TechRxiv
DL-CSNet-20220317.pdf (733.52 kB)
Download file

DL-CSNet: Dictionary Learning based Compressed Sensing Neural Network

Download (733.52 kB)
preprint
posted on 22.03.2022, 01:50 authored by Yanzhen Qiu, Chuangfeng Zhang, Ruishan Huang, Haochen Tian, Chenkui Xiong, Shaolin Liao
In this paper, we propose a novel neural network for Compressed Sensing (CS) application: the Dictionary Learning based Compressed Sensing neural Network (DL-CSNet). It is fairly simple but highly effective, which consists of only three layers: 1) a DL layer for latent sparse features extraction; 2) a smoothing layer via Total Variation (TV) like constraint; and 3) a CS acquisition layer for neural network training. In particular, the TV-like smoothing layer is a perfect complement to the sparsity-oriented DL layer to achieve smooth images. The trained DL-CSNet can learn the optimal dictionary matrix so that images can be reconstructed in high quality. At last, extensive experiments have been carried out on binary images and compared to most classical CS algorithms, which shows the superior performance of the proposed DL-CSNet.

History

Email Address of Submitting Author

liaoshlin@mail.sysu.edu.cn

ORCID of Submitting Author

0000-0002-4432-3448

Submitting Author's Institution

Sun Yat-sen University, No. 135, Xingang Xi Road, Guangzhou, 510275, P. R. China

Submitting Author's Country

China

Usage metrics

Read the peer-reviewed publication

in Journal of Physics: Conference Series

Licence

Exports