Simple Techniques for an Efficient Recognition of Handwritten Characters Using a MLP

Journal of Intelligent Systems

Volumn 6, Issue 3-4, 1996, Pages 199-220

  Gioiello, G A M ^a   Tarantino, A ^a   Sorbello, F ^a   Vassallo, G ^b  

^a UNIVERSITY OF PALERMO   (Italy)

^b CRES Ctro Per Ricerce E   (Italy)

Author keywords

digital architecture; handwritten character recognition; high recognition speed; learning algorithms; multi layer perceptrons

Indexed keywords

COMPUTER ARCHITECTURE; COMPUTER SYSTEMS; LEARNING ALGORITHMS; LEARNING SYSTEMS; NEURAL NETWORKS;

HANDWRITTEN CHARACTER RECOGNITION; MULTILAYER PERCEPTRONS (MLP);

CHARACTER RECOGNITION;

EID: 0030361984     PISSN: 03341860     EISSN: None     Source Type: Journal    
DOI: 10.1515/JISYS.1996.6.3-4.199     Document Type: Article

References (19)

1. Kovàcs, M., Guerrieri, R., Baccarani, G. A novel metric for nearest-neighbor classification of hand-written digits, Proceedings of the 11th IAPR International Conference on Pattern Recognition; 1994; 96-100.
2. Knerr, S., Personnaz, L., Dreyfus, G. Handwritten digit recognition by neural networks with single-layer training, IEEE Trans, on Neural Networks, 3 (6), 962-968 (1992).
3. Zhang, M., Suen, C.Y., and Bui, T.D. An optimal pairing scheme in associative memory classifier and its application in character recognition, Proc. 11th IAPR International Conference on Pattern Recognition, 1994; 50-53.
4. Specht, D.F. Probabilistic neural networks, Neural Networks, 3 (1), 109-118 (1990).
5. Wilson, C.L. Evaluation of character recognition systems, IEEE Conference on Neural Networks for Signal Processing, III, IEEE, New York, 1993, pp. 485-496.
6. Minsky, M., Papert, S. Perceptions, MIT Press, Cambridge, MA, 1969.
7. Hornik, K. Multilayer feedforward networks are universal approximators, Neural Networks, 2, 359-366 (1989).
8. Powell, M.J.D. Restart procedures for the conjugate gradient method, Mathematical Programming, 12, 241-254 (1968).
9. Barnard, E., Casasent, D. Invariance and neural nets, IEEE Trans, on Neural Networks, 2(5), 498-509 (1991).
10. Giles, C.L., Griffin, R.D., Maxwell, T. Encoding geometric invariances in higher order neural networks, Neural Information Processing Systems, Anderson, D.Z. (ed.), Denver, CO, 1988; 301-309.
11. Simard, P., Le Cun, Y., Denker, J., and Victorri, B. An efficient algorithm for learning invariances in adaptive classifiers, Proc. 11th IAPR International Conference on Pattern Recognition, 1994; 651-655.
12. Gori, M., Tesi, A. On the problem of local minima in backpropagation, IEEE Trans, on PAMI, 14 (1), 76-85 (1992).
13. Stork, D.G., and Allen, J.D. How to solve the N-bit parity problem with two hidden units, Neural Networks, 5, 923-926 (1992).
14. Gorse, D., Shepherd, A., and Taylor, J.G. A classical algorithm for avoiding local minima, Neuroprose repository.
15. Lowe, D., and Webb, A.R. Optimized feature extraction and the Bayes Decision in feed-forward classifier networks, IEEE Trans, on PAMI, 13 (4), 355-364 (1991).
16. Wilkinson, R.A., Geist, J., Janet, S., Grother, P.J., Burges, C.J.C., Creecy, R., Hammond, B., Hull, J.J., Larsen, N.J., Vogl, T.P., and Wilson, C.L. The first optical character recognition systems conference, Technical Report NISTIR 4912, National Institute of Standards and Technology, 1992.
17. Gioiello, G.A.M., Vassallo, G., and Sorbello, F. A new fully digital neural network hardware architecture for binary valued pattern recognition, Proc. of the International Conference on Signal Processing Applications and Technology (ICSPAT), Boston, 1992; 705-708.
18. Gioiello, G.A.M., Vassallo, G., and Sorbello, F. A new fully digital feed-forward neural network for hand-written digits recognition, Proc. of VI Italian Workshop on Parallel Architectures and Neural Networks, World Scientific, 1993; 255-260.
19. Gioiello, G.A.M., Vassallo, G., Condemi, C., and Sorbello, F. A VLSI digital solution for hand-written digit recognition using a neural network, Proceedings of DSP & CAES-93, Nicosia, Cyprus, 1993; 141-145.