摘要： 用Rough集理论提取车牌中的文字、字母、数字、短横线的特征，再用这些特征进行模板匹配。该文中的基于Rough集可辨矩阵的特征选择算法，时间复杂度为O(mn2)，改变了过去人们认为基于可辨矩阵的特征选择算法的时间复杂度不低于O(m2n2)的观点（其中m为数据集中特征/属性的个数，n为数据集中样本的个数）。给出了在车牌识别中的实验结果。

关键词: Rough集, 车牌识别, 特征选择, 二进制可辨矩阵

Abstract: This paper extracts the features of Chinese characters, letters, numbers and short across line based on Rough sets. Result by template matching can be obtained. The time complexity of feature selection algorithm based on Rough sets is O(mn2). Before, people think that the time complexity of feature selection algorithm based on Rough sets can not be under O(m2n2) in which m is the number of features, n is the number of samples in datasets. Finally, the experiment and results in license plate recognition are presented.

Key words: Rough sets, License plate recognition, Feature selection, Binary discernibility matrix