| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Postprocessing of Recognized Strings Using Nonstationary Markovian Models
October 1999 (vol. 21 no. 10)
pp. 990-999
Abstract—This paper presents Nonstationary Markovian Models and their application to recognition of strings of tokens. Domain specific knowledge is brought to bear on the application of recognizing zip Codes in the U.S. mailstream by the use of postal directory files. These files provide a wealth of information on the delivery points (mailstops) corresponding to each zip code. This data feeds into the models as n-grams, statistics that are seamlessly integrated with recognition scores of digit images. An especially interesting facet of the model is its ability to excite and inhibit certain positions in the n-grams leading to the familiar area of Markov Random Fields. The authors have previously described elsewhere [[2]] a methodology for deriving probability values from recognizer scores. These probability measures allow the Markov chain to be constructed in a truly Bayesian framework. We empirically illustrate the success of Markovian modeling in postprocessing applications of string recognition. We present the recognition accuracy of the different models on a set of 20,000 zip codes. The performance is superior to the present system which ignores all contextual information and simply relies on the recognition scores of the digit recognizers.
[1] 990 T.W. Anderson and L.A. Goodman, “Statistical Inference about Markov Chains,” Ann. Math Statistics, vol. 28, pp. 89-110, 1957.[2] D. Bouchaffra, V. Govindaraju, and S. Srihari, “A Methodology for Deriving Probabilistic Correctness Measures from Recognizers,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 930-935, Santa Barbara, Calif., 1998.[3] D. Bouchaffra, E. Koontz, V. Kripasundar, R.K. Srihari, and S.N. Srihari, “Integrating Signal and Language Context to Improve Handwritten Phrase Recognition: Alternative Approaches,” Proc. Sixth Int'l Workshop Artificial Intelligence and Statistics, Ft. Lauderdale, Fla., Jan. 1997.[4] D. Bouchaffra, E. Koontz, V. Kripasundar, and R.K. Srihari, “Incorporating Diverse Information Sources in Handwriting Recognition PostProcessing,” Int'l J. Imaging Systems and Technology, vol. 7, no. 4, June 1996.[5] P.F. Brown, V.J. Della Pietra, P.V. deSouza, J.C. Lai, and R.L. Mercer, “Class-Based n-Grams Models of Natural Language,” Computational Linguistics, vol. 18, no. 4, pp. 467-479, 1992.[6] R.L. Dobrushin, “The Description of Random Fields by Means of Conditional Probabilities and Conditions of Its Regularity,” Theory Probability Applications, vol. 13, pp. 197-224, 1968.[7] J. Favata and G. Srikantan, “A Multiple Feature/Resolution Approach to Handprinted Digit and Character Recognition,” Int'l J. Imaging Systems and Technology, vol. 7, pp. 304-311, 1996.[8] V. Govindaraju, A. Shekhawat, and S. Srihari, “Determining Delivery Point Code in US Mailstream,” Proc. IWFHR III, 1993.[9] T.M. Ha and H. Bunke, “Off-Line Handwritten Numeral String Recognition,” internal report, Univ. of Berne, Institut für Informatik und Angewandte Mathematik Neubrückstr, Switzerland, 1997.[10] J.J. Hull, “Incorporating Language Syntax in Visual Text Recognition with a Statistical Model,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 12, pp. 1,251-1,256, Dec. 1996.[11] A. Jessop, Informed Assessments. Ellis Horwood, 1990.[12] G. Kim and V. Govindaraju, “A Lexicon Driven Approach to Handwritten Word Recognition for Real Time Applications,“ IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 366-379, Apr. 1997.[13] G. Kim and V. Govindaraju, “A Lexicon Driven Approach to Handwritten Word Recognition for Real Time Applications,“ IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 366-379, Apr. 1997.[14] F. Kimura and M. Sridhar, “Handwritten Numerical Recognition Based on Multiple Algorithms,” Pattern Recognition, vol. 24, no. 10, pp. 969-983, 1991.[15] A. Kundu and Y. He, “On Optimal Order in Modeling Sequence of Letters in Words in Common Language as a Markov Chain,” Pattern Recognition, vol. 24, no. 7, pp. 603-608, 1991.[16] M.Y. Chen, A. Kundu, and J. Zhou, “Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 5, pp. 481-496, 1994.[17] C. Oliver et al., “Optimal Order of Markov Models Applied to Bankchecks,” Int'l J. Pattern Recognition and Artificial Intelligence, vol. 19, no. 4, 1997.[18] L.R. Rabiner, “Tutorial on Hidden Markov Model and Selected Applications in Speech Recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257-285, 1989.[19] Z. Shi and V. Govindaraju, “Segmentation and Recognition of Connected Handwritten Numeral Strings,” Pattern Recognition, vol. 30, pp. 1,501-1,504, 1997.[20] R. Shingal and G. Toussaint, “Experiments in Text Recognition with the Modified Viterbi Algorithm,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 1, no. 2, 1979.[21] M. Shridhar and A. Badreldin, “Context-Directed Segmentation Algorithm for Handwritten Numeral Strings,” Image Vision Computing, vol. 5, no. 1, pp. 3-9, 1987.[22] L. Lam and C.Y. Suen, "Structural Classification and Relaxation Matching of Totally Unconstrained Handwritten Zip-Code Numbers," Pattern Recognition, vol. 21, no. 1, pp. 19-31, 1988.[23] C.Y. Suen, “Computer Recognition of Unconstrained Handwritten Numerals,” Proc. IEEE, vol. 80, pp. 1,162-1,180, 1992.[24] R. Yee, M. Teo, and R. Shinghal, “A Hybrid Classifier for Recognizing Handwritten Numerals,” Proc. Fourth Int'l Conf. Document Analysis and Recognition, Ulm, Germany, Aug. 1997.[25] J. Zhou, Q. Gan, and C. Suen, “A High Performance Hand-Printed Numeral Recognition System,” Proc. Fourth Int'l Conf. Document Analysis and Recognition, Ulm, Germany, Aug. 1997.
Index Terms:
Nonstationary hidden Markov models, zip code recognition, postprocessing, class conditional probability, Markov random fields.
Citation:
Djamel Bouchaffra, Venu Govindaraju, Sargur N. Srihari, "Postprocessing of Recognized Strings Using Nonstationary Markovian Models," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 10, pp. 990-999, Oct. 1999, doi:10.1109/34.799906
