IEICE TRANSACTIONS on Fundamentals
High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —
Summary :
We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1-norm minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor components of the target signal are estimated. The minor components are further estimated using the estimated measurements exploiting a maximum a posterior (MAP) estimation, which leads to a ridge regression with the regularization parameter determined using the error bound for the estimated measurements. After a slight modification to the major components, the final estimate is obtained by combining the two estimates. Computational cost of the proposed algorithm is mostly the same as the l1-nom minimization. Simulation results for one-dimensional computer generated signals show that the proposed algorithm gives 11.8% better results on average than the l1-norm minimization and the lasso estimator. Simulations using standard images also show that the proposed algorithm outperforms those conventional methods.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E98-A No.9 pp.1880-1887
- Publication Date
- 2015/09/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E98.A.1880
- Type of Manuscript
- Special Section PAPER (Special Section on Signal Processing for Sensing and Diagnosis)
- Category
Authors
Akira HIRABAYASHI
Ritsumeikan University
Norihito INAMURO
Ritsumeikan University
Aiko NISHIYAMA
Ritsumeikan University
Kazushi MIMURA
Hiroshima City University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Akira HIRABAYASHI, Norihito INAMURO, Aiko NISHIYAMA, Kazushi MIMURA, "High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —" in IEICE TRANSACTIONS on Fundamentals,
vol. E98-A, no. 9, pp. 1880-1887, September 2015, doi: 10.1587/transfun.E98.A.1880.
Abstract: We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1-norm minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor components of the target signal are estimated. The minor components are further estimated using the estimated measurements exploiting a maximum a posterior (MAP) estimation, which leads to a ridge regression with the regularization parameter determined using the error bound for the estimated measurements. After a slight modification to the major components, the final estimate is obtained by combining the two estimates. Computational cost of the proposed algorithm is mostly the same as the l1-nom minimization. Simulation results for one-dimensional computer generated signals show that the proposed algorithm gives 11.8% better results on average than the l1-norm minimization and the lasso estimator. Simulations using standard images also show that the proposed algorithm outperforms those conventional methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E98.A.1880/_p
Copy
@ARTICLE{e98-a_9_1880,
author={Akira HIRABAYASHI, Norihito INAMURO, Aiko NISHIYAMA, Kazushi MIMURA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —},
year={2015},
volume={E98-A},
number={9},
pages={1880-1887},
abstract={We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1-norm minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor components of the target signal are estimated. The minor components are further estimated using the estimated measurements exploiting a maximum a posterior (MAP) estimation, which leads to a ridge regression with the regularization parameter determined using the error bound for the estimated measurements. After a slight modification to the major components, the final estimate is obtained by combining the two estimates. Computational cost of the proposed algorithm is mostly the same as the l1-nom minimization. Simulation results for one-dimensional computer generated signals show that the proposed algorithm gives 11.8% better results on average than the l1-norm minimization and the lasso estimator. Simulations using standard images also show that the proposed algorithm outperforms those conventional methods.},
keywords={},
doi={10.1587/transfun.E98.A.1880},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - High-Quality Recovery of Non-Sparse Signals from Compressed Sensing — Beyond l1 Norm Minimization —
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1880
EP - 1887
AU - Akira HIRABAYASHI
AU - Norihito INAMURO
AU - Aiko NISHIYAMA
AU - Kazushi MIMURA
PY - 2015
DO - 10.1587/transfun.E98.A.1880
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E98-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2015
AB - We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1-norm minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor components of the target signal are estimated. The minor components are further estimated using the estimated measurements exploiting a maximum a posterior (MAP) estimation, which leads to a ridge regression with the regularization parameter determined using the error bound for the estimated measurements. After a slight modification to the major components, the final estimate is obtained by combining the two estimates. Computational cost of the proposed algorithm is mostly the same as the l1-nom minimization. Simulation results for one-dimensional computer generated signals show that the proposed algorithm gives 11.8% better results on average than the l1-norm minimization and the lasso estimator. Simulations using standard images also show that the proposed algorithm outperforms those conventional methods.
ER -
English
