汉字识别方法分析及其在车牌识别系统中的应用.docx

汉字识别方法研究及其在车牌识别系统中的应用
模式识别与智能系统号业研究生;刘犬宇 指导教师:龙建忠
汉字识别是模式识别中一个晕要的研究方向,它在办公闩动化、高速信息处理、机器{!!l!觉等多办i『ij』l仃照耍的理论患义和实JIJ价值。拈智能交通系统中,应尾汉字识粥技术,对汽车牌照进行自动识剐,可以实现蟪车辆的监控和智能管理,具有广嗣的市场前景。
■值化算法,根据实验效果对各种方法进行了比较,选取了适用性较强的双线性插值法和最大方差比分割法,应用到汉字识别的预处理过程中。
作者对车牌汉字识别的特征提取方法进行了研究,酋先浇较了多种摹于统计模式识别的特征提取匹配算法,包括外围面积特征,网格特征和只l 于区分相似汉字的微结构投影特征。为了实现对模糊汉字灰度图的识别. 提出了基于二值图形变动分析的模糊模板匹配算法及其改进方案。经初步测试。该方法取得了良好的识别效果。本章还对贝卧斯分类器,r空州模式识别和人工神经网络在字符识界I中的应用进行了总结。可作为进一步砚究的基础。
在车牌字符识别巾引入了误识模型和多分类器集成技术。存实验分析的基础上,确定了影蜘系统谀嬲性能的两个立一妥参数;酋选距离发其与一i 选的距离差,并将其作为多分类器集成的判决依据。在实际系统中,我们使用了基于串行方式的两级识别器融合,车牌识别jF确枣达到了用户的要求,系统运行状况良好。
文章最后介绍了汉字识别的最新进展,并对其研究方向做了展望。
关键词:汉字识别 图像预处理特征提取 分类器设计 误识模型 多
分类器集成 车牌识别系统
Chinese Character Recognition and Its
Application in LPR System
M曩jor:Pattern Recognition and Intelligent system Postgraduate:Liu Dayu Supervisor:Long Jianzhong
Abstract:Chinese character recognition iS an important research direction in the field of pattern is of great value both in theory and practice and has applied in many circumstances,including official automation,high speed information processing,machine vision, the Intelligent Transportation System(ITS),automatic recognition of license plate by using the technique of character recognition can give facilities for vehicles’ surveillance and there’S much prospect in the application.
In chapter 2,some methods of pretreatment are introduced in detail, including algorithms of normalization and binarization for the image of license plate these methods,we select the bilinear
interpolation and thresholding segmentation of maximum variance that have good performance,and all of these have applied in the course of prepfocessing ofChinese character images.
A survey of character recognition methods is presented in chapter 3. Comparison of some extracted feature matching algorithms based on statistical pattern recognition is features are profile,mesh
and projection of m