基于小波分解和亮度矩的车牌定位方法  

Vehicle license plate location based on wavelet analysis and intensity moment

作　　者：朱程辉[1] 后俊[1] 王金玲[2] 

机构地区：[1]合肥工业大学电气与自动化工程学院,安徽合肥230009 [2]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2004年第8期907-910,共4页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(01042310)

摘　　要：文章提出了一种基于小波分解和亮度矩的复杂背景下,图像中车牌定位和分割的方法。针对小波分解能较好地保留图像中的细节信息,选用小波作为车牌分割工具;为了突出车牌字符与图像中其它信号特征的差异,定义了一个亮度矩函数,用以搜寻牌照的上下、左右边界。仿真结果表明,该方法定位准确率高、速度快。In this paper,an effective license plate location algorithm is presented which employs wavelet transformation and intensity moment to extract number plate from the complex-background images. By means of the wavelet analysis, the image details can be processed very well,and by defining an intensity moment function to protrude the plate characters from other signals, the locality of the license plate can be determined. The simulation result indicates that the method advanced in this paper is very potent.

关 键 词：小波分解 亮度矩 车牌定位 图像分割 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]