(2D)2UDP: A New Two-Directional Two-Dimensional Unsupervised Discriminant Projection for Face Recognition

Author

Li, Yong-zhi ; He, Guang-ming ; Yang, Jing-Yu ; Wang, Yu-ping

Author_Institution

Sch. of Inf. Sci. & Technol., Nanjing Forestry Univ., Nanjing

Volume

4

fYear

2008

fDate

18-20 Oct. 2008

Firstpage

3

Lastpage

7

Abstract

Based on manifold learning, a new feature extraction method is proposed for face recognition in the paper. The new method is called two-directional two-dimensional unsupervised discriminant projection ((2D)²UDP), which simultaneously works image matrix in the row direction and in the column direction for feature extraction. The experimental results on ORL face databases and AR face databases indicate that the proposed method has higher recognition rate and more stable.

Keywords

face recognition; feature extraction; learning (artificial intelligence); AR face databases; ORL face databases; face recognition; feature extraction method; image matrix; manifold learning; two-directional two-dimensional unsupervised discriminant projection; Face recognition; Feature extraction; Forestry; Image databases; Information science; Laplace equations; Paper technology; Principal component analysis; Scattering; Spatial databases; face recognition; feature extraction; manifold-learning techniques; unsupervised discriminant projection;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation, 2008. ICNC '08. Fourth International Conference on

Conference_Location

Jinan

Print_ISBN

978-0-7695-3304-9

Type

conf

DOI

10.1109/ICNC.2008.657

Filename

4667237