Rejection strategy for convolutional neural network by adaptive topology applied to handwritten digits recognition

In this paper, we propose a rejection strategy for convolutional neural network models. The purpose of this work is to adapt the network's topology injunction of the geometrical error. A self-organizing map is used to change the links between the layers leading to a geometric image transformation occurring directly inside the network. Instead of learning all the possible deformation of a pattern, ambiguous patterns are rejected and the network's topology is modified in function of their geometric errors thanks to a specialized self-organizing map. Our objective is to show how an adaptive topology, without a new learning, can improve the recognition of rejected patterns in the case of handwritten digits.

[1]  Nikolai Gorski.  Optimizing error-reject trade off in recognition systems , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[2]  Kunihiko Fukushima,et al.  A neural network for visual pattern recognition , 1988, Computer.

[3]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[4]  Loo-Nin Teow,et al.  Robust vision-based features and classification schemes for off-line handwritten digit recognition , 2002, Pattern Recognit..

[5]  Hiroshi Sako,et al.  Handwritten digit recognition: investigation of normalization and feature extraction techniques , 2004, Pattern Recognit..

[6]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[7]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..

[8]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[9]  Alessandro L. Koerich.  Rejection strategies for handwritten word recognition , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[10]  Horst Bunke,et al.  Rejection strategies for offline handwritten sentence recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[11]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  Jin Wang,et al.  Weight smoothing to improve network generalization , 1994, IEEE Trans. Neural Networks.