节点文献
利用支持向量机SVM~★识别车辆类型
Vehicle Type Recognition by Using Support Vector Machine SVM~★
【摘要】 支持向量机(SupportVectorMachine,SVM)分类方法在实际二类分类问题的应用中显示出良好的学习和泛化能力,已被广泛地应用于多类分类问题的研究.以车辆轮廓特征为对象,将二类分类支持向量机SVM★应用于多类车辆类型的识别,并与其它分类器的分类结果进行了对比.通过9次交叉验证实验,结果表明SVM★对车辆数据样本的测试准确率达到了85.59%,其分类性能优于其它分类器.
【Abstract】 The Support Vector Machine(SVM) has shown excellent learning and generalization ability in the practice problems of binary classification,and has been widely employed in multi-class classification.Based on the framework features of the vehicles,the SVM★ is used to classify 4 types of vehicles.The results of the SVM★ are compared with that of different classifiers.The testing accuracy to this vehicle dataset reaches 85.59% by means of 9-fold cross-validation which demonstrates that the classification performance of SVM★ is superior to those of other classifiers.
【Key words】 support vector machine(SVM); vehicle recognition; framework feature;
- 【文献出处】 重庆大学学报(自然科学版) ,Journal of Chongqing University(Natural Science Edition) , 编辑部邮箱 ,2006年01期
- 【分类号】TP391.4
- 【被引频次】7
- 【下载频次】295