小样本条件下采用Gabor特征的人脸识别

人脸表征和特征提取是人脸识别中的关键问题．针对Gabot特征的识别能力问题，利用点分布模型和类别可分离性判据研究了人脸不同位置和不同Gabor展开系数的分类能力．实验结果表明，合理地构造Gabor特征和选择特征点位置，能够提高识别率和减少特征数量．在此基础上，提出了在小样本条件下结合主动形状模型和Gabor特征进行人脸识别的方法．

Face Recognition Using Gabor Feature with Small Samples

Face representation and feature extraction are the key problems to face recognition. We perform feature selection based on PDM and discriminating power of Gabor features in different locations, orientations and scales. Experiments show that these methods achieve higher recognition rate with fewer features. In the paper we have also proposed a novel face recognition method based on active shape model (ASM) and Gabor transform.