摘要
针对车牌识别系统中由于低质车牌首字符特征提取困难而导致车牌首字符识别率不高的问题,提出了一种新的车牌汉字特征提取方法。该方法首先对车牌首字符的二值图像进行网格化处理,并对每一块网格区域提取字符笔画所在像素的占空比、散度和质心3个特征分量,接着将提取到的所有的特征向量用支持向量机分类器进行训练,最终可以得到一组鲁棒性很强的分类器。实验结果表明,该特征提取方法与支持向量机分类器结合可以较大地提高车牌首字符的识别率。
This paper offers a new method of extracting feature for solving the problem of the low Chinese character recognition rate resulted from the poor quality of the Chinese character image in the license plate recognition system. Firstly,the binary Chinese character image that has been segmented is divided into many blocks. Secondly, this paper extracts three stroke pixel＇s feature components that include the proportion of stroke pixels in the block, the divergence and the centroid for each block. Thirdly, this paper combines the new feature extraction method with the SVM classifier. At last, a group of robust classifiers are obtained. The experimental results show that the Chinese character recogni tion rate can be improved greatly.
出处
《计算机科学》
CSCD
北大核心
2013年第06A期176-179,共4页
Computer Science
关键词
车牌识别
支持向量机
字符识别
形状参数
License plate recognition, Support vector machine, Character recognition, Shape parameter
