Title :
Wiener filters in canonical coordinates for transform coding, filtering, and quantizing
Author :
Scharf, Louis L. ; Thomas, John K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Colorado Univ., Boulder, CO, USA
fDate :
3/1/1998 12:00:00 AM
Abstract :
Canonical correlations are used to decompose the Wiener filter into a whitening transform coder, a canonical filter, and a coloring transform decoder. The outputs of the whitening transform coder are called canonical coordinates; these are the coordinates that are reduced in rank and quantized in our finite-precision version of the Gauss-Markov theorem. Canonical correlations are, in fact, cosines of the canonical, angles between a source vector and a measurement vector. They produce new formulas for error covariance, spectral flatness, and entropy
Keywords :
Markov processes; Wiener filters; adaptive filters; adaptive signal processing; correlation methods; decoding; entropy; filtering theory; matrix decomposition; quantisation (signal); singular value decomposition; transform coding; Gauss-Markov theorem; Wiener filters; adaptive canonical coordinates; angles; canonical correlations; canonical filter; coherence matrix; coloring transform decoder; entropy; error covariance; filtering; measurement vector; quantization; singular value decomposition; source vector; spectral flatness; transform coding; whitening transform coder; Adaptive filters; Coordinate measuring machines; Decoding; Entropy; Filtering; Gaussian processes; Matrix decomposition; Transform coding; Vectors; Wiener filter;
Journal_Title :
Signal Processing, IEEE Transactions on