Sciweavers

6 search results - page 1 / 2
» Robust Face Recognition from a Single Training Image per Per...
Sort
View
ISNN
2004
Springer
13 years 10 months ago
Robust Face Recognition from a Single Training Image per Person with Kernel-Based SOM-Face
In this paper, a kernel-based SOM-face method is proposed to recognize expression variant faces under the situation of only one training image per person. Based on the localization...
Xiaoyang Tan, Songcan Chen, Zhi-Hua Zhou, Fuyan Zh...
PR
2006
113views more  PR 2006»
13 years 4 months ago
Face recognition from a single image per person: A survey
One of the main challenges faced by the current face recognition techniques lies in the difficulties of collecting samples. Fewer samples per person mean less laborious effort for...
Xiaoyang Tan, Songcan Chen, Zhi-Hua Zhou, Fuyan Zh...
PRL
2002
146views more  PRL 2002»
13 years 4 months ago
Face recognition with one training image per person
: Recently, a method called (PC)2 A was proposed to deal with face recognition with one training image per person. As an extension of the standard eigenface technique, (PC)2 A comb...
Jianxin Wu, Zhi-Hua Zhou
IDEAL
2005
Springer
13 years 10 months ago
Weighted SOM-Face: Selecting Local Features for Recognition from Individual Face Image
Abstract. In human face recognition, different facial regions have different degrees of importance, and exploiting such information would hopefully improve the accuracy of the reco...
Xiaoyang Tan, Jun Liu, Songcan Chen, Fuyan Zhang
ECCV
2004
Springer
13 years 10 months ago
Pose Invariant Face Recognition Under Arbitrary Unknown Lighting Using Spherical Harmonics
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Lei Zhang 0002, Dimitris Samaras