This Article 
 Bibliographic References 
 Add to: 
Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network
May 1994 (vol. 16 no. 5)
pp. 481-496

Because of large variations involved in handwritten words, the recognition problem is very difficult. Hidden Markov models (HMM) have been widely and successfully used in speech processing and recognition. Recently HMM has also been used with some success in recognizing handwritten words with presegmented letters. In this paper, a complete scheme for totally unconstrained handwritten word recognition based on a single contextual hidden Markov model type stochastic network is presented. Our scheme includes a morphology and heuristics based segmentation algorithm, a training algorithm that can adapt itself with the changing dictionary, and a modified Viterbi algorithm which searches for the (l+1)th globally best path based on the previous l best paths. Detailed experiments are carried out and successful recognition results are reported.

[1] A. Kundu, Y. He, and P. Bahl, "Recognition of handwritten word: First and second order hidden Markov model based approach,"Patt. Recognition, vol. 22, no. 3, pp. 283-297, 1989.
[2] C. C. Tappert, C. Y. Suen and T. Wakahara, "The state of the art in on-line hand-writing recognition,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, pp. 787-808, Aug. 1990.
[3] C. C. Tappert, "Adaptive on-line handwriting recognition," inProc. 7th Int. Conf. Pattern Recognit., Montreal, Canada, pp. 1004-1007, 1984, July-Aug.
[4] S. N. Srihari, Ed.,Computer Text Recognit. and Error Correction. Silver Spring, MD: IEEE Computer Society Press, 1984.
[5] J. R. Ullmann, "Advances character recognition," inApplications of Pattern Recognit.K.-S. Fu, Ed., CRC Press, Inc., 1986, ch. 9.
[6] J. Mantas, "An overview of character recognition methodologies,"Pattern Recognit. J., vol. 19, no. 6, 1986, pp. 425-430.
[7] V. K. Govindan, "Character recognition--A review,"Patt. Recogn., vol. 23. no. 7, pp. 671-683, 1990.
[8] R. Farag, "Word level recognition of cursive script,"IEEE Trans. Comput., vol. C-28, no. 2, pp. 172-175 1979.
[9] R. M. Bozinovic and S. N. Srihari, "Off-line cursive word recognition,"IEEE Trans. Pattern Anal., Machine Intell., vol. 11, pp. 68-83, Jan. 1989.
[10] L. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition,"Proc. IEEE, vol. 77, pp. 257-286, Feb. 1989.
[11] A. Ljolje and S. E. Levinson, "Development of an acoustic-phonetic hidden Markov model for continuous speech recognition,"IEEE Trans. Signal Processing, vol. 39, pp. 29-39, Jan. 1991.
[12] R. Nag, K. H. Wong, and F. Fallside, "Script recognition using hidden Markov model," inProc. IEEE Int. Conf. on Acoust., Speech, Signal Processing, 1986, pp. 2071-2074.
[13] A. Kundu, Y. He, and P. Bahl, "Word recognition and word hypothesis generation for handwritten script: A hidden Markov model based approach," inProc. IEEE Conf. on CVPR, 1988, pp. 457-462.
[14] R.M. Haralick, S.R. Sternberg, and X. Zhuang, "Image analysis using mathematical morphology,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, no. 4, pp. 532-550, 1987.
[15] J. Serra,Image Analysis and Mathematical Morphology. London, England: Academic Press Inc., 1982.
[16] R. C. Vogt,Automatic Generation of Morphological Set Recognition Algorithm. New York, NY: Springer-Verlag Inc., 1989.
[17] T. Pavlidis and D. Lee, "Residual analysis for feature extraction," inFrom Pixels to Features J. Simon, Ed., Amsterdam, The Netherlands, North-Holland, 1989, p. 219.
[18] J. C. Simon, "A complemental approach to feature detection," inFrom Pixels to FeaturesJ. Simon, Ed., Amsterdam. The Netherlands, North-Holland, 1989, p. 229.
[19] G. D. Forney, Jr., "The Viterbi algorithm," inIEEE Proc., vol. 61, pp. 268-278, Mar. 1973.
