Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition

@article{Pati1993OrthogonalMP,
  title={Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition},
  author={Yagyensh C. Pati and Ramin Rezaiifar and Perinkulam S. Krishnaprasad},
  journal={Proceedings of 27th Asilomar Conference on Signals, Systems and Computers},
  year={1993},
  pages={40-44 vol.1}
}
We describe a recursive algorithm to compute representations of functions with respect to nonorthogonal and possibly overcomplete dictionaries of elementary building blocks e.g. affine (wavelet) frames. We propose a modification to the matching pursuit algorithm of Mallat and Zhang (1992) that maintains full backward orthogonality of the residual (error) at every step and thereby leads to improved convergence. We refer to this modified algorithm as orthogonal matching pursuit (OMP). It is shown… 

Figures from this paper

Deconvolution by Regularized Matching Pursuit

TLDR
An efficient method that restores signals from strongly noised blurred discrete data is presented, which combines ideas from spline theory, wavelet analysis and greedy algorithms.

A low complexity Orthogonal Matching Pursuit for sparse signal approximation with shift-invariant dictionaries

TLDR
A variant of Orthogonal Matching Pursuit, called LoCOMP, is proposed for scalable sparse signal approximation, designed for shift-invariant signal dictionaries with localized atoms, and achieves approximation performance comparable to OMP at a computational cost similar to Matching pursuit.

Blended Matching Pursuit

TLDR
This work presents a blended matching pursuit algorithm, combining coordinate descent-like steps with stronger gradient descent steps, for minimizing a smooth convex function over a linear space spanned by a set of atoms.

A fast orthogonal matching pursuit algorithm

  • M. Gharavi-AlkhansariThomas S. Huang
  • Computer Science
    Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
TLDR
This paper presents a fast algorithm for implementation of orthogonal matching pursuit which for many coding applications has a computational complexity very close to that of the nonorthogonal version.

Optimized orthogonal matching pursuit approach

TLDR
An adaptive procedure for signal representation is proposed, which improves upon the earlier proposed matching pursuit and orthogonal matching pursuit approaches.

Path Orthogonal Matching Pursuit for k-Sparse Image Reconstruction

TLDR
The path-augmentation step to the standard orthogonal matching pursuit algorithm is introduced, and it is shown that the method achieves lower reconstruction error for fixed sparsity levels than either orthogonic matching pursuit or generalized orthogona matching pursuit.

Flexible tree-search based orthogonal matching pursuit algorithm

TLDR
The flexible tree-search based orthogonal matching pursuit (FTB-OMP) algorithm provides design parameters that give flexibility to establish a tradeoff between approximation performance and experimental time complexity.

A complementary matching pursuit algorithm for sparse approximation

TLDR
A deeper analysis of the algorithm shows that the residual error at any iteration may not be orthogonal to the immediately selected atom, however, this brings about the possibility of increasing the convergence speed and improving the sparsity of the solution vector.

Adaptive multiresolution image coding with matching and basis pursuits

TLDR
Matching pursuit and basis pursuit with finite dictionaries of convolutional splines are used for adaptive multiresolution image compression and outperform the DCT based JPEG both in terms of PSNR and subjective image quality at lower bit rates.

Multi-scale kernel basis and iterative orthogonal matching pursuit for sparse approximation

TLDR
Experiments and comparisons demonstrate that the proposed multi-scale kernel basis and iterative orthogonal matching pursuit algorithm (IOMP) are good at fast computing sparse approximation.
...

References

SHOWING 1-6 OF 6 REFERENCES

Matching pursuits with time-frequency dictionaries

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

What is projection pursuit

1. Huber. Projection pursuit. The Annals of Statistics

  • 1. Huber. Projection pursuit. The Annals of Statistics
  • 1985

Discussion following article by P

  • The Annals of Statistics,
  • 1985

Projection pursuit. The Annals of Statistics

  • Projection pursuit. The Annals of Statistics
  • 1985