| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Automatic Feature Generation for Handwritten Digit Recognition
December 1996 (vol. 18 no. 12)
pp. 1256-1261
Abstract—An automatic feature generation method for handwritten digit recognition is described. Two different evaluation measures, orthogonality and information, are used to guide the search for features. The features are used in a backpropagation trained neural network. Classification rates compare favorably with results published in a survey of high-performance handwritten digit recognition systems. This classifier is combined with several other high performance classifiers. Recognition rates of around 98% are obtained using two classifiers on a test set with 1,000 digits per class.
[1] 1256 P.D. Gader, B. Forester, M. Ganzberger, A. Gillies, B. Mitchell, M. Whalen, and T. Yocum, "Recognition of Handwritten Digits Using Template and Model Matching," Pattern Recognition, vol. 24, pp. 421-432, 1991.[2] P.D. Gader, D. Hepp, B. Forester, T. Peurach, and B.T. Mitchell, "Pipelined Systems for Recognition of Handwritten Digits in USPS ZIP Codes," Proc. US Postal Service Advanced Technology Conf.,Washington, D.C., 1990.[3] P.D. Gader and M.A. Khabou, "Automated Feature Generation for Handwritten Digit Recognition," Proc. Third Int'l Workshop Frontiers of Handwriting Recognition,Buffalo, N.Y., 1993.[4] P.D. Gader, Y. Won, and M. Khabou, "Image Algebra Networks for Pattern Classification," SPIE Image Algebra and Morphological Image Processing V, 1994.[5] J.-H. Chiang and P.D. Gader, "Improving Digit Recognition Reliability by a Hybrid Neural Model," Proc. Int'l Conf. CFSA/IFIS/SOFT '95 on Fuzzy Theory and Applications, pp. 182-187,Taipei, Taiwan, Dec. 1995.[6] A. Gillies, "Automatic Generation of Morphological Template Features," Proc. SPIE Conf. Image Algebra and Morphological Image Processing,San Diego, 1990.[7] F. Kimura and M. Sridhar, “Handwritten Numerical Recognition Based on Multiple Algorithms,” Pattern Recognition, vol. 24, no. 10, pp. 969-983, 1991.[8] B. Mitchell and A. Gillies, "A Model-based Computer Vision System for Recognizing Handwritten ZIP Codes," Machine Vision and Applications, vol. 2, pp. 231-243, 1989.[9] 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.[10] F. Nakane, H. Miyao, and Y. Nakano, "Feature Extraction and Identification of Corners Using Neural Networks," Proc. Fourth Int'l Workshop Frontiers of Handwriting Recognition,Taipei, Taiwan, 1994.[11] J. Favata, G. Srikantan, and S.N. Srihari, "Handprinted Character/Digit Recognition Using a Multiple Feature/Resolution Philosophy," Proc. Fourth Int'l Workshop Frontiers of Handwriting Recognition,Taipei, Taiwan, 1994.[12] F. Stentiford, "Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search Procedure," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, pp. 349-355, 1985.[13] P.D. Gader and B. Forester, "Integrating Template and Model Matching for Unconstrained Handwritten Numeral Recognition," Proc. SPSE's 43rd Ann. Conf.,Rochester, N.Y., 1990.[14] J.M. Keller, P.D. Gader, H. Tahani, J.-H. Chiang, and M. Mohamed, "Advances in Fuzzy Integration for Pattern Recognition," Pattern Recognition Letters, vol. 65, pp. 273-283, 1994.[15] T.K. Ho, J.J. Hull, and S.N. Srihari, “Decision Combination in Multiple Classifiers Systems,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 66-75, Jan. 1994.[16] Y.S. Huang and C.Y. Suen, A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, pp. 90-93, 1998.[17] C. Sung-Bae and J.H. Kim, “Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification,” IEEE Trans. Systems, Man,and Cybernetics, vol. 25, no. 2, pp. 380-384, 1995.[18] C.Y. Suen, “Computer Recognition of Unconstrained Handwritten Numerals,” Proc. IEEE, vol. 80, pp. 1,162-1,180, 1992.[19] R. Casey, "Moment Normalization of Handprinted Characters," IBM J. Research and Development, pp. 548-557, 1970.[20] L.R. Rabiner, “Tutorial on Hidden Markov Model and Selected Applications in Speech Recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257-285, 1989.[21] J. Tubbs, "A Note on Binary Template Matching," Pattern Recognition, vol. 22, pp. 359-365, 1989.[22] P. Gader and M. Whalen, "Advanced Research in Handwritten ZIP Code Recognition," US Postal Service Office of Advanced Tech nology, Washington D.C., Dec. 1990.[23] P.D. Gader, A.M. Gillies, and D. Hepp, "Handwritten Character Recognition," Digital Image Processing Methods, E. Dougherty, ed., pp. 223-261.New York: Marcel Dekker, 1994.[24] P.D. Gader, M. Mohammed, and J.H. Chiang, “Handwritten Word Recognition with Character and Inter Character Neural Networks,” IEEE Trans. System, Man, and Cybernetics, pp. 158-164, vol. 27, no. 1, 1997.[25] A.M. Gillies, D. Hepp, M. Ganzberger, R. Rovner, and P.D. Gader, "Handwritten Address Interpretation," Report from ERIM to US Postal Service, Office of Advanced Tech nology, 1993.[26] Y.L. Le Cun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, "Back-Propagation Applied to Handwritten Zip Code Recognition," Neural Computation, vol. 1, pp. 541-551, 1989.[27] Y.L. Le Cun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, L. Jackel, and H. Baird, "Constrained Neural Network for Unconstrained Handwritten Digit Recognition," Proc. First Int'l Workshop Frontiers in Handwriting Recognition,Montreal, Canada, 1990.[28] C. Sung-Bae and J.H. Kim, “Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification,” IEEE Trans. Systems, Man,and Cybernetics, vol. 25, no. 2, pp. 380-384, 1995.
Index Terms:
Handwritten digit recognition, feature generation, feature selection, entropy, information, orthogonality, neural networks.
Citation:
Paul D. Gader, Mohamed Ali Khabou, "Automatic Feature Generation for Handwritten Digit Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 12, pp. 1256-1261, Dec. 1996, doi:10.1109/34.546262
