Multi-Vector Feature Space Based on Pseudo-Euclidean Space and Oblique Basis for Similarity Searches of Images.
Yasuo YamaneTadashi HoshiaiHiroshi TsudaKaoru KatayamaManabu OhtaHiroshi IshikawaPublished in: CVDB (2004)
Keyphrases
- euclidean space
- riemannian manifolds
- vector space
- pairwise distances
- similarity search
- metric space
- feature space
- low dimensional
- image retrieval
- image data
- high dimensional
- data points
- input image
- embedding space
- three dimensional
- feature vectors
- mean shift
- image analysis
- image collections
- edge detection
- image set
- geodesic distance
- dimensional euclidean space
- image registration
- query processing
- high dimensional data
- database management systems
- parameter space
- dimensionality reduction
- principal component analysis
- shape analysis
- dissimilarity measure
- pairwise
- training set
- data structure
- similarity searching
- fisher information
- decision trees
- image processing