Constrained discriminant neighborhood embedding for high dimensional data feature extraction.
Bo LiLei LeiXiao-Ping (Steven) ZhangPublished in: Neurocomputing (2016)
Keyphrases
- high dimensional data
- feature extraction
- dimensionality reduction
- locality preserving projections
- nonlinear dimensionality reduction
- linear discriminant analysis
- low dimensional
- discriminant analysis
- principal component analysis
- discriminant information
- manifold learning
- discriminant embedding
- graph embedding
- dimension reduction
- high dimensional
- small sample size
- low dimensional structure
- subspace clustering
- high dimensionality
- similarity search
- nearest neighbor
- vector space
- feature space
- high dimensions
- neighborhood graph
- data sets
- input space
- pattern recognition
- data points
- face recognition
- sparse representation
- data analysis
- high dimensional data sets
- feature vectors
- clustering high dimensional data
- high dimensional datasets
- locally linear embedding
- latent space
- image processing
- high dimensional spaces
- low rank
- feature selection
- dimensionality reduction methods
- dimensional data
- subspace learning
- lower dimensional
- low dimensional manifolds
- machine learning
- geodesic distance
- euclidean space
- data distribution
- underlying manifold
- support vector machine svm
- input data
- multi dimensional