Abstract
This paper presents an approach to using both labelled and unlabelled data to train a multi-layer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train networks for colour classification in graphic arts.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Castelli, V., Cover, T.M.: On the exponential value of labeled samples. Pattern Recognition Letters 16, 105–111 (1995)
Lippman, R.P.: Pattern Classification Using Neural Networks. IEEE Communications Magazine 27, 47–64 (1989)
Miller, D.J., Uyar, H.S.: Combined learning and use for a mixture model equivalent to the RBF classifier. Neural Computation 10, 281–293 (1998)
Miller, D.J., Uyar, H.S.: A mixture of experts classifier with learning based on both labelled and unlabelled data. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 571–577. MIT Press, Cambridge (1997)
Ruck, D.W., Rogers, S.K., Kabrisky, M., Oxley, M.E., Suter, B.W.: The multilayer perceptron as an approximation to a Bayes optimal discriminant function. IEEE Trans. Neural Networks 1, 296–298 (1990)
Shashahani, B., Landgrebe, D.: The Effect on Unlabelled Samples in Reducing the Small Sample Size Problem and Mitigating the Huges Phenomenon. IEEE Transactions on Geoscience and Remote Sensing 32, 1087–1095 (1994)
Towell, G.: Using unlabeled data for supervised learning. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 647–653. MIT Press, Cambridge (1997)
Verikas, A., Malmqvist, K., Bergman, L.: Colour Image Segmentation by Modular Neural Network. Pattern Recognition Letters 18, 173–185 (1997)
Verikas, A., Malmqvist, K., Bergman, L., Signahl, M.: Colour Classification by Neural Networks in Graphic Arts. Neural Computing & Applications 7, 52–64 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Verikas, A., Gelzinis, A., Malmqvist, K. (1999). Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts. In: Imam, I., Kodratoff, Y., El-Dessouki, A., Ali, M. (eds) Multiple Approaches to Intelligent Systems. IEA/AIE 1999. Lecture Notes in Computer Science(), vol 1611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48765-4_59
Download citation
DOI: https://doi.org/10.1007/978-3-540-48765-4_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66076-7
Online ISBN: 978-3-540-48765-4
eBook Packages: Springer Book Archive