Abstract
A novel approach for handwritten digit recognition is proposed in this paper, which combines the low rank approximation and the competitive neural network together. The images in each class are clustered into several subclasses by the competitive neural network, which is helpful for feature extraction. The low rank approximation is used for image feature extraction. Finally, the k-nearest neighbor classifier is applied to the classification. Experiment results on USPS dataset show the effectiveness of the proposed approach.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Liu, C.-L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten Digit Recognition: Benchmarking of State-of-the-Art Techniques. Pattern Recognition 36, 2271–2285 (2003)
Kim, D., Bang, S.Y.: A Handwritten Numeral Character Classification Using Tolerant Rough Set. IEEE Trans. Pattern Anal. and Machine Intelligence 22, 923–937 (2000)
Mayraz, G., Hinton, G.: Recognizing Handwritten Digits Using Hierarchical Products of Experts. IEEE Trans. Pattern Anal. and Machine Intelligence 24, 189–197 (2002)
Zhang, B., Fu, M., Yan, H.: A Nonlinear Neural Network Model of Mixture of Local Principal Component Analysis: Appl. to Handwritten Digit Recognition. Pattern Recognition 34, 203–214 (2001)
Ye, J.: Generalized Low Rank Approximations of Matrices. The 21st International Conference on Machine Learning, 887–894 (2004)
Kohonen, T.: Self-organization and Associative Memory. Springer, Berlin (1987)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Zhang, X.D.: Matrix Analysis and Applications. Tsinghua University Press, Beijing (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, Y., Zhu, F., Lv, H., Zhang, X. (2006). Handwritten Digit Recognition Using Low Rank Approximation Based Competitive Neural Network. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11760023_42
Download citation
DOI: https://doi.org/10.1007/11760023_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34437-7
Online ISBN: 978-3-540-34438-4
eBook Packages: Computer ScienceComputer Science (R0)