摘要
通过对车牌定位、车牌字符分割和车牌字符识别进行研究,提出了一种车牌识别系统的设计和实验仿真方法。该方法首先采用基于Canny算子边缘检测和数学形态学相结合的方法定位出车牌,进行二值化、滤波和形态学开运算后使用投影二分法分割出7个车牌字符,最后使用模板匹配和特征统计相结合的方法识别出车牌字符。试验表明该方法是有效的、可行的,与传统使用单一算法相比较,该方法大大提高了车牌识别系统的正确率。
This paper introduced a design and experimental simulation method of license plate recognition system based on the research of license plate location,license plate character segmentation and license plate character recognition.This method firstly located a license plate with the combining method of Canny operator edge detection and mathematical morphology.After binarization,filtering and morphological opening process,seven license plate characters were segmented by projection dichotomy.Finally,license plate character was recognized by the combining method of template matching and statistical characteristics.Experiment demonstrates that this method is feasible,effective and greatly improves the accuracy rate of license plate recognition system,compared with the traditional method of a single algorithm.
出处
《微型机与应用》
2011年第14期37-40,共4页
Microcomputer & Its Applications
基金
安徽省自然科学基金项目(11040606Q59)
常州市科技攻关项目(CE20100004)
武进区科技攻关项目(WG2010036)
关键词
图像预处理
车牌定位
车牌字符分割
车牌字符识别
image preprocessing
license plate location
license plate character segmentation
license plate character recognition
