基于融合子空间的人脸识别方法

A New Face Recognition Method Based on The Combination of Multi-Subspace

针对PCA、LDA、Bayesian 3种子空间方法,介绍了这3种子空间判别人脸的原理,用一种新颖的思想分析了3种子空间的判别依据,在此基础上来提出了一种改进的子空间识别方法——融合子空间。实验结果证明,该方法跟传统的PCA、LDA和Bayesian子空间识别方法相比,有效的增加了对表情和光照的鲁棒性,并提高了识别率。

In this paper,we first analysis the principal of the three subspace methods,PCA、LDA、Bayesian and their discriminate function.On this basic,a new method-the combination of Multi-Subspace is introduced.The experimental results show that it effectively improves the recognition rate,and enhance the robustness of both illumination and position.