基于全局和局部特征集成的人脸识别

Integration of Global and Local Feature for Face Recognition

提出利用一种串、并行结合的方式将全局和局部面部特征进行集成:首先利用全局特征进行粗略的匹配,然后再将全局和局部特征集成起来进行精细的确认.在该方法中,全局和局部特征分别采用傅里叶变换和Gabor小波变换进行提取.两个大规模的人脸库(FERET and FRGCv2.0)上的实验结果表明,此方法不仅可以显著提高系统的精度,而且可以提升系统的速度.

This paper proposes to combine the global and local facial features in both serial and parallel manner. Firstly, global features are used for coarse classification. Then, global and local features are integrated for fine classification. In the proposed method, global and local features are extracted by Discrete Fourier Transform （DFT） and Gabor Wavelets Transform （GWT） respectively. Experiments on two large scale face databases （FERET and FRGC v2.0） validate that the proposed method can not only greatly increase the system accuracy but also improve the system speed.