基于数学形态法和主成分分析法的车牌定位  

Vehicle License Plate Location Based on Mathematical Morphology and PCA

作　　者：张宇[1] 黄险峰[1] 

机构地区：[1]五邑大学信息学院,江门529020

出　　处：《计算机与数字工程》2009年第4期130-134,共5页Computer & Digital Engineering

摘　　要：作为车牌识别的首要和关键技术,车牌定位的结果直接决定了识别的成败。新的方法充分利用车牌图像的位置、形状、纹理、颜色等特征,结合数学形态法进行车牌定位,并以主成分分析法进行车牌倾斜校正。试验结果表明,新的方法能够快速而准确得定位车牌。As the chiefly and the key technique of the vehicle license plate recognition （VLPR）, the result of vehicle license plate location and character segmentation directly decide recognition success or failure. The new method which used vehicle license characteristics fully and so on image position, shape, texture, color, combined the Mathematical Morphology method to located plate, and rectified the plate in method of principal component analysis（PCA）. Experimental results demonstrate that the new method location the plate fast and accurately.

关 键 词：HSI 特征颜色对 数学形态法 区域扩展 主成分分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]