[1]WANG Yongmao,XU Zhengguang,WU Jinxia.Face Recognition Based on Label Multiple Kernel Locat Discriminant Embedding[J].Journal of Zhengzhou University (Engineering Science),2012,33(03):125-128.[doi:10.3969/j.issn.1671-6833.2012.03.032]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
33卷
Number of periods:
2012 03
Page number:
125-128
Column:
Public date:
2012-05-10
- Title:
-
Face Recognition Based on Label Multiple Kernel Locat Discriminant Embedding
- Author(s):
-
WANG Yongmao; XU Zhengguang; WU Jinxia
-
1.School of Automation, University of Seience and Technology af Beijing, Beijing 100083, Chinn;2. Sehool of Computer Sei.ence and Technology, Henan Polytechnie University, Jiaozuo 454003, China
-
- Keywords:
-
face recognition ; subspace leaming; label multiple kemel; dimensionality reduction
- CLC:
-
TP391.4
- DOI:
-
10.3969/j.issn.1671-6833.2012.03.032
- Abstract:
-
Based on loeal discriminant embedding, an efficient nonlinear subspace leaming method, LabelMuliple Kemel local Discriminant Embedding ( LMKLDE ) , is developed, Firstly, according to the label in-formation of given data set, local kerel function is defined and multiple kernel is gained, Then, different lo-eal kerel funetions are merged by linear combination to form final kernel funetion. Finally, LMKiDE is de-veloped by introducing label multiple kernel to LDE in order to deal with datasets of highly nonlinear struc.ture. Experiments on ORL, and Yale face database demonstrate the effectiveness of the proposed method.