Efficient classification by neural networks using encoded patterns
暂无分享,去创建一个
The corners and the middle points, which are extracted as features from the line approximation of a given pattern, are overlaid on a radial grid to form the input array for training a backpropagation network for classification. The proposed method is shown to be simple and robust by extensive testing of its performance on patterns both with and without noise.
[1] Paulo J. G. Lisboa,et al. Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.
[2] Gary E. Ford,et al. Network model for invariant object recognition , 1994, Pattern Recognit. Lett..
[3] K Fukushima,et al. Handwritten alphanumeric character recognition by the neocognitron , 1991, IEEE Trans. Neural Networks.