Abstract
The objective of this paper is to present the research activities of our group with respect to the development of an automatic form reading system. We aim to automate the registration of students by autonomously recognizing the handwritten information on application forms. An image of a digitized form is acquired, the relevant areas of the image are segmented and passed to a character recognition system. The complexity of the recognition is limited to isolated handwritten characters. We propose a prototype oriented method for the classification of the characters that seems to promise better results than classical feature-based techniques. The representation method of the characters are parametric curves. We try to adapt a prototype to a pattern in order to measure its deformation from the original prototype. Results are limited to conceptual proposals for the form reading system.
Preview
Unable to display preview. Download preview PDF.
References
Blackwell, K. T., Vogl, T. P., Hyman, S. D., Barbour, G. S., Alkon, D. L.: A new approach to hand-written character recognition. Pattern Recognition 25 (1992) 655–666
Boser, B., Guyon, I., Vapnik, I.: A training algorithm for optimal margin classifiers. in Proc. of COLT II, Philadelphia, USA (1992)
Breuel, T. M.: Handwritten character recognition using neural networks. Handbook of Neural Computation, IOP Publishing Ltd. and Oxford University Press (1997)
Burr, D. J.: A neural network digit recognizer. Proc. IEEE Conf. Systems, Man, and Cybernetics, Atlanta, GA (1986) 1621–1625
Burr, D. J.: Experiments on neural network recognition of spoken and written text. IEEE Trans. on Acoustics, Speech, and Signal Processing 36 (1988) 1162–1168
Duda, R. O., Hart, P. E.: Pattern Classification and Scene Analysis. J. Wiley & Sons, New York (1973)
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36 (1980) 193–202
Garris M. D., Blue J. L., Candela G. T., Grother P. J., Janet S. A., Wilson C. L.: NIST Form-based handprint recognition system. TR NISTTR 5959, U.S. Dept. of Commerce, NIST, Gaitherburg, MD 20899-001 (1997)
Hastie, T., Tibshirani, R.: Handwritten digit recognition via deformable prototypes. AT&T Bell Technical report (1994), URL: ftp://playfair.stanford.edu/reports/hastie/zip.ps.Z
Haykin, S.: Neural Networks-A Comprehensive Foundation. Macmillan College Publ. Comp. (1994)
Hecht-Nielsen, R.: Neurocomputing, Addison-Wesley. Reading, MA (1990)
Impedovo, S., Marangelli, B., Fanelli, A. M.: A Fourier descriptor set for recognizing nonstylized numerals. IEEE Trans. on Systems, Man, and Cybernetics 8 (1978) 640–645
Impedovo, S.: Plane curve classification through Fourier descriptors: An application to Arabic handwritten numeral recognition. Proc. 7th IAPR Int. Conf. on Pattern Recognition (1984) 1069–1072
Impedovo, S.: Fundamentals in Handwriting Recognition. Springer Verlag (1994)
Kressel U., Schfürmann J.: Pattern classification techniques based on function approximation. in Handbook on Optical Character Recognition and Document Analysis, H. Bunke and P.S.P. Wang (Eds.), World Scientific Publishing Company (1996)
Le Cun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, A., Hubbard, W., Jackel, L.: Handwritten digit recognition with a back-propagation network. In Touretzky, ed., Advances in Neural Information Processing Systems 2 (1990) Morgan Kaufman, Denver
Li, R. Y., Xu, M.: Character recognition using a fast neural-net classifier. Pattern Recognition Letters 13 (1992) 369–374
Malavija, A.: FOHRES: Fuzzy online handwriting recognition system. 2.nd Int. Conf. on Fuzzy Set Theory, Durham (1993)
Michie, D., Spiegelhalter, D. J., Taylor, C. F.: Machine Learning, Neural & Statistical Classification. Ellis Horwood (1994)
Newman, R.: The OSCAR project: An offline script and character recognition toolset. URL: http://hcslxl.essex.ac.uk/oscar/oscar.html
Reber, W. L., Lyman, J.: An artificial neural system design for rotation and scale invariant pattern recognition. in Proceedings of IEEE First International Conf. on Neural Networks, San Diego, CA, IV (1987) 277–283
Revow, M., Williams, C. K. I., Hinton, G. E.: Using generative models for handwritten digit recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 18 (1996) 592–606
Senior, A. W.: Off-line handwriting recognition: a review and experiments. Technical report CUED/F-INFENG/TR 105, Cambridge University Engineering Dept. Cambridge, England (1992)
Simard, P. Y., Le Cun, Denker, J. S.: Efficient pattern recognition using a new transformation distance. in Advances in Neural Information Processing Systems 2 (1993) Morgan Kaufman, San Mateo, USA
Suen, C. Y., Nadal, C., Legault, R., Mai T. A., Lam, L.: Computer recognition of unconstrained handwritten numerals. Proc. of the IEEE 80 (1992) 1162–1180
Tappert, C. C., Suen, C. Y., Wakahara, T.: The State of the Art in On-Line Handwriting Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 12 (1990) 787–808
Teh, C.-H., Chin, R. T.: On image analysis by the methods of moments. IEEE Trans. on Pattern Analysis and Machine Intelligence 10 (1988) 496–513
Wechsler, H., Zimmerman, G. L.: 2-D Invariant Object Recognition Using Distributed Associative Memory. IEEE Trans. on Pattern Analysis and Machine Intelligence 10 (1988) 811–821
William, C. K. I., Revow, M. D., Hinton, G. E.: Using a neural net to instantiate a deformable model. Advances in Neural Information Processing Systems 7 (1995) 965–972, The MIT Press
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rauber, T.W., de Souza, V.B., Rossetto, S. (1997). A system for automatic form reading. In: Murshed, N.A., Bortolozzi, F. (eds) Advances in Document Image Analysis. BSDIA 1997. Lecture Notes in Computer Science, vol 1339. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63791-5_24
Download citation
DOI: https://doi.org/10.1007/3-540-63791-5_24
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63791-2
Online ISBN: 978-3-540-69646-9
eBook Packages: Springer Book Archive