| 基于遗传算法的手写体汉字识别系统优化方法的研究 |
| |
| 引用本文： | 林磊,王晓龙,刘家锋. 基于遗传算法的手写体汉字识别系统优化方法的研究[J]. 计算机研究与发展, 2001, 38(6): 658-661 |
| |
| 作者姓名： | 林磊 王晓龙 刘家锋 |
| |
| 作者单位： | 哈尔滨工业大学计算机科学与工程系 |
| |
| 基金项目： | 国家自然科学基金项目资助!(69973 0 15 ) |
| |
| 摘 要： | 为了改善手写体汉字识别系统的性能，提出了前端单字识别器（SCR）和后端语言解码器（post-processing system）有效结合的模型，并且利用遗传算法对系统参数进行优化。以联机手写体汉字识别系统作为SCR进行测试，首选准确率为69．46％，汉字识别的准确率达到87．59％，较优化前提高6．4％。实验结果表明，遗传算法（GA）是一种有效的优化系统参数的方法。
|
| 关 键 词： | 手写体汉字识别系统 遗传算法 优化 计算机 |
RESEARCH ON OPTIMIZATION OF A HANDWRITTEN CHINESE CHARACTER RECOGNITION SYSTEM BASED ON GENETIC ALGORITHM |
| |
| LIN Lei,WANG Xiao-Long,LIU Jia-Feng. RESEARCH ON OPTIMIZATION OF A HANDWRITTEN CHINESE CHARACTER RECOGNITION SYSTEM BASED ON GENETIC ALGORITHM[J]. Journal of Computer Research and Development, 2001, 38(6): 658-661 |
| |
| Authors: | LIN Lei WANG Xiao-Long LIU Jia-Feng |
| |
| Abstract: | In order to improve the accuracy of a handwritten Chinese character recognition system, a model is presented, which combines SCR and post-processing system. Genetic algorithm is applied to optimize system parameters. Tested on an online handwritten Chinese character recognition system(SCR), 87.59% accuracy is achieved when first character candidate accuracy rate is 69.46%, and optimization contributes 6.4% improvement. The experiment results show that genetic algorithm (GA) is an effective method to optimize system parameters. |
| |
| Keywords: | handwritten Chinese character recognition genetic algorithm parameters optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