[20] L. R. Rabiner and B. H. Juang, "An introduction to hidden Markov models,"IEEE ASSP Mag., pp. 4-16, Jun. 1986.
[21] M.-Y. Chen, A. Kundu, and J. Zhou, "Off-line handwritten word recognition using a single contextual hidden Markov model," inProc. IEEE Comput. Vision and Pattern Recognit. (CVPR) Conf., Champaign, Illinois, June 1992, pp. 669-672.
[22] L. R. Bahl, F. Jelinek, and R. L. Mercer, "A maximum likelihood approach to continuous speech recognition,"IEEE Trans. Pattern Anal. Machine Intell., vol. 5, pp. 179-190, Mar. 1983.
[23] L. R. Bahl, P. F. Brown, P. V. de Souza and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," inProc. IEEE Int., Conf. on Acoust., Speech, Signal Processing, 1986, pp. 49-52.
[24] Y. Ephraim, A. Dembo, and L. R. Rabiner, "A minimum discrimination information approach for hidden Markov modeling,"IEEE Trans. Inform. Theory, vol. 35, pp. 1001-1013, Sept. 1989.
[25] H. Bourlard and C. J. Wellekens, "Links between Markov models and multilayer perceptrons,"IEEE Trans. Pattern Anal., Machine Intell., vol. 12, pp. 1167-1178, Dec. 1990.
[26] Y. Bengio, R. D. Mori, G. Flammia and R. Kompe, "Global optimization of a neural network-hidden Markov model hybrid,"IEEE Trans. Neural Networks, vol. 3, pp. 252-259 Mar. 1992.
[27] R. M. Gray, "Vector quantization,"IEEE ASSP Mag., vol. 1, pp. 4-29, Apr. 1984.
[28] R. Chellappa and S. Chatterjee, "Classification of textures using Gaussian Markov random fields,"IEEE Trans. Acoust. Speech Signal Processing, vol. ASSP-33, no. 4, pp. 959-963, 1985.
[29] C.-H. Teh and R. T. Chin, "On image analysis by the methods of moments,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, pp. 496-513, July 1988.
[30] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[31] Y. He, M.-Y. Chen, and A. Kundu, "Handwritten word recognition using HMM with adaptive length Viterbi algorithm," inProc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1992, pp. III. 153-156.
[32] H. F. Silverman and D. P. Morgan, "The application of dynamic programming to connected speech recognition,"IEEE ASSP Mag., pp. 7-25, July 1990.
[33] N. Seshadri and C.-E. W. Sundberg, "Generalized Viterbi algorithms for error detection with convolutional codes," inProc. IEEE Global Telecommunications Conf. (GLOCOM), Dallas, TX, Nov. 1989, pp. 1534-1538.
[34] R. Schwartz and Y. L. Chow, "The n-best algorithm: An efficient and exact procedure for finding thenmost likely sentence hypotheses," inProc. IEEE Int. Conf. on Acoust., Speech, Signal Processing, 1990, pp. 81-84.
[35] S. J. Raudys and A. K. Jain, "Small sample size effects in statistical pattern recognition: Recommendations for practitioners,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, March 1991, pp. 252-264.
[36] R. Wagner and M. Fischer, "The string-to-string correction problem,"J. ACM, vol. 21, pp. 168-173, 1974.
[37] S. A. Dudani, K. J. Breeding, and R. B. Mcghee, "Aircraft identification by moment invariants,"IEEE Trans. Comput., vol. C-26, pp. 39-45 Jan, 1977.
[38] Y.-S. Chen and W.-H. Hsu, "A new parallel thinning algorithm for binary image," inProc. National Comput. Symp., Taiwan, R.O.C., 1985.
[39] A. K. Dutta, "An experimental procedure for handwritten character recognition,"IEEE Trans. Comput., pp. 536-545, May, 1974.

Index Terms:
character recognition; hidden Markov models; mathematical morphology; heuristic programming; image segmentation; signal detection; off-line handwritten word recognition; hidden Markov model type stochastic network; totally unconstrained handwritten word recognition; morphology; heuristics based segmentation algorithm; training algorithm; Viterbi algorithm
M.Y. Chen, A. Kundu, J. Zhou, "Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 5, pp. 481-496, May 1994, doi:10.1109/34.291449
Usage of this product signifies your acceptance of the Terms of Use.