Automatic Extraction of Lip Feature Points

Authors: Roland Göcke, J Bruce Millar, Alexander Zelinsky, and Jordi Robert-Ribes

Presented by Roland Göcke at the Australian Conference on Robotics and Automation ACRA 2000, Melbourne, Australia, 30 August - 1 September 2000


We present a novel algorithm for the robust and reliable automatic extraction of lip feature points for speechreading. The algorithm uses a combination of colour information in the image data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence measure quantifying how well the feature extraction process worked is introduced. A parameter set describing the shape of the mouth is derived from the positions of the feature points. Using a stereo camera system, measurements are in 3D. Such a 3D parameter set is of great value for automatic speech-reading systems.

Download (649kB, PDF)

[Homepage] [Research] [Publications]

(c) Roland Göcke
Last modified: Wed Nov 24 13:46:12 AUS Eastern Daylight Time 2004