The Use of Dynamic Deformable Templates for Lip Tracking in an Audio-Visual Corpus with Large Variations in Head Pose, Face Illumination and Lip Shapes.
Zhiyong WuJiying WuHelen M. MengPublished in: ISCSLP (2008)
Keyphrases
- facial features
- head motion
- audio visual
- deformable templates
- gabor wavelets
- audio visual speech recognition
- face pose
- illumination variations
- face images
- facial expressions
- pose variations
- multi modal
- multi stream
- face detection
- head tracking
- face model
- human faces
- shape variations
- face recognition
- object tracking
- template matching
- partial occlusion
- feature points
- facial images
- lighting conditions
- image matching
- illumination conditions
- visual information
- deformable template
- appearance variations
- visual data
- multimedia
- active appearance models
- shape model
- keypoints
- visual speech
- data sets
- computer vision
- image sequences
- video sequences
- principal component analysis