Exploring the effects of scatter matrices, eigenvalue decomposition methods, and regularization techniques in feature extractions for small sample size classification problem.
Bor-Chen KuoKuang-Yu ChangShu-Chuan ShihShih-Hsun LiPublished in: IGARSS (2005)
Keyphrases
- small sample size
- scatter matrices
- linear discriminant analysis
- high dimensionality
- decomposition methods
- sample size
- face recognition
- high dimensional
- microarray data
- null space
- discriminant analysis
- high dimensional data
- dimensionality reduction
- dimension reduction
- feature selection
- pattern recognition
- feature space
- feature vectors
- feature extraction
- support vector machine svm
- optimization criterion
- decomposition method
- covariance matrix
- model selection
- principal component analysis
- least squares
- feature set
- latent dirichlet allocation
- decision trees
- image processing
- constraint satisfaction problems
- training data
- database theory
- discriminative information
- gaussian distribution
- data analysis