Abstract
This paper proposes a general local learning framework to effectively alleviate the complexities of classifier design by means of “divide and conquer”principle and ensemble method. The learning framework consists of quantization layer and ensemble layer. After GLVQ and MLP are applied to the framework, the proposed method is tested on public handwritten lowercase data sets, which obtains a promising performance consistently. Further, in contrast to LeNet5, an effective neural network structure, our method is especially suitable for a large-scale real-world classification problem although it is easily scaled to a small training set with preserving a good performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sharkey, A.J.C.: Multi-net systems. In: Sharkey, A.J.C. (eds.): Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems. Springer-Verlag, London (1999) 1–30
Krogh, A., Vedels by, J.: Neural network ensembles, cross validation, and active learning. In: Tesauro, G., Touretzky, D., Leen, T. (eds.): Advances in Neural Information Processing Systems, Vol. 7. MIT Press, Cambridge MA (1995) 231–238
Tumer, K., Ghosh, J.: Linear and order statistics combiners for pattern classification. In: Sharkey, A.J.C. (eds.): Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems. Springer-Verlag, London (1999) 127–161
Breiman, L.: Bagging predictors. Machine Learning. 24(2) (1996) 123–140
Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy (1996) 148–156
Jocobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Computation. 3(1) (1991) 79–87
Kohonen, T.: Self-Organizing Maps. Springer-Verlag, Berlin, Germany, 2nd Edition (1997)
Diamantini, C., Spalvieri, A.: Quantizing for minimum average misclassification risk. IEEE Trans. Neural Network. 9(1) (1998) 174–182
Kohenon, T.: The self organizing map. Proc. IEEE. 78(9) (1990) 1464–1480
Diamantini, C., Spalvieri, A.: Certain facts about kohonen’s lvq1 algorithm. IEEE Trans. Circuits Syst. I. 47 (1996) 425–427
Juang, B.H., Katagiri, S.: Discriminative learning for minimum error classification. IEEE Trans. Signal Processing. 40(2) (1992) 3043–3054
Katagiri, S., Lee, C.H., Juang, B.H.: Discriminative multilayer feedforward networks. In: Proc. IEEE Workshop Neural Network for Signal Processing. Piscat-away, NJ (1991) 11–20
Sato, A., Yamada, K.: Generalized learning vector quantization. In: Advances in Neural Information Processing Systems. Vol. 8. MIT Press, Cambridge, MA (1996) 423–429
Sato, A., Yamada, K.: A formulation of learning vector quantization using a new misclassification measure. Proc. of ICPR’98 (1998) 332–325
Sato, A., Yamada, K.: An analysis of convergence in generalized lvq. Proc. of ICANN’98. (1998) 171–176
Bradley, P.S., Fayyad, U.M.: Refining initial points for k-means clustering. In: Proceedings of the Fifteenth International Conference on Machine Learning. Morgan Kaufmann, San Francisco, CA (1998) 91–99
Fujisawa, Y., Shi, M., Wakabayashi, T., Kimura, F.: Handwritten numeral recognition using gradient and curvature of gray scale image. In: Proceedings of International Conference on Document Analysis and Recognition. India (1999) 277–280
Srihari, S.N.: Recognition of handwritten and machine-printed text for postal address interpretations. Pattern Recognition Letters. 14 (1993) 291–302
Matsui, T., Tsutsumida, T., Srihari, S.N.: Combination of stroke/background structure and contour-direction features and handprinted alphanumeric recognition. In: Proc. Int. Workshop on Frontiers in Handwriting Recognition. Taipei, Taiwan, Republic of China (1994) 87–96
Dong, J.X., Krzyzak, A., Suen, C.Y.: A multi-net learning framework for pattern recognition. In: International Conference on Document Analysis and Recognition. accepted. Washington, USA (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dong, Jx., Krzyżak, A., Suen, C.Y. (2001). Local Learning Framework for Recognition of Lowercase Handwritten Characters. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2001. Lecture Notes in Computer Science(), vol 2123. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44596-X_19
Download citation
DOI: https://doi.org/10.1007/3-540-44596-X_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42359-1
Online ISBN: 978-3-540-44596-8
eBook Packages: Springer Book Archive