随机分形维数和小波变换的车牌字符识别  

Recognition of Vehicle License Character of Random Fractal Dimension and Wavelet Transform

作　　者：聂笃宪[1] 曾文曲[2] 

机构地区：[1]华南农业大学理学院,广东广州510642 [2]广东工业大学计算机学院,广东广州510090

出　　处：《广东工业大学学报》2005年第4期58-61,共4页Journal of Guangdong University of Technology

基　　金：广东省自然科学省基金项目((2003)32475)

摘　　要：运用随机分形特征描述了车牌字符的形态、复杂程度和不规则性特征,结合小波变换,使得车牌字符的分形特征描述更加丰富,同时避免了分形维数计算阈值选择带来的问题.模拟结果表明分形和小波结合使用的方法为车牌字符识别提供了新途径,但计算量较大.This paper uses random fractal character to describe complexity and characteristics. At the same time, it solves the the shape of vehicle license character, its problem that was caused by the chosen threshold when calculating the fractal dimension. Simulation results show that the method joining the fractal to wavelet is a new feasible approach to recognize vehicle license characters. But it should be mentioned that the calculation is mass.

关 键 词：分形 分形维数 小波变换 车牌 字符识别 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]