Title
Pose-Independent Face Identification from Video Sequences
Abstract
A scheme for pose-independent face recognition is presented. An "unwrapped" texture map is constructed from a video sequence using a texture-from-motion approach, which is shown to be quite accurate. Simple lighting normaliza- tion methods improve robustness to directional and/or varying lighting con- ditions. Recognition of single frames against calculated unwrapped textures is carried out using principal component analysis. The system is typically better than 90% correct in its identifications.
Year
DOI
Venue
2001
10.1007/3-540-45344-X_2
AVBPA
Keywords
Field
DocType
principal component analysis,video sequences,single frame,pose-independent face recognition,calculated unwrapped texture,texture map,pose-independent face identification,video sequence,texture-from-motion approach,texture mapping,face recognition
Facial recognition system,Texture mapping,Computer vision,Authentication,Convolutional neural network,Computer science,Image processing,Artificial intelligence,Biometrics,Principal component analysis
Conference
Volume
ISSN
ISBN
2091
0302-9743
3-540-42216-1
Citations 
PageRank 
References 
1
0.41
9
Authors
2
Name
Order
Citations
PageRank
Michael C. Lincoln110.41
Adrian F. Clark222172.99