基于小波变换和支持向量机的车牌定位方法研究  

Research of License Plate Location Method Based on Wavelet Transform and Support Vector Machine

作　　者：刘旭华[1] 周军[1] 朱田华[1] 

机构地区：[1]辽宁工业大学电子与信息工程学院,辽宁锦州121001

出　　处：《辽宁工业大学学报（自然科学版）》2013年第2期75-79,共5页Journal of Liaoning University of Technology(Natural Science Edition)

摘　　要：车牌定位是车牌识别系统中最为关键的部分。在前人研究的基础上提出了一种基于小波变换和支持向量机的车牌定位方法。利用小波变换提取出车辆图像中的竖直纹理分量。对处理后的图像进行数学形态学操作得到车牌候选区域。利用车牌的综合特征从候选车牌中试选出一个车牌,并用支持向量机对试选出的车牌进行鉴定。实验证明该方法对具有复杂背景的车辆图像有很好的定位效果。The license plate location is the most critical part of the license plate recognition system. On the basis of previous studies, a license plate location method based on wavelet transform and support vector machine was proposed. Using wavelet transform, the vertical texture components of the vehicle image was extracted. Using mathematical morphology operation, the candidate region of the processed image was obtained. Try to select a license plate with the combined features of license plate was done, and the license plate selected with support vector machines was verified. Experimental results show that the method of license plate has good results in the location of the vehicle image under complex background.

关 键 词：车牌定位 小波变换 支持向量机 数学形态学 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]