基于Gabor直方图特征和MVBoost的人脸表情识别

Facial Expression Recognition Based on Gabor Histogram Feature and MVBoost

提出采用Gabor变换与分级直方图统计相结合的方法来提取表情特征,以分层次反映局部区域内纹理变化的信息.这比仅用一维的Gabor系数具有更强的特征表示能力.借助直方图特征,还设计了向量输入、多类连续输出的弱分类器,并嵌入到多类连续AdaBoost的算法框架中,得到了向量输入、多类输出的MVBoost方法.该方法直接对特征进行多类的判决以满足多类时分类的需求,而不必训练多个二分类的AdaBoost分类器,从而使训练过程和分类过程都得到简化.

In this paper, the Gabor transform is combined with the hierarchical histogram to extract facial expressional features, which could hierarchically represent the change of texture in local area, and thus capture the intrinsic facial features involved in facial expression analysis. In addition, Gabor transform is relatively less sensitive to the change of lighting conditions and can thus tolerates certain rotation and deformation of images. All these properties make this representation scheme quite robust in various conditions and more powerful than traditional representation scheme using 1-D Gabor coefficients. With the histogram feature used, a weak classifier which uses vectors as input and multi-class real values as output is designed to classify facial expression. This weak classifier has been embedded into the multi-class real AdaBoost algorithm to meet the request of multi-class classification of facial expression. The resulted method （named MVBoost） directly assigns a multi-class label to every input image. Thus it needs not to train many two-class classifiers to meet the request of multi-class classification. The training process and classification process are both simplified. Experiments conducted on common database show the efficiency and effectiveness of the proposed technique. It is expected that this new technique will make contribution to fast and robust facial expression recognition.