Abstract | ||
---|---|---|
In this paper we model the components of the compressive sensing (CS) problem using the Bayesian framework by utilizing a hierarchical form of the Laplace prior to model sparsity of the unknown signal. This signal prior includes some of the existing models as special cases and achieves a high degree of sparsity. We develop a constructive (greedy) algorithm resulting from this formulation where necessary parameters are estimated solely from the observation and therefore no user-intervention is needed. We provide experimental results with synthetic 1D signals and images, and compare with the state-of-the-art CS reconstruction algorithms demonstrating the superior performance of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICASSP.2009.4960223 | ICASSP |
Keywords | Field | DocType |
high degree,necessary parameter,model sparsity,in- verse problems,existing model,sparse bayesian learning,unknown signal,bayesian compressive,laplace prior,compressive sensing,bayesian framework,relevance vector machine rvm.,state-of-the-art cs reconstruction,hierarchical form,index terms— bayesian methods,computer science,computational modeling,greedy algorithms,data mining,gaussian noise,inverse problems,greedy algorithm,machine learning,relevance vector machine,indexing terms,compressed sensing,bayesian method,bayesian methods,parameter estimation,noise,image reconstruction,sensors,signal reconstruction | Iterative reconstruction,Mathematical optimization,Pattern recognition,Laplace transform,Computer science,Greedy algorithm,Artificial intelligence,Inverse problem,Prior probability,Signal reconstruction,Compressed sensing,Bayesian probability | Conference |
ISSN | Citations | PageRank |
1520-6149 | 31 | 1.63 |
References | Authors | |
17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
S. Derin Babacan | 1 | 534 | 26.60 |
Rafael Molina | 2 | 1439 | 103.16 |
Aggelos K. Katsaggelos | 3 | 3410 | 340.41 |