Abstract
We presented a model combining supervised learning for the classification stage and a specific not-supervised model for the test stage. It allows changing the topology of the supervised part for improving the reject quality. Within the framework of the recognition of disturbed forms, our strategy was based on the adaptability of the classifier instead of, for example, making it learn more samples by artificially creating all the possible deformations, our approach consisted in defining the type of problematical transformation, by changing the localities observed by the principal classifier. The system makes it possible indeed to refine the results till it makes possible to raise ambiguities for certain confusions but there remains still depend on the effectiveness of the initial rejection and the assumptions concerning the choice of the model of class. On the level of the prospects, if the type of deformation is perfectly known: cut, rotation, problem of shift, it would be possible to introduce new properties inside the self-organizing map to speed up its convergence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Akiyama K (1996) A new reject decision method for statistical pattern recognition. Proc. of IWFHR-5
Chow C.K (1970) On optimum recognition error and reject tradeoff. IEEE. Trans. Information Theory, vol 16, pp. 41–46
Dur Trier O, and Al (1996) Feature Extraction Methods for Character Recognition-A Survey. Pattern Recognition, vol. 4, nř 29, pp. 641–662
Gorksi N (1997) Optimizing error-reject trade off in recognition systems. 4th International Conference Document Analysis and Recogntion, pp. 556–559
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43:–69
Koerich L.A (2004) Rejection Strategies for Handwritten Word Recognition. to appear in 9th International Workshop on Frontiers in Handwriting Recognition (IWFHR-9)
LeCun Y, and Al (1998) Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, vol. 86, nř11, pp. 2278–2324
Simard P, and Al (2003) Best Practice for Convolutional Neural Networks Applied to Visual Document Analysis. International Conference on Document Analysis and Recognition, ICDAR, IEEE Computer Society, pp. 958–962
Teow L, and Al (2002) Robust vision-based features and classification schemes for off-line handwritten digit recognition. Pattern Recognition 35(11): 2355–2364
Zimmermann M, and Al (2004) Rejection Strategies for Offline Handwritten Sentence Recognition. 17th International Conference on Pattern Recognition (ICPR) Volume II, p. 550–553
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
Cecotti, H., Belaïd, A. (2005). A New Rejection Strategy for Convolutional Neural Network by Adaptive Topology. In: Kurzyński, M., Puchała, E., Woźniak, M., żołnierek, A. (eds) Computer Recognition Systems. Advances in Soft Computing, vol 30. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-32390-2_13
Download citation
DOI: https://doi.org/10.1007/3-540-32390-2_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25054-8
Online ISBN: 978-3-540-32390-7
eBook Packages: EngineeringEngineering (R0)