Publications:Lip Biometrics for Digit Recognition


Do not edit this section

Keep all hand-made modifications below

Title Lip Biometrics for Digit Recognition
Author Maycel I. Faraj and Josef Bigun
Year 2007
PublicationType Conference Paper
HostPublication Computer Analysis of Images and Patterns, Proceedings
Conference 12th International Conference on Computer Analysis of Images and Patterns, Vienna, AUSTRIA, AUG 27-29, 2007
Diva url
Abstract This paper presents a speaker-independent audio-visual digit recognition system that utilizes speech and visual lip signals. The extracted visual features are based on line-motion estimation obtained from video sequences with low resolution (128 ×128 pixels) to increase the robustness of audio recognition. The core experiments investigate lip motion biometrics as stand-alone as well as merged modality in speech recognition system. It uses Support Vector Machines, showing favourable experimental results with digit recognition featuring 83% to 100% on the XM2VTS database depending on the amount of available visual information.