On the relationships between SVD, KLT and PCA
- 1 January 1981
- journal article
- Published by Elsevier BV in Pattern Recognition
- Vol. 14 (1-6), 375-381
- https://doi.org/10.1016/0031-3203(81)90082-0
Abstract
In recent literature on digital image processing much attention is devoted to the singular value decomposition (SVD) of a matrix. Many authors refer to the Karhunen-Loeve transform (KLT) and principal components analysis (PCA) while treating the SVD. In this paper we give definitions of the three transforms and investigate their relationships. It is shown that in the context of multivariate statistical analysis and statistical pattern recognition the three transforms are very similar if a specific estimate of the column covariance matrix is used. In the context of two-dimensional image processing this similarity still holds if one single matrix is considered. In that approach the use of the names KLT and PCA is rather inappropriate and confusing. If the matrix is considered to be a realization of a two-dimensional random process, the SVD and the two statistically defined transforms differ substantially.This publication has 5 references indexed in Scilit:
- Singular Value Decomposition (SVD) Image CodingIEEE Transactions on Communications, 1976
- Singular value decompositions and digital image processingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Outer Product Expansions and Their Uses in Digital Image ProcessingIEEE Transactions on Computers, 1976
- Image restoration by singular value decompositionApplied Optics, 1975
- The Design of Multistage Separable Planar FiltersIEEE Transactions on Geoscience Electronics, 1971