Neural network-based systems for handprint OCR applications

IEEE Transactions on Image Processing

Volumn 7, Issue 8, 1998, Pages 1097-1112

  Garris, Michael D ^b   Wilson, Charles L ^a,b   Blue, James L ^b  

^a IEEE

^b NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY   (United States)

Author keywords

Boltzmann weight pruning; Handprint; Multi layer perceptron; Neural networks; Optical character recognition; Public domain

Indexed keywords

COMPUTATIONAL METHODS; CONSTRAINT THEORY; IMAGE QUALITY; NEURAL NETWORKS; OPTICAL CHARACTER RECOGNITION;

BOLTZMANN WEIGHT PRUNING; HANDPRINT RECOGNITION;

PATTERN RECOGNITION SYSTEMS;

EID: 0032139746     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/83.704304     Document Type: Article

References (64)

1. K. Han and I. K. Sethi, "Off-line cursive handwriting segmentation," in Proc. Third Int. Conf. Document Analysis and Recognition, Aug. 1995, pp. 894-896.
2. A. Negi, K. S. Swaroop, and A. Agarwal, "A correspondence based approach to segmentation of cursive words," in Proc. Third Int. Conf. Document Analysis and Recognition, Montreal, P.Q., Canada, Aug. 1995, pp. 1034-1037.
3. J. T. Favata and S. N. Srihari, "Off line recognition of handwritten cursive words," in Proc. Conf. Machine Vision Applications in Character Recognition and Industrial Inspection, San Jose, CA, SPIE, 1992, vol. 1661, pp. 224-234.
4. S. N. Srihari, "Name and address block reader system for tax form processing," in Proc. Third Int. Conf. Document Analysis and Recognition, Montreal, P.Q., Canada, 1995, pp. 5-10.
5. R. A. Wilkinson et al., "The first optical character recognition systems conference," Tech. Rep. NISTIR 4912, Nat. Inst. Standards Technol., Aug. 1992.
6. J. Geist et al., "The second census optical character recognition systems conference," Tech. Rep. NISTIR 5452, Nat. Inst. Standards Technol., May 1994.
7. J. S. Denker, et al., "Neural network recognizer for hand-written zip code digits," in Advances in Neural Information Processing Systems, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989, pp. 323-331.
8. Y. LeCun, J. S. Denker, and S. A. Solla, "Optimal brain damage," in Advances in Neural Information Processing Systems, vol. 2, D. S. Touretzky, Ed. Morgan Kaufman, 1990, pp. 598-605.
9. G. L. Martin and J. A. Pittman, "Recognizing hand-printed letters and digits using backpropagation learning," Neural Comput., vol. 3, pp. 258-267, Summer 1991.
10. G. Seni, R. K. Srihari, and N. Nasrabadi, "Large vocabulary recognition of on-line handwritten cursive words," IEEE Trans. Pattern Anal. Machine Intell., vol. 18, pp. 757-762, 1996.
11. O. D. Trier, A. K. Jain, and T. Taxt, "Feature extraction methods for character recognition: A survey," Pattern Recognit., vol. 29, pp. 641-662, 1996.
12. P. J. Grother, "Karhunen Loéve feature extraction for neural handwritten character recognition," in Proc. Conf. Applications of Artificial Neural Networks III, Orlando, FL, Apr. 1992, vol. 1709, pp. 155-166.
13. M. D. Garris et al., "NIST form-based handprint recognition system," Tech. Rep. NISTIR 5469, Nat. Inst. Standards Technol., July 1994.
14. M. D. Garris, R. A. Wilkinson, and C. L. Wilson, "Analysis of a biologically motivated neural network for character recognition," in Proc. Conf. Analysis of Neural Network Applications, May 1991, pp. 160-175.
15. A. Shustorovich, "A subspace projection approach to feature extraction: The two-dimensional Gabor transform for character recognition," Neural Networks, vol. 7, pp. 1295-1301, 1994.
16. G. E. Hinton and C. K. I. Williams, "Adaptive elastic models for hand-printed character recognition," in Advances in Neural Information Processing Systems, vol. 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. Morgan Kaufmann, 1992, pp. 512-519.
17. C. K. I. Williams, M. D. Revow, and G. E. Hinton, "Using a neural net to instantiate a deformable model," in Advances in Neural Information Processing Systems, vol. 7, G. Tesauro, D. S. Touretzky, and T. Leen, Eds. Morgan Kaufmann, 1995, pp. 965-972.
18. CEDAR CDROM 1. Handwritten Cities, States, ZIP Codes, Digits, and Alphabetic Characters Database, United States Postal Service Office of Advanced Technology, 1992.
19. I. Guyon, V. N. Vapnick, B. E. Boser, L. Y. Botton, and S. A. Solla, "Structural risk minimization for character recognition," in Advances in Neural Information Processing Systems, J. E. Moody, S. J. Hanson, and R. P. Lippmann Eds. San Mateo, CA: Morgan Kauffman, vol. 4, pp. 471-479, 1992.
20. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, pp. 318-362.
21. Y. LeCun, et al., "Back propagation applied to handwritten zip code recognition," Neural Comput., vol. 1, pp. 541-551, 1989.
22. H. Schwenk and M. Milgram, "Transformation invariant autoassociation with application to handwritten character recognition," in Advances in Neural Information Processing Systems, vol. 7, G. Tesauro, D. S. Touretzky, and T. Leen, Eds. San Mateo, CA: Morgan Kaufmann, 1995, pp. 991-1006.
23. P. Simard, Y. Le Cun, and J. S. Denker, "Efficient pattern recognition using a new transformation distance," in Advances in Neural Information Processing Systems, vol. 5, S. J. Hanson, J. D. Cowan, and C. L. Giles, Eds. San Mateo, CA: Morgan Kaufmann, 1993, pp. 50-58.
24. O. Matan, et al., "Multi-digit recognition using a space displacement neural network," in Advances in Neural Information Processing Systems, vol. 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo, CA: Morgan Kaufmann, 1992, pp. 488-495.
25. J. D. Keeler, D. E. Rumelhart, and W. K. Leow, "Integrated segmentation and recognition of hand-printed numerals," in Advances in Neural Information Processing Systems, vol. 3, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1991, pp. 557-563.
26. J. D. Keeler and D. E. Rumelhart, "A self-organizing integrated segmentation and recognition neural net," in Advances in Neural Information Processing Systems, vol. 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo, CA: Morgan Kaufmann, 1992, pp. 496-503.
27. S. Haykin, Neural Networks. Englewood Cliffs, NJ: Prentice-Hall, 1993.
28. S. W. Lee and E. J. Lee, "Integrated segmentation and recognition of connected handwritten characters with recurrent neural network," in Proc. Third Int. Conf. Document Analysis and Recognition, Montreal, P.Q., Canada, Aug. 1995, pp. 413-416.
29. D. J. Hepp, "Recognition of handprinted and cursive words by finding feature correspondences," in Proc. Conf. Document Recognition, San Jose, CA, 1994, pp. 47-58.
30. M. J. Ganzberger et al., "Matching database records to handwritten text," in Conf. Document Recognition, San Jose, CA, 1994, vol. 2181, pp. 66-75.
31. G. L. Martin, "Centered-object integrated segmentation and recognition of overlapping handprinted characters," Neural Comput., vol. 5, pp. 419-429, May 1993.
32. G. L. Martin and J. Talley, "Recognizing handwritten phrases from U.S. Census forms by combining neural networks and dynamic programming," J. Artif. Neural Networks, vol. 2, pp. 167-194, 1995.
33. A. Shustorovich and C. W. Thrasher, "Neural network positioning and classification of handwritten characters," Neural Networks, vol. 6, pp. 685-693, 1996.
34. S. Ullman, The Interpretation of Visual Motion. Cambridge, MA: MIT Press, 1979.
35. G. L. Martin, "Centered-object integrated segmentation and recognition for visual character recognition," in Advances in Neural Information Processing Systems, vol. 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo, CA: Morgan Kaufmann, 1992, pp. 504-511.
36. K. Fukushima, "Connected character recognition with a neural networks," in Proc. Int. Conf. Document Analysis and Recognition, Montreal, P.Q., Canada, Aug. 1995, pp. 240-242.
37. H. Drucker, R. Schapire, and P. Simard, "Boosting performance in neural networks," Int. J. Pattern Recognit. Artif. Intell., vol. 7, pp. 705-719, 1993.
