Robust optimisation algorithm for the measurement matrix in compressed sensing

CAAI Transactions on Intelligence Technology

article

Ying Zhou¹  Quansen Sun¹  Jixin Liu² 

[1] School of Computer Science and Engineering, Nanjing University of Science and Technology;Research Center of Wideband Wireless Communication Technology, Nanjing University of Posts and Telecommunications

关键词: compressed sensing;    optimisation;    image reconstruction;    Hadamard matrices;    Hadamard-diagonal matrix;    measurement matrix;    effective optimisation strategy;    mutual coherence;    HDM;    construction efficiency;    sensing efficiency;    sparse domain;    energy concentration characteristic;    compressed sensing;    robust optimisation algorithm;    popular measurement matrices;    (B0260) Optimisation techniques;    (B0290H) Linear algebra (numerical analysis);    (B6135) Optical;    image and video signal processing;    (C1180) Optimisation techniques;    (C4140) Linear algebra (numerical analysis);    (C5260B) Computer vision and image processing techniques;   

DOI  :  10.1049/trit.2018.1011

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

The measurement matrix which plays an important role in compressed sensing has got a lot of attention. However, the existing measurement matrices ignore the energy concentration characteristic of the natural images in the sparse domain, which can help to improve the sensing efficiency and the construction efficiency. Here, the authors propose a simple but efficient measurement matrix based on the Hadamard matrix, named Hadamard-diagonal matrix (HDM). In HDM, the energy conservation in the sparse domain is maximised. In addition, considering the reconstruction performance can be further improved by decreasing the mutual coherence of the measurement matrix, an effective optimisation strategy is adopted in order to reducing the mutual coherence for better reconstruction quality. The authors conduct several experiments to evaluate the performance of HDM and the effectiveness of optimisation algorithm. The experimental results show that HDM performs better than other popular measurement matrices, and the optimisation algorithm can improve the performance of not only the HDM but also the other popular measurement matrices.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND