基于支持向量机的交通标志识别方法研究

提出一种基于支持向量机的交通标志识别算法。该算法利用交通标志的形状和颜色特征,对在环境中的交通标志图像进行交通标志定位和种类划分,然后利用Hu不变矩对各种类中的交通标志进行特征值提取。最后将特征值输入到支持向量机中,利用支持向量机良好的学习和泛化能力对交通标志进行识别。实验结果表明此方法对交通标志识别准确性很高。

Study on Traffic Sign Recognition Based on Support Vector Machine

This paper presented a traffic sign recognition algorithm based on SVM(support vector machine).The algorithm used the color and shape features of traffic signs to locate and divide traffic signs in the mages.Then, extracted eigenvalues of traffic signs by Hu invariant moments.Finally,eigenvalues were inputed to SVM.and recongized traffic signs by SVM which has good learning and generalization ability.The experiment results show high detection accuracy for traffic signs.