Stroke-based handwritten Chinese character recognition using neural networks

Abstract This paper proposes a neural network approach to solving the handwritten Chinese character recognition problem. A two-dimensional Hopfield network is employed to provide a more general formulation such that some difficult problems in the Chinese character recognition system are implicitly solved.

[1]  Jun S. Huang,et al.  Stroke segmentation by bernstein-bezier curve fitting , 1990, Pattern Recognit..

[2]  Wei-Chung Lin,et al.  A hierarchical multiple-view approach to three-dimensional object recognition , 1991, IEEE Trans. Neural Networks.

[3]  Hong-Yuan Liao,et al.  Two-dimensional neural networks for handwritten Chinese character recognition , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[4]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Jun S. Huang,et al.  A transformation invariant matching algorithm for handwritten chinese character recognition , 1990, Pattern Recognit..

[6]  George Nagy,et al.  Recognition of Printed Chinese Characters , 1966, IEEE Trans. Electron. Comput..