基于Gabor特征提取和SVM交通标志识别方法研究

Research on traffic sign recognition based on Gabor feature extraction and SVM

交通标志识别是智能车辆基于视觉传感感知道路信息的关键技术,针对传统识别技术不能满足实时性和准确性的要求,采用一种基于Gabor特征提取和支持向量机(SVM)交通标志识别方法。首先选定交通标志图像进行灰度化、图像增强处理,采用Gabor滤波技术进行特征提取,针对大量的特征信息采用主成分分析(PCA)降维,并用支持向量机分类识别。最后在Matlab平台上进行实验,验证该方法的识别率和识别时间。实验结果表明,该方法较传统方法识别精度高,实时性好。

The traffic sign recognition is the key technology based on vision sensing of intelligent vehicle to sense the road information.Since the traditional identification technology can′t satisfy the requirements of real?time performance and accuracy,a traffic sign recognition method based on Gabor feature extraction and support vector machine(SVM)is proposed.The traffic sign image is selected for graying and image enhancement.The Gabor filtering technology is used to extract the feature of the image.The principal component analysis(PCA)is used to reduce the dimensions of the massive feature information,and the SVM is used to classify and recognize the traffic signs.The experiments are carried out with Matlab platform to verify the recognition rate and recognition time of this method.The experiment results show this method has higher recognition accuracy and better real?time performance than the traditional methods.