| 基于自适应遗传算法的神经网络字符识别 |
| |
| 引用本文： | 王晓东,;薛宏智,;马盈仓.基于自适应遗传算法的神经网络字符识别[J].西北纺织工学院学报,2008(2):210-213. |
| |
| 作者姓名： | 王晓东 ;薛宏智 ;马盈仓 |
| |
| 作者单位： | [1]西安工程大学理学院,陕西西安710048; [2]长安大学理学院,陕西西安710064 |
| |
| 基金项目： | 陕西省教育厅专项科研计划项目（07JK255）;西安工程大学校管科研资助项目（2006XG37） |
| |
| 摘 要： | 为了增强传统自适应遗传算法在进化初期的鲁棒性及避免早熟收敛，给出了一种改进算法，并利用这一算法来调整BP模型的网络权值与阈值，最后将新算法应用于字符的识别．仿真结果表明，新算法比BP算法具有更强的识别能力．
|
| 关 键 词： | 遗传算法 BP算法 字符识别 |
Character recognition based on adaptive genetic neural network |
| |
| Affiliation: | WANG Xiao-dong , XUE Hong-zhi , MA Ying-cang ( 1. School of Science, Xi＇an Polytechnic University, Xi＇an 710048, China ; 2. School of Science, Chang an University, Xi＇ an 710064,China) |
| |
| Abstract: | An improved algorithm has been given in order to make the robust characteristic of traditional adaptive genetic algorithm stronger during the initial evolutionary process and overcome premature convergence, then the neural network weights and threshold of BP model is adjusted by the algorithm. Finally, the new algorithm is applied to character recognition. Simulation results prove that the new algorithm has a stronger discernment than the BP algorithm. |
| |
| Keywords: | genetic algorithm BP algorithm character Recognition |
| 本文献已被 维普 等数据库收录！ |
|
