车牌定位系统中关健技术的研究与实现  

Research and Implementation of Key Technology in Plate Location System

作　　者：廖宇[1] 

机构地区：[1]湖北民族学院信息工程学院,湖北恩施445000

出　　处：《湖北民族学院学报（自然科学版）》2011年第1期92-95,共4页Journal of Hubei Minzu University(Natural Science Edition)

基　　金：湖北省自然科学基金项目(2010CDB00901)

摘　　要：针对车牌识别系统中由于分割不准确而造成识别率低的问题,提出一种基于一阶水平差分算子的自适应边缘检测的分割方法,以便更好的将汽车图像从复杂的背景中分割出来,同时用优化投影法对车牌进行定位,并在字符识别中利用改进15特征点提取法实现了车牌字符的识别.实验结果表明,该算法对车牌识别的准确性高,识别速度快,鲁棒性好.This paper proposed an adaptive edge detection segmentation method based on first-order difference operator to solve the low recognition rate problem in plate recognition system in order to better segment the car images from complex background.The optimized projection is used to locate the license plate.In character recognition,using improved extraction with 15 feature points method to make license plate character recognition.The experimental results show that this algorithm achieved a high accuracy,rapid recognition and good robustness in license recognition.

关 键 词：车牌识别 图像分割 车牌定位 图像处理 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]