A class-modular feedforward neural network for handwriting recognition

@article{Oh2002ACF,
  title={A class-modular feedforward neural network for handwriting recognition},
  author={Il-Seok Oh and Ching Y. Suen},
  journal={Pattern Recognition},
  year={2002},
  volume={35},
  pages={229-244}
}
Since the conventional feedforward neural networks for character recognition have been designed to classify a large number of classes with one large network structure, inevitably it poses the very complex problem of determining the optimal decision boundaries for all the classes involved in a high-dimensional feature space. Limitations also exist in several aspects of the training and recognition processes. This paper introduces the class modularity concept to the feedforward neural network… CONTINUE READING