Incremental Unsupervised-Learning of Appearance Manifold with View-Dependent Covariance Matrix for Face Recognition from Video Sequences.
LinaTomokazu TakahashiIchiro IdeHiroshi MurasePublished in: IEICE Trans. Inf. Syst. (2009)
Keyphrases
- covariance matrix
- appearance manifolds
- unsupervised learning
- face recognition
- principal component analysis
- human faces
- face images
- facial expressions
- video sequences
- dimensionality reduction
- low dimensional
- d scene
- appearance model
- sample size
- feature extraction
- image set
- face detection
- semi supervised
- lighting conditions
- model selection
- high dimensional data
- feature selection
- machine learning
- expectation maximization
- depth map
- multi view
- multiple views
- viewpoint
- high dimensional
- video data
- input data
- object detection
- input image
- multiscale