Matching pursuits with time-frequency dictionaries

  title={Matching pursuits with time-frequency dictionaries},
  author={St{\'e}phane Mallat and Zhifeng Zhang},
  journal={IEEE Trans. Signal Process.},
The authors introduce an algorithm, called matching pursuit, that decomposes any signal into a linear expansion of waveforms that are selected from a redundant dictionary of functions. These waveforms are chosen in order to best match the signal structures. Matching pursuits are general procedures to compute adaptive signal representations. With a dictionary of Gabor functions a matching pursuit defines an adaptive time-frequency transform. They derive a signal energy distribution in the time… 

Figures from this paper

Adaptive Time-Frequency Decompositions with Matching

An algorithm is derived that isolates the coherent structures of a signal and describes an application to pattern extraction from noisy signals, and the dictionary waveforms which best match a signal's structures are chosen iteratively.

Adaptive time-frequency transform

  • S. MallatZhifeng Zhang
  • Engineering
    1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
It is shown that time-frequency dictionaries yield adaptive decompositions where signal structures are represented by Gabor functions that match their time- frequencies signature.


A new version of matching pursuit algorithm, that decomposes any signal into a linear expansion of the functions selected from the redundant set called dictionary, that allows one to correctly and uniformly represent also the signals with linear chirps included in their structure.

Probabilistic matching pursuit with Gabor dictionaries

Fast Matching Pursuit with Multi-Gabor Dictionaries

This work presents an acceleration technique and an implementation of the matching pursuit algorithm acting on a multi-Gabor dictionary, i.e., a concatenation of several Gabor-type time-frequency dictionaries, each of which consists of translations and modulations of a possibly different window and time and frequency shift parameters.

Signal enhancement with matching pursuit

  • Gang XuJing Meng
  • Computer Science
    IEEE 60th Vehicular Technology Conference, 2004. VTC2004-Fall. 2004
  • 2004
It is proved by experiments that the matching pursuit method can efficiently enhance a signal corrupted by noise without prior information about the noise and the signal.

Wavelet vector quantization with matching pursuit

  • G. DavisS. Mallat
  • Computer Science
    Proceedings of 1994 Workshop on Information Theory and Statistics
  • 1994
A greedy-algorithm, called matching pursuit, that performs a sub-optimal expansion of signals in redundant dictionary of waveforms is introduced, which can be interpreted as a shape-gain multistage vector quantization.

Matching Pursuits may yield superior results to Orthogonal Matching Pursuits when secondary information is estimated from the signal model

  • Guifeng LiuV. DeBrunner
  • Mathematics
    2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers
  • 2010
In this paper, we compare the Orthogonal Matching Pursuits and the Matching Pursuits algorithm as used with the same dictionary in a stationary spectral estimation problem. Specifically, we develop

Ultrasonic Signal Decomposition via Matching Pursuit with an Adaptive and Interpolated Dictionary

A modified implementation of the matching pursuit algorithm is described, where the algorithm is specifically designed for an efficient decomposition of ultrasonic signals.



Entropy-based algorithms for best basis selection

Adapted waveform analysis uses a library of orthonormal bases and an efficiency functional to match a basis to a given signal or family of signals, and relies heavily on the remarkable orthogonality properties of the new libraries.

Wavelets: A Tutorial in Theory and Applications

Orthogonal wavelets daubechies' scaling function on (0.3), D. Pollen wavelet matrices and the representation of discrete functions, P.N. Heller, et al wavelets and generalized functions, G.G. Walter

The wavelet transform, time-frequency localization and signal analysis

Two different procedures for effecting a frequency analysis of a time-dependent signal locally in time are studied and the notion of time-frequency localization is made precise, within this framework, by two localization theorems.

Product code vector quantizers for waveform and voice coding

Several algorithms are presented for the design of shape-gain vector quantizers based on a traning sequence of data or a probabilistic model, and their performance is compared to that of previously reported vector quantization systems.

Wavelets and signal processing

A simple, nonrigorous, synthetic view of wavelet theory is presented for both review and tutorial purposes. The discussion includes nonstationary signal analysis, scale versus frequency, wavelet

Time-frequency distributions-a review

A review and tutorial of the fundamental ideas and methods of joint time-frequency distributions is presented with emphasis on the diversity of concepts and motivations that have gone into the formation of the field.

Vector quantization

  • R. Gray
  • Computer Science
    IEEE ASSP Magazine
  • 1984
During the past few years several design algorithms have been developed for a variety of vector quantizers and the performance of these codes has been studied for speech waveforms, speech linear predictive parameter vectors, images, and several simulated random processes.

On a conjecture of Huber concerning the convergence of projection pursuit regression

with am a minimizing direction [or as is demonstrated easily a maximizing direction for E(gm)2]. Huber establishes weak L2(P) convergence of the procedure [rm -O 0 weakly in L2(P)]. Also in the

Ten Lectures on Wavelets

This paper presents a meta-analyses of the wavelet transforms of Coxeter’s inequality and its applications to multiresolutional analysis and orthonormal bases.