Wavelet vector quantization with matching pursuit

Author

Davis, G. ; Mallat, S.

Author_Institution

Courant Inst. of Math. Sci., New York, NY, USA

fYear

1994

fDate

27-29 Oct 1994

Firstpage

55

Abstract

To compute the optimal expansion of signals in redundant dictionary of waveforms is an NP complete problem. We introduce a greedy-algorithm, called matching pursuit, that performs a sub-optimal expansion. This algorithm can be interpreted as a shape-gain multistage vector quantization. The waveforms are chosen iteratively in order to best match the signal structures. Matching pursuits are general procedures used to compute adaptive signal representations. Applications to speech and image processing with dictionaries of Gabor functions are shown, in particular for the noise removal

Keywords

adaptive signal processing; image processing; signal representation; speech processing; vector quantisation; wavelet transforms; Gabor functions; NP complete problem; adaptive signal representations; greedy-algorithm; image processing; iterative method; matching pursuit; noise removal; optimal signal expansion; redundant dictionary; shape-gain multistage vector quantization; signal structures; speech processing; sub-optimal signal expansion; waveforms; wavelet vector quantization; Dictionaries; Image processing; Matching pursuit algorithms; Noise shaping; Speech processing; Time frequency analysis; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on

Conference_Location

Alexandria, VA

Print_ISBN

0-7803-2761-6

Type

conf

DOI

10.1109/WITS.1994.513886

Filename

513886