汽车牌照识别系统中车牌定位与校正及字符分割的研究.docx

南京航空航天大学硕士学位论文摘要汽车牌照识别系统是智能交通系统的核心部分，可用于公路电子收费、出入控制和车流监控等众多场合，它主要包括车牌定位、校正、字符分割和识别四个部分。其中，车牌的定位、校正和分割对后续的字符识别有重要影响。本文在总结近年来国内外在车牌定位、校正和分割领域的最新研究进展的基础上，对车牌定位、校正及分割的算法进行了系统的研究。在车牌定位上，利用了车牌图像中字符和底色具有固定颜色搭配这一规律，首先在色度饱和度亮度空间（HSV 空间）中判断颜色，搜寻符合车牌底色与字符颜色搭配规律的像素点作为颜色对特征点；然后利用数学形态学进行处理，根据车牌上字符的纹理特征，对每行上的连通线段进行分析和排除；接着对各行保留下的连通线段进行合并以确定车牌位置；最后通过车牌区域扩张得到完整的车牌图像。在车牌校正中，针对车牌边框对结果影响较大的问题，本文提出了一种基于颜色对特征点主成分分析的车牌水平倾斜校正方法。该方法通过对车牌图像中的颜色对特征点进行主成分分析以求出车牌水平倾斜方向并予以校正。水平校正之后又完成了垂直校正并确定了车牌的上下和左右边界位置。在字符分割阶段，经过二值化、反色和滤波去噪等预处理之后再借助相关的投影信息和先验知识来确定每个字符的分割位置，并针对粘连字符进行了简单而有效的处理。最后，用 VC++编程构建了车牌定位与校正及字符分割系统的软件平台。该平台包含了上述的车牌定位、校正和分割等所有步骤。对实际获取的车牌进行了大量实验，获得了令人满意的结果，为后续的字符识别创造了条件。关键词：车牌定位，倾斜校正，字符分割，颜色对特征点，数学形态学，主成分分析，阈值分割i汽车牌照识别系统中车牌定位与校正及字符分割的研究AbstractVehicle license plate recognition system(LPRS) is the hardcore of theintelligent traffic system(ITS).It can be used in the fields such as electroncharging,pass controlling,automobile stream supervising and so on.LPRS consistsof four main modules which are license plate location,slant correction,charactersegmentation and character recognition.The former three modules have greateffects on the last module.This paper has summarized a lot of materials and doesresearch onlicense plate location,slant correction and character segmentation.In the stage of license plate location,color segmentation is applied firstly inHSV color space to extract color pair pixels according to the rule that charactercolor and background color should be matched.Then,mathematics morphologicaloperation is adopted in order to get some continuous lines and texture features ofthese lines are analyzed so as to filtrate disturbed lines.After that process theremained continuous lines are combined to locate the plate.Finally,the whole plateis got through expanding the plate area.In the stage of slant correction,a horizontal slant correction approach basedon color pair pixels and principal component analysis is presented.Throughprincipal component analysis of the color pair pixels,the slan