Permutative coding technique for handwritten digit recognition system

作者: E. Kussul , T. Baidyk

DOI: 10.1109/IJCNN.2003.1223743

关键词:

摘要: The new neural classifier for the handwritten digit recognition is proposed. based on Permutative Coding technique. This coding technique derived from associative-projective networks developed in 80th-90th. performance was tested MNIST database. error rate of 0.54% obtained.

参考文章(9)
Cheng-Lin Liu, K. Nakashima, H. Sako, H. Fujisawa, Handwritten digit recognition using state-of-the-art techniques international conference on frontiers in handwriting recognition. pp. 320- 325 ,(2002) , 10.1109/IWFHR.2002.1030930
E. Kussul, T. Baidyk, L. Kasatkina, V. Lukovich, Rosenblatt perceptrons for handwritten digit recognition international joint conference on neural network. ,vol. 2, pp. 1516- 1520 ,(2001) , 10.1109/IJCNN.2001.939589
Ernst Kussul, Tatiana Baidyk, Improved method of handwritten digit recognition tested on MNIST database Image and Vision Computing. ,vol. 22, pp. 971- 981 ,(2004) , 10.1016/J.IMAVIS.2004.03.008
S. Belongie, J. Malik, J. Puzicha, Shape matching and object recognition using shape contexts IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 24, pp. 509- 522 ,(2002) , 10.1109/34.993558
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Dmitri A Rachkovskij, Ernst M Kussul, None, Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning Neural Computation. ,vol. 13, pp. 411- 452 ,(2001) , 10.1162/089976601300014592
L. Bottou, C. Cortes, J.S. Denker, H. Drucker, I. Guyon, L.D. Jackel, Y. LeCun, U.A. Muller, E. Sackinger, P. Simard, V. Vapnik, Comparison of classifier methods: a case study in handwritten digit recognition international conference on pattern recognition. ,vol. 2, pp. 77- 82 ,(1994) , 10.1109/ICPR.1994.576879
S. Belongie, J. Malik, J. Puzicha, Matching shapes international conference on computer vision. ,(2001)