Incremental learning for feature extraction filter mask used in similar pattern classification

The incremental learning system for a feature extraction unit in the character recognition system is described and experimental results are shown. The relationship between this learning system and neural networks (NN) are explained and the specifications of this method are described as an NN application. The improved version of this system which is related to the Gabor filter was tested and an accuracy improvement was shown in the experiments of a similar pattern classification. An important goal of this research was to observe created filter masks. It was confirmed that the visual pattern of created filter masks was reasonable for the purpose.

[1]  Shun-ichi Amari,et al.  A Theory of Adaptive Pattern Classifiers , 1967, IEEE Trans. Electron. Comput..

[2]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jenlong Moh,et al.  A general purpose model for image operations based on multilayer perceptrons , 1995, Pattern Recognit..

[4]  Aggelos K. Katsaggelos,et al.  Edge detection using a neural network , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[5]  Yoshihiko Hamamoto,et al.  A gabor filter-based method for recognizing handwritten numerals , 1998, Pattern Recognit..

[6]  Akinori Kawamura,et al.  Feature-Extraction-Based Character Recognition Using Minimum Classification Error Training , 1998 .

[7]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[8]  Alain Biem,et al.  Feature extraction based on minimum classification error/generalized probabilistic descent method , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Alan F. Murray,et al.  International Joint Conference on Neural Networks , 1993 .

[10]  Kuldip K. Paliwal,et al.  Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognition , 1995, EUROSPEECH.

[11]  Michiel Bacchiani,et al.  Optimization of time-frequency masking filters using the minimum classification error criterion , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Yoshiaki Kurosawa.  Similar Pattern Discrimination by Filter Mask Learning with Probabilistic Descent , 2007, SCIA.

[13]  Helge J. Ritter,et al.  A neural 3-D object recognition architecture using optimized Gabor filters , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[14]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[15]  Biing-Hwang Juang,et al.  New discriminative training algorithms based on the generalized probabilistic descent method , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[16]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .

[17]  Alain Biem,et al.  Filter bank design based on discriminative feature extraction , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Cheng-Lin Liu,et al.  Building compact classifier for large character set recognition using discriminative feature extraction , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[20]  Kazuo Kyuma,et al.  Learning algorithm by reinforcement signals for the automatic recognition system , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[21]  Atsushi Sato.  Discriminative Dimensionality Reduction Based on Generalized LVQ , 2001, ICANN.

[22]  Jouko Lampinen,et al.  Distortion tolerant pattern recognition based on self-organizing feature extraction , 1995, IEEE Trans. Neural Networks.

[23]  Jianming Lu,et al.  Noise Removal for Degraded Images Using Neural Networks , 2002 .

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