Joint Sensing Matrix and Sparsifying Dictionary Optimization for Tensor Compressive Sensing
arXiv:1601.07804 · doi:10.1109/TSP.2017.2699639
Abstract
Tensor Compressive Sensing (TCS) is a multidimensional framework of Compressive Sensing (CS), and it is advantageous in terms of reducing the amount of storage, easing hardware implementations and preserving multidimensional structures of signals in comparison to a conventional CS system. In a TCS system, instead of using a random sensing matrix and a predefined dictionary, the average-case performance can be further improved by employing an optimized multidimensional sensing matrix and a learned multilinear sparsifying dictionary. In this paper, we propose a joint optimization approach of the sensing matrix and dictionary for a TCS system. For the sensing matrix design in TCS, an extended separable approach with a closed form solution and a novel iterative non-separable method are proposed when the multilinear dictionary is fixed. In addition, a multidimensional dictionary learning method that takes advantages of the multidimensional structure is derived, and the influence of sensing matrices is taken into account in the learning process. A joint optimization is achieved via alternately iterating the optimization of the sensing matrix and dictionary. Numerical experiments using both synthetic data and real images demonstrate the superiority of the proposed approaches.
References in corpus (8)
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- High-Resolution Radar via Compressed Sensing
- Near-ideal model selection by minimization
- Simultaneous Codeword Optimization (SimCO) for Dictionary Update and Learning
- Projection Design For Statistical Compressive Sensing: A Tight Frame Based Approach
- Compressive Sensing of Sparse Tensors
- Optimized projections for compressed sensing via rank-constrained nearest correlation matrix
- Compressed Sensing of Simultaneous Low-Rank and Joint-Sparse Matrices
Cited by in corpus (5)
- Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
- Sampling and Inference of Networked Dynamics using Log-Koopman Nonlinear Graph Fourier Transform
- Online Multilinear Dictionary Learning
- Optimal Sampling for Dynamic Complex Networks with Graph-Bandlimited Initialization
- Compressed Sensing with Probability-based Prior Information