Abstract
The Scanning N-Tuple classifier (SNT) was introduced by Lucas and Amiri [1],[2] as an efficient and accurate classifier for chaincoded hand-written digits. The SNT operates as speeds of tens of thousands of sequences per second, duringb oth the trainingand the recognition phases.
The main contribution of this paper is to present a new discriminative trainingrule for the SNT. Two versions of the rule are provided, based on minimizingthe mean-squared error and the cross-entropy, respectively. The discriminative trainingrule offers improved accuracy at the cost of slower trainingtime, since the trainingis now iterative instead of single pass. The cross-entropy trained SNT offers the best results, with an error rate of 2.5% on sequences derived from the MNIST test set.
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
S.M. Lucas and A. Amiri, “Recognition of chain-coded handwritten characters with the scanningn-tuple method”, Electronics Letters, vol. 31, no. 24, pp. 2088–2089, 1995.
S.M. Lucas and A. Amiri, “Statistical syntactic methods for high performance ocr”, IEE Proceedings on Vision, Image and Signal Processing, vol. 143, pp. 23–30, (1996).
G. Tambouratzis, “Improvingthe clusteringp erformance of the scanningn-tuple method by usingself-sup ervised algorithms to introduce subclasses”, IEEE Transactions on Pattern analysis and Machine Intelligence, vol. 24, pp. 722–733, (2002).
S. Hoque, K. Sirlantzis, and M. C. Fairhurst, “Bit plane decomposition and the scanningn-tuple classifier”, Proceedings of International Workshop on Frontiers in Handwriting Recognition (IWFHR-8), pp. 207–212, 2002.
E. H. Ratzla., “A scanningn-tuple classifier for online recognition of handwritten digits”, in Proceedings of the Sixth International Conference on Document Analysis and Recognition, pp. 18–22. IEEE, Seattle, WA, (2001).
J. S. Bridle, “Alpha-nets: a recurrent “neural” network architecture with a hidden markov model interpretation”, Speech Communication, vol. 9, pp. 83–92, (1990).
C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, (1995).
C. L. Giles and T. Maxwell, “Learning, invariance and generalisation in high-order neural networks”, Applied Optics, vol. 26, pp. 4972–4978, (1987).
P. Garcia, E. Vidal, and F. Casacuberta, “Local languages, the successor method, and a step towards a general methodology for the inference of regular grammars”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 9, pp. 841–845, (1987).
E. Vidal and D. Llorens, “Using knowledge to improve N-gram language modelling through the MGGI methodology.”, in Proceedings of the Third International Colloquium on Grammatical Inference (ICGI-96): Learning Syntax from Sentences, Laurent Miclet and Colin de la Hieguera, Eds., Berlin, 25-27 1996, vol. 1147, pp. 179–190, Springer.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition”, Proceedings of the IEEE, vol. 86, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lucas, S.M. (2003). Discriminative Training of the Scanning N-Tuple Classifier. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_29
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive