疲劳驾驶面部表情识别算法

针对疲劳驾驶的六种表情 ,提出几何规范化结合 Gabor滤波提取表情特征 ,使用支持向量机对疲劳驾驶的面部表情分类识别的系统。首先对视频图像预处理进行几何规范化 ,利用二维 Gabor核函数构造最优滤波器 48个,获取 48个面部表情特征点 ,最后利用支持向量机进行面部表情分类识别。实验结果表明径向基函数的 SVM性能最好。

Facial expression recognition algorithm for fatigue driving

This paper proposed an expression recognition system based on geometry standardization, Gabor wavelet filter and support vector machine ( SVM) according to six face expression of fatigue driving. The system ensured the geometry standardi-zation of video. Then it constituted forty-eight optimization filters according to 2D-Gabor kernel functions to acquire forty-eight expressional feature point inside the latency rectangle region. It was applied to recognizing facial expression using SVM. Ex-perimental results demonstrate that RBF the radial basis function( RBF) SVM has better performance than other SVMs on hu-man facial expression recognition, and prove that the algorithm is efficient and feasible.