Face recognition;
Low dimensional manifold;
Small Sample Size;
Matrix exponential;
Exponential discriminant locality projections;
EIGENFACES;
SAMPLE;
D O I:
10.1016/j.neucom.2016.02.063
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
How to determine the low dimensional manifold is a challenging problem. Locality Preserving Projections (LPP) can gracefully deal with it. With the help of discriminant information provided by Discriminant Locality Preserving Projection (DLPP), the performance of face recognition can be significantly improved. In the real world, the DLPP has the Small Sample Size (SSS) problem. To deal with this issue, we utilize the matrix exponential to obtain more effective information, which can avoid the singular matrix's disadvantages. Thus, in this paper, we propose an effective and efficient algorithm called Exponential discriminant locality projections (EDLPP) for face recognition. The experimental results on three challenging benchmark datasets (ORL, YALE and LFW) demonstrate that the proposed EDLPP algorithm outperforms favorably against several state-of-the-art methods. (C) 2016 Elsevier B.V. All rights reserved.