This Article 
 Bibliographic References 
 Add to: 
Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network
June 1996 (vol. 18 no. 6)
pp. 648-652

Abstract—In this paper, we propose a new scheme for off-line recognition of totally unconstrained handwritten numerals using a simple multilayer cluster neural network trained with the back propagation algorithm and show that the use of genetic algorithms avoids the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique, and improves the recognition rates. In the proposed scheme, Kirsch masks are adopted for extracting feature vectors and a three-layer cluster neural network with five independent subnetworks is developed for classifying similar numerals efficiently. In order to verify the performance of the proposed multilayer cluster neural network, experiments with handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. For the case of determining the initial weights using a genetic algorithm, 97.10%, 99.12%, and 99.40% correct recognition rates were obtained, respectively.

[1] C.Y. Suen, “Computer Recognition of Unconstrained Handwritten Numerals,” Proc. IEEE, vol. 80, pp. 1,162-1,180, 1992.
[2] J. Rocha and T. Pavlidis, "A Shape Analysis Model With Applications to a Character Recognition System," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, pp. 393-404, 1994.
[3] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Internal Representations by Error Propagation," Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations, D.E. Rumelhart and J.L. McClelland et al., eds., chapter 8, pp. 318-362.Cambridge, Mass.: MIT Press, 1986.
[4] R.K. Belew, J. Mclnerney, and N.N. Schraudolph, "Evolving Networks: Using the Genetic Algorithm with Connectionist Learning," Artificial Life II, C.G. Laugton, C. Taylor, J.D. Farmer, and S. Rasmussen, eds. Addison-Wesley, 1991, pp. 511-547.
[5] 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.
[6] T. Mai and C.Y. Suen, "A Generalized Knowledge-Based System for the Recognition of Unconstrained Handwritten Numerals," IEEE Trans. Systems, Man and Cybernetics, vol. 20, no. 4, pp. 835-848, 1990.
[7] R. Legault and C.Y. Suen, "Contour Tracing and Parametric Approximations for Digitized Patterns," Computer Vision and Shape Recognition, A. Krzyzak, T. Kasvand, and C. Y. Suen, (eds.). Singapore: World Scientific Publishing, 1989, pp. 225-240.
[8] C.Y. Suen, C. Nadal, T.A. Mai, R. Legault, and L. Lam, "Recognition of Handwritten Numerals Based on the Concept of Multiple Experts," Proc. of First Intl. Workshop on Frontiers in Handwriting Recognition,Montreal, Canada, pp. 131-144, Apr. 1990.
[9] A. Krzyzak, W. Dai, and C.Y. Suen, "Unconstrained Handwritten Character Classification Using Modified Backpropagation Model," Proc. of First Int. Workshop Frontiers in Handwriting Recognition,Montreal, Canada, pp. 155-166, Apr. 1990.
[10] Y. Le Cun et al., "Constrained Neural Network for Unconstrained Handwritten Digit Recognition," Proc. of First Int. Workshop on Frontiers in Handwriting Recognition,Montreal, Canada, pp. 145-154, Apr. 1990.
[11] S. Knerr, L. Personnaz, and G. Dreyfus, "Handwritten Digit Recognition by Neural Networks with Single-Layer Training," IEEE Trans. Neural Networks, vol. 3, no. 6, pp. 962-968, Nov. 1992.
[12] P. Ahmed and C.Y. Suen, "Computer Recognition of Totally Unconstrained Handwritten ZIP Codes," Int'l. J. Pattern Recognition and Artificial Intelligence, vol. 1, no. 1, pp. 1-15, 1987.
[13] M. Beun, "A Flexible Method for Automatic Reading of Handwritten Numerals," Philips Technical Review, vol. 33, pp. 89-101 and pp. 130-137, 1973.
[14] E. Cohen, J.J. Hull, and S.N. Srihari, "Understanding Handwritten Text in A Structured Environment: Determining ZIP Codes from Addresses," Int'l. J. Pattern Recognition and Artificial Intelligence, vol. 5, nos. 1and 2, pp. 221-264, 1991.
[15] B. Duerr, W. Haettich, H. Tropf, and G. Winkler, "A Combination of Statistical and Syntactical Pattern Recognition Applied to Classification of Unconstrained Handwritten Numerals," Pattern Recognition, vol. 12, pp. 189-199, 1980.
[16] P.D. Gader, D. Hepp, B. Forester, T. Peurach, and B.T. Mitchell, "Pipelined Systems for Recognition of Handwritten Digit in USPS ZIP Codes," Proc. U.S. Postal Service Advanced Technology Conf., pp. 539-548, Nov. 1990.
[17] C.L. Kuan and S.N. Srihari, "A Stroke-Based Approach to Handwritten Numeral Recognition," Proc. U.S. Postal Service Advanced Technology Conf., pp. 1033-1041, 1988.
[18] B. Lemarie, "Practical Implementation of a Radial Basis Function Network for Handwritten Digit Recognition," Proc. Second Int. Conf. on Document Analysis and Recognition,Tsukuba, Japan, pp. 412-415, Oct. 1993.
[19] B.T. Mitchell and A.M. Gillies, "A Model-Based Computer Vision System for Recognizing Handwritten ZIP Codes," Machine Vision and Applications, vol. 2, pp. 231-243, 1989.
[20] L. Stringa, "A New Set of Constraint-Free Character Recognition Grammars," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 1210-1217, Dec. 1990.
[21] D.-S. Lee and S.N. Srihari, "Handprinted Digit Recognition: A Comparison of Algorithms," Proc. Third Intl. Workshop Frontiers in Handwriting Recognition,Buffalo, USA, pp. 153-162, May 1993.
[22] W.K. Pratt, Digital Image Processing, John Wiley&Sons, New York, 1978.
[23] Y.-J. Kim, S.-W. Lee, and M.-W. Kim, "Parallel Hardware Implementation of Handwritten Character Recognition System on Wavefront Array Processor Architecture," Proc. Third Intl. Conf. Document Analysis and Recognition,Montreal, Canada, pp. 715-718, Aug. 1995.

Index Terms:
Totally unconstrained handwritten numeral recognition, multilayer cluster neural network, genetic algorithm.
Seong-Whan Lee, "Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 648-652, June 1996, doi:10.1109/34.506416
Usage of this product signifies your acceptance of the Terms of Use.