Fusing shape and texture features for pose-robust face recognition

Publikationstyp
Conference Paper
Date Issued
2012-02-02
Sprache
English
Author(s)
Gernoth, Thorsten  
Grigat, Rolf-Rainer  
Herausgeber*innen
Bingham, Philip R.  
Lam, Edmund Y.  
Institut
Bildverarbeitungssysteme E-2  
TORE-URI
http://hdl.handle.net/11420/10010
First published in
Proceedings of SPIE  
Number in series
8300
Article Number
830006
Citation
Proceedings of SPIE - The International Society for Optical Engineering 8300: 830006 (2012)
Contribution to Conference
SPIE medical imaging, 2012  
Publisher DOI
10.1117/12.909070
Scopus ID
2-s2.0-84859469433
Publisher
SPIE
ISBN
978-0-8194-8947-0
Unconstrained environments with variable ambient illumination and changes of head pose are still challenging for many face recognition systems. To recognize a person independent of pose, we separate shape from texture information using an active appearance model. We do not directly use the texture information from the active appearance model for recognition. Instead we extract local texture features from a shape and pose free representation of facial images. We use a smooth warp function to transform the images. We compensate also the shape information for head pose changes and fuse the results of separate classiers for shape features and local texture features. We analyze the inuence of the individual contributions of shape and texture information on the recognition performance. We show that fusing shape and texture information can boost the recognition performance in an access control scenario.
Subjects
active appearance model
discrete cosine transform
face recognition
Infrared imaging
DDC Class
004: Informatik
More Funding Information
This work is part of the project KABTEC - Kabienentechnologien für kompfortable Passagierplattformen funded by the German Federal Ministry of Economics and Technology.