Abstract
In this paper, a kernel-based LVQ classifier in input space is proposed to recognize handwritten digit. Classical Learning Vector Quantization is performed in the input space through Euclidean distance, but it doesn’t work well when the input patterns are highly nonlinear. In our model, the kernel method is used to define a new metric of distance in input space so we can get a direct view of the clustering result. At last, we test our model by handwritten digit recognition using MNIST database and it obtains better recognition performance than traditional LVQ.
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
Ahmed, J., Alkhalifa, E.M.: Efficient Single Layer Handwritten Digit Recognition through An Optimizing Algorithm. In: Proceedings of the 9th International Conference on Neural Information Processing, ICONIP 2002, vol. 5, pp. 2464–2468 (2002)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, R., Jackel, L.D.: Handwritten Digit Recognition with a Back-Propagation Network. In: Touretzky, D. (ed.) Advances in Neural Information Processing Systems 2, Morgan Kaufmann, San Francisco (1990)
Talukder, K.H.: Performance Analysis of Back-Propagation Learning Algorithm for Handwritten Digit Classification. In: Multi Topic Conference, 2002. Abstracts. INMIC 2002. International, vol. 61 (2002)
Su, M., Lai, E., Tew, C.: A SOM-Based Fuzzy System and Its Application in Handwritten Digit Recognition. In: Proceedings of International Symposium on Multimedia Software Engineering 2000, pp. 253–258 (2000)
Zhang, B., Fu, M., Yan, H., Jabri, M.A.: Handwritten Digit Recognition by Adaptive- Subspace Self-Organizing Map (ASSOM). IEEE Transactions on Neural Networks 10, 939–945 (1999)
Oh, S.: Improving The Error Backpropagation Algorithm with a Modified Error Function. IEEE Transactions on Neural Networks 8, 799–803 (1997)
Wu, J., Hong, Y.: Combined SOM and LVQ Based Classifiers for Handwritten Digit Recognition. In: Proceedings of the IEEE International Conference on Neural Networks 1995, vol. 6, pp. 3074–3077 (1995)
Sackinger, E., Boser, B.E., Bromley, J., LeCun, Y., Jackel, L.D.: Application of the ANNA Neural Network Chip to High-Speed Character Recognition. IEEE Transactions on Neural Networks 3, 498–505 (1992)
Kohonen, T.: Self-organization and Associative Memory, 2nd edn. Springer, Berlin (1987)
Pan, Z.S., Chen, S.C., Zhang, D.Q.: A Kernel-based SOM Classification in Input Space. Acta Electronica Sinica 32, 227–231 (2004)
Andras, P.: Kernel-Kohonen Networks. International Journal of Neural Systems 12, 117–135 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lv, H., Wang, W. (2005). Handwritten Digit Recognition with Kernel-Based LVQ Classifier in Input Space. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_32
Download citation
DOI: https://doi.org/10.1007/11427445_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25913-8
Online ISBN: 978-3-540-32067-8
eBook Packages: Computer ScienceComputer Science (R0)