基于支持向量机的轿车车型识别

Recognition of car model based on support vector machine

为了从轿车图像中快速、准确地识别出轿车车型,采用支持向量机(Support Vector Ma-chine,SVM)方法作为分类器,以轿车的长、宽、高和轴距等4个特征参数作为输入特征向量,并根据这些特征向量对不同车型进行分类和识别.实验结果表明,对11个品牌15种车型的识别准确率达100%.本研究表明,在正确选取轿车的特征参数基础上,采用SVM方法识别轿车车型可以达到很好的效果,SVM方法在智能交通管理系统等领域具有较高的应用价值.

To recognize models from the car pictures quickly and accurately,the Support Vector Machine（SVM） method is used as classifier,and four feature parameters of cars,including length,width,height and wheelbase,are chosen as the input of characteristic vectors,and variant car models are classified and identified according to the characteristic vectors.The experimental results show that accuracy rate of recognition reaches 100% for as many as 15 various models of 11 brands.The experiment indicates that car model recognition based on the right selection of feature parameters is of good performance by using the SVM method.This SVM method has a high application value in the intelligent traffic management systems and other relative fields.