基于字符特征与支持向量机的车牌字符识别

Research on License Plate Character Recognition Based on Character characteristic and Support Vector Machine

首先,对车牌图像进行预处理,针对不同的字符样本采用不同特征提取方法;然后,用提取的特征训练SVM分类器。结果表明,在训练样本较少的情况下,该系统具有较高的识别率和识别速度,并具有很好的分类推广能力。

First, this article carries on the pretreatment to the car license image, uses the different feature extraction method in view of the different character sample; Then, trains the SVM sorter with the extraction characteristic. The results show that, in the case of small samples, the method has the high recognition rate and speed, and has the very good classified promotion ability.