Lip Feature Extraction Using Red Exclusion

Lewis, T.W. and Powers, D.M.W.

    Automatic speech recognition (ASR) performs well under restricted conditions, but performance degrades in noisy environments. Audio-Visual Speech Recognition (AVSR) combats this by incorporate a visual signal into the recognition. This paper briefly reviews the contribution of psycholinguistics to this endeavour and the recent advances in machine AVSR. An important first step in AVSR is that of feature extraction from the mouth region. This paper examines several well-known pixel based techniques - grayscale, horizontal edge, red and hue colour space - and compare how well they work on our naturalistic database. Finally, a novel method of feature extraction, red exclusion, is described that outperforms the others on this data set.
Cite as: Lewis, T.W. and Powers, D.M.W. (2001). Lip Feature Extraction Using Red Exclusion. In Proc. Selected papers from Pan-Sydney Area Workshop on Visual Information Processing (VIP2000), Sydney, Australia. CRPIT, 2. Eades, P. and Jin, J., Eds. ACS. 61-67.
pdf (from pdf (local if available) BibTeX EndNote GS