38. J. L. Blue, et al., "Evaluation of pattern classifiers for fingerprint and OCR applications," Pattern Recognit., vol. 27, pp. 485-501, 1994.
39. C. L. Wilson, P. J. Grother, and C. S. Barnes, "Binary decision clustering for neural network based optical character recognition," Pattern Recognit., vol. 29, pp. 425-437, 1996.
40. K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed. New York: Academic, 1990.
41. L. K. Hansen, C. Liisberg, and P. Salamon, "The error-reject tradeoff," computer reprint, 1995.
42. J. L. Blue and P. J. Grother, "Training feed forward networks using conjugate gradients," in Proc. Conf. Character Recognition and Digitizer Technologies, San Jose, CA, Feb. 1992, pp. 179-190.
43. S. Saarinen, R. Bramley, and G. Cybenko, "Ill-conditioning in neural network training problems," SIAM J. Sci. Comput., vol. 14, pp. 693-714, 1993.
44. J. Carr, Applications of Centre Manifold Theory. Berlin, Germany: Springer-Verlag, 1981.
45. M. W. Hirsch and S. Smale, Differential Equations, Dynamical Systems, and Linear Algebra. New York: Academic, 1974.
46. J. Guckenheimer and P. Holmes, Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields. Berlin, Germany: Springer-Verlag, 1983.
47. J. Sijbrand, "Properties of center manifolds," Trans. Amer. Math. Soc., vol. 289, pp. 431-469, June 1985.
48. S. N. Chow and J. K. Hale, Methods of Bifurcation Theory. Berlin, Germany: Springer-Verlag, 1982.
49. F. Girosi, M. Jones, and T. Poggio, "Regularization theory and neural networks architectures," Neural Comput., vol. 7, pp. 219-269, 1995.
50. D. H. Ackley, G. E. Hinton, and T. J. Sejnowski, "A learning algorithm for Botlzmann machines," Cogn. Sci., vol. 9, pp. 147-169, 1985.
51. F. L. Alt, "Digital pattern recognition by moments," in Optical Character Recognition, G. L. Fischer et al., Eds. McGreger & Werner, 1962, pp. 159-179.
52. O. M. Omidvar and C. L. Wilson, "Information content in neural net optimization," J. Connection Sci., vol. 6, pp. 91-103, 1993.
53. C. L. Wilson, J. L. Blue, and O. M. Omidvar, "Training dynamics and neural network performance," Neural Networks, vol. 10, pp. 907-923, 1997.
54. U. Grenander, General Pattern Theory. Oxford, U.K.: Oxford Univ. Press, 1993.
55. C. L. Wilson, et al., "Design, integration, and evaluation of form-based handprint and OCR systems," Tech. Rep. NISTIR 5932, Nat. Inst. Standards Technol., Dec. 1996.
56. P. J. Grother, "Handprinted forms and characters database," Tech. Rep. Special Database 19, HFCD, Nat. Inst. Standards Technol., Mar. 1995.
57. M. D. Garris and P. J. Grother, "Generalized form registration using structure-based techniques," in Proc. Fifth Ann. Symp. Document Analysis and Information Retrieval, Las Vegas, NV, Apr. 1996, pp. 321-334.
58. M. D. Garris, "Intelligent form removal with character stroke preservation," in Proc. Conf. Document Recognition III, San Jose, CA, Feb. 1996, pp. 321-332.
59. _, "Unconstrained handprint recognition using a limited lexicon," Tech. Rep. NISTIR 5310, Nat. Inst. Standards Technol., 1993.
60. _, "Teaching computers to read handprinted paragraphs," Tech. Rep. NISTIR 5894, Nat. Inst. Standards Technol., Sept. 1996.
61. _, "Component-based handprint segmentation using adaptive writing style model," Tech. Rep. NISTIR 5843, Nat. Inst. Standards Technol., June 1996.
62. C. L. Wilson, "Effectiveness of feature and classifier algorithms in character recognition systems," in Proc. Conf. Character Recognition Technologies, D. P. D'Amato, Ed., San Jose, CA, 1993, vol. 1906.
63. M. D. Garris and S. A. Janet, "NIST scoring package user's guide release 1.0," Tech. Rep. NISTIR 4950, Nat. Inst. Standards Technol., Oct. 1992.
64. P. J. Grother, "Cross validation comparison of NIST OCR databases," in Proc. Conf. Character Recognition Technologies, D. P. D'Amato, Ed., San Jose, CA, 1993, pp. 296-307.