Abstract
The signal reconstruction quality has become a critical factor in compressed sensing at present. This paper proposes a matching pursuit algorithm for backtracking regularization based on energy sorting. This algorithm uses energy sorting for secondary atom screening to delete individual wrong atoms through the regularized orthogonal matching pursuit (ROMP) algorithm backtracking. The support set is continuously updated and expanded during each iteration. While the signal energy distribution is not uniform, or the energy distribution is in an extreme state, the reconstructive performance of the ROMP algorithm becomes unstable if the maximum energy is still taken as the selection criterion. The proposed method for the regularized orthogonal matching pursuit algorithm can be adopted to improve those drawbacks in signal reconstruction due to its high reconstruction efficiency. The experimental results show that the algorithm has a proper reconstruction.
Highlights
Magnetic resonance (MR) image reconstruction technology has been long-established in clinical medical detection with the rapid development of medical image processing technology
The orthogonal matching pursuit algorithm (OMP) algorithm continues the selection rule of atoms in the matching pursuit algorithm and realizes the orthogonalization of the selected atom set recursively to ensure the optimization of the iteration, reducing the number of iterations
For the same signal, the number of measurements required to stabilize the reconstructed signal using the ESBRMP algorithm was less than the OMP, regularized orthogonal matching pursuit (ROMP), and subspace tracking algorithm (SP) algorithms
Summary
Magnetic resonance (MR) image reconstruction technology has been long-established in clinical medical detection with the rapid development of medical image processing technology. The method of extracting a sinusoidal signal from the noise has attracted many scientists and using the compressibility of the signal to sample data is a new subject It originates from the study of the acquisition of a finite-rate-of-innovation signal. The convex optimization process has a good reconstruction effect, but it is often disadvantageous to practical applications because it takes an excessively long time to run For this reason, the greedy iterative algorithm [15,16,17,18] has been favored by the vast majority of researchers because of its low complexity and simple geometric principle. The orthogonal matching pursuit algorithm (OMP) [19,20,21], the regularized orthogonal matching pursuit algorithm (ROMP) [22,23], uses each atom and the residual value of the measurement matrix for the inner product. The experimental results show that this algorithm had a better reconstruction effect
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
