| 一种改进的基于 ART2神经网络的文字识别算法 |
| |
| 引用本文： | 何滔,赵莹莹.一种改进的基于 ART2神经网络的文字识别算法[J].桂林电子科技大学学报,2012(3):237-239. |
| |
| 作者姓名： | 何滔 赵莹莹 |
| |
| 作者单位： | 桂林电子科技大学信息科技学院,广西 桂林 541004 |
| |
| 基金项目： | 广西高等教育教学改革工程(2012JGA240) |
| |
| 摘 要： | 为了解决 ART2神经网络的漂移问题,提出了一种改进的基于 ART2神经网络的文字分类和识别方法.此方法能够自主学习,收敛速度快,识别率和识别速度都比 BP神经网络高.实践证明,基于此设计的脱机手写体文字识别系统能对较规范的手写体文字进行识别,识别率达到85%.
|
| 关 键 词： | ART2神经网络 漂移 收敛速度 |
An improved character recognition algorithm based on ART2 neural network |
| |
| He Tao,Zhao Yingying.An improved character recognition algorithm based on ART2 neural network[J].Journal of Guilin Institute of Electronic Technology,2012(3):237-239. |
| |
| Authors: | He Tao Zhao Yingying |
| |
| Affiliation: | (Institute of Information Technology of Guilin University of Electronic Technology,Guilin 541004,China) |
| |
| Abstract: | An improved character recognition algorithm is improved,which mainly solves the problem of shift in ART2 neural network.The method achieves unsupervised learning,faster convergence velocity,higher recognition rate than BP neural network.The practice has proved that the offline handwritten character recognition system based on the improved algorithm can recognize normative handwritten characters.The recognition rate is up to 85 %. |
| |
| Keywords: | ART2 neural network shift convergence velocity |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
