Local binary patterns for lip motion analysis

Publikationstyp
Conference Paper
Date Issued
2008-12-01
Sprache
English
Author(s)
Kricke, Ralph  
Gernoth, Thorsten  
Grigat, Rolf-Rainer  
Institut
Bildverarbeitungssysteme E-2  
TORE-URI
http://hdl.handle.net/11420/10067
Start Page
1472
End Page
1475
Article Number
4712044
Citation
15th IEEE International Conference on Image Processing, 2008 (ICIP 2008): 1472-1475, 4712044
Contribution to Conference
15th IEEE International Conference on Image Processing (ICIP 2008)  
Publisher DOI
10.1109/ICIP.2008.4712044
Scopus ID
2-s2.0-69949180774
Publisher
IEEE
ISBN
978-1-4244-1765-0
Lip motion analysis can enhance a security system based on face recognition significantly. Examining speaker dependent lip movements and visually determining the spoken content can prevent attacks using photographs or pre-recorded video sequences. Our system operates under active near infrared illumination. We investigate the use of a new type of features, namely local binary patterns, to model lip motions with hidden Markov models. We evaluate the classification accuracy with the TUNIR database, which we made available to the public for the future comparison of competing approaches.
Subjects
Biometric authentication
Infrared imaging
DDC Class
600: Technik