Dimensionality reduction based on minimax risk criterion for face recognition.
Lei TangYing-Ke LeiLin ZhuDe-Shuang HuangPublished in: IJCNN (2010)
Keyphrases
- dimensionality reduction
- face recognition
- linear discriminant analysis
- principal component analysis
- linear dimensionality reduction
- feature extraction
- subspace learning
- neighborhood preserving
- neyman pearson
- discriminant analysis
- face images
- high dimensional
- class separability
- feature selection
- sparse representation
- kernel discriminant analysis
- high dimensional data
- recognition rate
- locality preserving projections
- low dimensional
- high dimensionality
- dimensionality reduction methods
- risk management
- decision making
- pattern recognition
- kernel pca
- facial images
- data representation
- manifold learning
- face databases
- risk assessment
- minimax regret
- principal components
- high risk
- local binary pattern
- neighborhood preserving embedding
- pattern recognition and machine learning
- feature space
- structure preserving
- optimization criterion
- computer vision
- worst case
- alpha beta
- human faces
- kernel learning
- face verification
- risk factors
- evaluation function
- neural network
- face detection
- high resolution
- lower dimensional
- search algorithm
- support vector