An effective result-feedback neural algorithm for handwritten character recognition
Xiaoyan Zhu, Hao Yu, Yifan Shi, David D. Zhang · PolyU Institutional Research Archive (Hong Kong Polytechnic University) · 2001
In this paper, a new algorithm of handwritten character recognition based on result-feedback is proposed. It is designed as an effective neural network by adding confidence back-propagation and input modification, thus both pre-processing and recognition operations are closely integrated together. The convergence of the algorithm is proved and many experiments show that the error rate in such a result-feedback neural network (RFNN) can be greatly reduced as well as the robust to environmental noise.