改进的遗传算法在车牌自动识别系统中的应用  

Application of Revised Genetic Algorithm in the Automatic Recognition System of Vehicle License

作　　者：虞安军[1] 吴海珍[1] 蒋加伏[1] 

机构地区：[1]长沙理工大学计算机与通讯工程学院,湖南长沙410076

出　　处：《计算机仿真》2006年第11期224-227,共4页Computer Simulation

基　　金：湖南省自然科学基金资助项目(03JJY3101);湖南省教育厅科研项目(04C076)

摘　　要：在车牌自动识别系统中,如何选择对车牌字符分类能力强的特征组合是系统面临的关键问题。针对传统组合优化方法用于特征选择的种种缺陷和简单遗传算法过早收敛的缺点,提出了利用伪并行、最优解保存和自适应参数调整相结合的改进的遗传算法对提取的车牌字符图像众多特征进行优化选择的策略。仿真实验证明,改进的遗传算法不但从收敛速度和搜索能力上优于简单的遗传算法,而且可以有效的避免出现早熟现象,防止陷入局部最优;所提出的特征选择算法不仅提高了车牌字符识别率,而且识别结果十分稳定。In the automatic recognition system of vehicle license, feature selection for vehicle character recognition is the key factor in pattern recognition. In view of the deficiencies of traditional combination optimization method and the shortcoming of too early convergence of simple genetic algorithm, a new method of feature selection based on a revised genetic algorithm of pseudo - parallel combined with optimum solution reservation and adaptive parameter adjustment is proposed. The results of the simulation show that the revised genetic algorithm not only is better than the simple genetic algorithm in respect of convergence speed and search ability, but also can effectively avoid appearing precocity and plunging into local optimum. What＇s more the experimental results indicate that the vehicle character recognition rates are improved significantly and the classification results are very robust using the proposed method.

关 键 词：车牌自动识别系统 特征选择 简单遗传算法 改进的遗传算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]