车牌识别系统中的图像预处理研究  

Research on Image Preprocessing of License Plate Recognition System

作　　者：赵娟[1] 黄春艳[1] 

机构地区：[1]华北水利水电学院,河南郑州450011

出　　处：《华北水利水电学院学报》2011年第3期117-119,共3页North China Institute of Water Conservancy and Hydroelectric Power

基　　金：河南省教育厅自然科学基金项目(2010A110012);河南省2010年科技发展计划项目(102300410129);华北水利水电学院青年基金项目(HSQJ2009017)

摘　　要：车牌图像预处理是车牌识别系统中的一个关键步骤,预处理的结果直接影响后续的识别结果.先对彩色图像进行灰度化处理,再进行目标二值化、滤波,从而实现车牌的精确定位和字符分割.采用形态学细化算法对图像进行未完全细化处理,再用剥皮算法对其进行细微处理,最后得到比较好的车牌图像.仿真实验表明,提出的细化算法克服了传统算法中的缺点,有较强的适应性,达到较好的处理效果.License plate preprocessing is a key step in the license plate recognition system,and the preprocessing result will directly affect the recognition result.Firstly,colorful image was done gray processing,then done binarization and filtering,in the end the accurate positioning and the character segmentation of license plate were realized.The image was done no complete thining processing by morphological thinning algorithm,then the image was done microprocessing by peeling method,at last,the image of license plate was gained.The results from the simulation experiment show that the thining algorithm overcome the shortcomings of tradition algorithm,and has strong suitability,and could gain better processing result.

关 键 词：中值滤波 细化算法 剥皮法 形态学 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]