论文信息 - A class-modular GLVQ ensemble with outlier learning for handwritten digit recognition

A class-modular GLVQ ensemble with outlier learning for handwritten digit recognition

A class-modular generalized learning vector quantization (GLVQ) ensemble method with outlier learning for handwritten digit recognition is proposed. A GLVQ classifier is a discriminative method. Though discriminative classifiers have the remarkable ability to solve character recognition problems, they are poor at outlier resistance. To overcome this problem, a GLVQ classifier trained with both digit images and outlier images is introduced. Moreover, the original 10-classification problem is separated into ten 2-classification problems using ten GLVQ classifiers, each of which recognizes its corresponding digit class. Experimental results of handwritten digit recognition and outlier rejection reveal that our method is far more superior at outlier resistance than a conventional GLVQ classifier, while maintaining its digit recognition performance.

Katsuhiko Takahashi | Daisuke Nishiwaki

[1] Hiroshi Sako,et al. Discriminative Learning to Improve the Outlier Resistance of Neural Classifiers , 2001 .

[2] Ching Y. Suen,et al. A class-modular feedforward neural network for handwriting recognition , 2002, Pattern Recognit..

[3] John S. Denker,et al. Improving Rejection Performance on Handwritten Digits by Training with Rubbish , 1993, Neural Computation.

[4] Tetsushi Wakabayashi,et al. Accuracy Improvement through Increased Feature Size in Handwritten Numeral Recognition , 1994 .

[5] Atsushi Sato,et al. Generalized Learning Vector Quantization , 1995, NIPS.

[6] Ching Y. Suen,et al. Sorting and Recognizing Cheques and Financial Documents , 1998, Document Analysis Systems.

[7] Masaki Nakagawa,et al. Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition , 2001, Pattern Recognit..

[8] Hiroshi Sako,et al. Performance evaluation of pattern classifiers for handwritten character recognition , 2002, International Journal on Document Analysis and Recognition.

[9] Atsushi Sato. A learning method for definite canonicalization based on minimum classification error , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.