English

Deep Learning Sparse Ternary Projections for Compressed Sensing of Images

Computer Vision and Pattern Recognition 2017-08-29 v1 Machine Learning Machine Learning

Abstract

Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly learns a pair of a projection matrix and a reconstruction operator in an end-to-end fashion. The experimental results on real images demonstrate the effectiveness of the proposed approach compared to state-of-the-art methods, with significant advantage in terms of complexity.

Keywords

Cite

@article{arxiv.1708.08311,
  title  = {Deep Learning Sparse Ternary Projections for Compressed Sensing of Images},
  author = {Duc Minh Nguyen and Evaggelia Tsiligianni and Nikos Deligiannis},
  journal= {arXiv preprint arXiv:1708.08311},
  year   = {2017}
}

Comments

To appear in GlobalSIP 2017