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

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

Volumn 2003-January, Issue , 2003, Pages 268-272

  Takahashi, Katsuhiko ^a   Nishiwaki, Daisuke ^a  

^a NEC CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

PROBLEM SOLVING; STATISTICS;

DIGIT RECOGNITION; DISCRIMINATIVE CLASSIFIERS; DISCRIMINATIVE METHODS; ENSEMBLE METHODS; GENERALIZED LEARNING VECTOR QUANTIZATION; HANDWRITTEN DIGIT RECOGNITION; OUTLIER REJECTION;

CHARACTER RECOGNITION;

EID: 33847216062     PISSN: 15205363     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICDAR.2003.1227671     Document Type: Conference Paper

References (12)

1. J. Bromley, J. S. Denker, "Improving rejection performance on handwritten digits by training with "Rubbish"", Neural Computation, Vol. 5, pp. 367-370 (1993).
2. C.-L. Liu, H. Sako, "Discriminative learning to improve the outlier resistance of neural classifiers", Technical report of IEICE, PRMU 2001-99, pp. 1-8 (2001).
3. S. Kim, S. You, Y. Choi, "Rejection of garbage patterns for improving reliability in continuous handwritten numeral recognition", Methodologies for the conception, design and application of intelligent systems, Vol. 2, pp. 778-781 (1996).
4. T. Kato, S. Omachi, H. Aso, "Unsupervised learning for single hypothesis problem via mixtures of modified quadratic discriminant functions", Technical report of IEICE, PRMU 2001-103, pp. 31-38 (2001) (in Japanese).
5. S. Naoi, "Toward personal optival character reader form enterprise special use", Technical report of IEICE, PRMU 97-249, pp. 63-72 (1998) (in Japanese).
6. A. Sato, K. Yamada, "Generalized learning vector quantization", Advances in neural information processing systems 8, MIT press, Cambridge, MA, pp. 423-429 (1996).
7. C.-L. Liu, M. Nakagawa, "Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition", Pattern Recognition, Vol. 34, pp. 601-615 (2001).
8. A. Sato, "A learning method for definite canonicalization based on minimum classification error", Proc. of ICPR 2000, pp. 199-202 (2000).
9. C.-L. Liu, H. Sako, H. Fujisawa, "Performance evaluation of pattern classifiers for handwritten character recognition", International journal on documnent analysis and recognition, Vol. 4, No. 3, pp. 191-204 (2002).
10. I.-S. Oh, C.Y. Suen, "A class-modular feedforward neural network for handwriting recognition", Pattern Recognition, Vol. 35, pp. 229-244 (2002).
11. C.Y. Suen, K. Liu, N.W. Strathy, "Sorting and recognizing cheques and financial documents", Proc. of third IAPR workshop on document analysis systems, pp. 1-18 (1998).
12. T. Wakabayashi, S. Tsuruoka, F. Kimura, Y. Miyake, "Accuracy improvement through increased feature size in handwritten numeral recognition", Transactions of IEICE(D-II), Vol.J77-D-II, No.10, pp. 2046- 2053 (1994)(in Japanese).