Bilinear Lanczos components for fast dimensionality reduction and feature extraction

DOI10.1016/J.PATCOG.2010.04.029MaRDI QIDQ991249zbMATH OpenOpenAlexFDO

Authors Chuan-Xian Ren, Dao-Qing Dai

Publication date 2 September 2010

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2010.04.029

zbMATH Keywords

dimensionality reductionface recognitionfeature extractionimage classificationbilinear Lanczos componentfast low-rank approximation

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Recommendations

• Inexact and incremental bilinear Lanczos components algorithms for high dimensionality reduction and image reconstruction
• A bilinear algorithm for sparse representations
• Low-rank bilinear classification: efficient convex optimization and extensions
• Lanczos bidiagonalization: a fast start for nonnegative matrix factorization
• Fast, deterministic and sparse dimensionality reduction
• A unified framework for linear dimensionality reduction in L1
• Fast and Orthogonal Locality Preserving Projections for Dimensionality Reduction
• Linear low-rank approximation and nonlinear dimensionality reduction

Cites work

• scientific article; zbMATH DE number 1049353 (Why is no real title available?)
• scientific article; zbMATH DE number 1069613 (Why is no real title available?)
• A Lanczos bidiagonalization algorithm for Hankel matrices
• A Multilinear Singular Value Decomposition
• ASYMPTOTIC BEHAVIOR OF THE KRYLOV–LANCZOS INTERPOLATION
• An analytical algorithm for generalized low-rank approximations of matrices
• Analysis of the symmetric Lanczos algorithm with reorthogonalization methods
• From image vector to matrix: A straightforward image projection technique -- IMPCA vs. PCA
• Generalized low rank approximations of matrices
• Handwritten digit recognition: Benchmarking of state-of-the-art techniques.
• Handwritten digit recognition: Investigation of normalization and feature extraction techniques.
• Incremental learning of bidirectional principal components for face recognition
• Preconditioned Lanczos method for generalized Toeplitz eigenvalue problems
• Rational Lanczos approximations to the matrix square root and related functions.
• Sparsity preserving projections with applications to face recognition
• Spectral decomposition of a 4th-order covariance tensor: applications to diffusion tensor MRI
• The theoretical analysis of GLRAM and its applications

Cited in

(7)

• The theoretical analysis of GLRAM and its applications
• A probabilistic model for image representation via multiple patterns
• Inexact and incremental bilinear Lanczos components algorithms for high dimensionality reduction and image reconstruction
• Matrix-free Krylov iteration for implicit convolution of numerically low-rank data
• Low-rank bilinear classification: efficient convex optimization and extensions
• An analytical algorithm for generalized low-rank approximations of matrices
• Efficient L1-Norm Principal-Component Analysis via Bit Flipping

Describes a project that uses

Uses Software

• ORL face
• CMU PIE

This page was built for publication: Bilinear Lanczos components for fast dimensionality reduction and feature extraction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q991249)