Application of BP neural network in the digital recognition system
暂无分享,去创建一个
the purpose of digital identification technology based on artificial neural networks is to achieve efficient character recognition through the simulation of human brain function and structure. This paper uses BP neural network to design three classifiers which separately extract the input vector with different characteristics, proposes a weighted integration multi-classifier method based on the analysis of common used integrated multi-classifiers, and uses the method to integrate the designed three classifiers to design a weight-based integrated multi-classifier handwritten digital identification system.
[1] Thierry Pun,et al. A new method for grey-level picture thresholding using the entropy of the histogram , 1980 .
[2] Martin T. Hagan,et al. Neural network design , 1995 .
[3] Sankar K. Pal,et al. Entropy: a new definition and its applications , 1991, IEEE Trans. Syst. Man Cybern..
[4] V. Crnojevic,et al. Advanced impulse Detection Based on pixel-wise MAD , 2004, IEEE Signal Processing Letters.