Title :
Properties of Separable Covariance Matrices and Their Associated Gaussian Random Processes
Author :
Therrien, C. W. ; Fukunaga, Kaori
Author_Institution :
Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA 02173.
Abstract :
A number of properties of separable covariance matrices are summarized. Expressions for the divergence of the corresponding two-dimensional Gaussian random processes are given in terms of row and column covariance matrices, and in terms of linear prediction parameters and maximum likelihood spectral estimates. Such time and frequency domain expressions are not widely known, even for one-dimensional random processes.
Keywords :
Covariance matrix; Eigenvalues and eigenfunctions; Frequency domain analysis; Image analysis; Image texture analysis; Laboratories; Matrix decomposition; Maximum likelihood estimation; Random processes; Direct product; Kronecker product; separable covariance matrix; two-dimensional correlation; two-dimensional linear prediction; two-dimensional spectral estimate;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1984.4767580
