中文摘要：

根据车牌区域内字符的纹理特征以及车牌的颜色特征,提出了一种基于相似度的模板匹配车牌定位方法。该算法先对车牌区域构造出相应的模板,同时分别构造出模板与待定位图像的模糊集,再根据所构造出的模糊集,用滑动窗法计算模板与当前窗口的相似度,得到一个相似度矩阵。取其中最大相似度所对应的区域作为车牌候选区,通过对该候选区进行判断与精确定位分割出车牌区域。实验结果表明该方法能得到较理想的车牌定位效果。

英文摘要：

According to the characteristics of the texture on a car license plate（CLP）,and the characteristics of the color on the CLP,a new location method based on similarity measure template matching is proposed in this paper.The template for representing license plates and the fuzzy sets for representing the template and car pictures are structured,respectively.The similarity for each template size location of each photo is estimated by using the method of sliding windows,and matrices of similarity are gotten.The location with the maximum similarity as the range of interesting（ROI） will be chosen.Through processing the ROI,the CLP zone can be segmented easily.The experimental results show that the method is effective for car license plate location.