Line Handwriting Recognizer,” Proc. Int'l Conf. Acoustics, Speech and Signal Processing (ICASSP '96), pp. 3483-3486, May 1996
[34] J. Subrahmonia, K. Nathan, M. Perrone, “Writer Dependent Recognition of On-line Unconstrained Handwriting,” Proc. Int'l Conf. Acoustics, Speech and Signal Processing (ICASSP '96), vol. 6, pp. 3478-3481, 1996.
[35] C.C. Tappert, “Adaptive On-Line Handwriting Recognition,” Proc. Seventh Int'l Conf. Pattern Recognition, pp. 1004-1007, July/Aug. 1984.
[36] C.C. Tappert, C.Y. Suen, and T. Wakahara, “The State of the Art in On-Line Handwriting Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 179-190, Aug. 1990.
[37] T. Wakahara and K. Odaka, “Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 12, pp. 1332-1341, Dec. 1998.
[38] K. Yamasaki, “Automatic Allograph Categorization Based on Stroke Clustering for On-Line Handwritten Japanese Character Recognition,” Proc. 14th Int'l Conf. Pattern Recognition (ICPR), pp. 1150-1152, Aug. 1998.

Index Terms:
online handwriting, writer-adaptation, writing style modeling, hidden Markov models, lexemes
Citation:
S.D. Connell, A.K. Jain, "Writer Adaptation for Online Handwriting Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 329-346, March 2002, doi:10.1109/34.990135
Usage of this product signifies your acceptance of the Terms of Use.