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方法。车牌定位模块中,提出了采用基于小波变换的车牌边缘提取和数学形态学相结合的方法定位出车牌,进行二值化、滤波后使用垂直投影法分割出车牌字符,最后使用多模板匹配和二次细分识别相结合的方法识别出车牌字符。经实验验证,基于该算法的车牌识别系统能够达到较高的车牌识别率。
This paper introduced a design and experimental method of license plate recognition system based on the study of license plate location, license plate character segmentation and license plate character recognition. In the plate location module, a method that combines WT-based (wavelet transform) plate edge extraction and mathematical morphology was pro- posed to locate a license plate. After being binarired and filtered, license plate characters were segmented by vertical projec- tion. Finally, license plate character was recognized by the combining method of multiple templates matching and secondary subdivision recognition. The experiments indicate that license plate recognition system based on the proposed algorithm achieves higher recognition rate of license plate.
出处
《现代电子技术》
2012年第15期142-144,共3页
Modern Electronics Technique
关键词
图像预处理
车牌定位
车牌字符分割
车牌字符识别
irnage preprocessing
license plate location
license plate character segmentation
license plate character recognition