Three-dimensional view-invariant face recognition using a hierarchical pose-normalization strategy.
Martin D. LevineAjit RajwadePublished in: Mach. Vis. Appl. (2006)
Keyphrases
- view invariant
- three dimensional
- pose normalization
- d objects
- multi view
- single view
- action recognition
- viewpoint
- human faces
- multiple viewpoints
- facial features
- shape model
- human actions
- surface reconstruction
- facial expressions
- image sequences
- pose estimation
- keypoints
- range images
- pairwise
- principal component analysis
- coarse to fine
- human motion
- gaussian process regression
- spatio temporal
- machine learning