基于Contourlet变换与FLD的人脸表情识别方法

提出了一种基于Contourlet变换与FLD的人脸表情特征提取方法。Contourlet变换是一种新的多尺度几何分析方法,它在具备小波变换的多分辨率特性和时频局部特性的同时,还具有很强的多方向选择性和各向异性。图像经过Contourlet变换后的低频分量可体现表情的概貌,高频方向子带可体现表情的轮廓和纹理等细节。将低频分量与部分高频方向子带结合起来作为整体特征,可压缩图像的数据量,并能够体现表情的本质特征。首先用Fisher线性判别法(FLD)进行特征提取,然后采用K-近邻法进行分类。实验证明,该方法比经典的FLD方法有着更快的特征提取速度和更高的表情识别率。

Facial expression recognition method based on Contourlet transform & FLD

A facial expression feature extraction method is presented based on Contourlet transform and FLD.The Contourlet transform is a new image multiscale geometric analysis method,which not only has the multi-resolution and local time-frequency characters of wavelet transform,but also has directionality and anisotropy.The LF-Components of image processed by Contourlet indicate the expression's approximately while the HF-Components are the details of the expression's contour and texture.A new method is proposed: f...