Abstract：In this paper, a threshold-based Sparsity Adaptive Matching Pursuit (T-SAMP) algorithm was proposed to solve the problem that the Sparsity Adaptive Matching Pursuit algorithm had high complexity on image reconstruction. Considering the Backtracking-Based Adaptive Orthogonal Matching Pursuit in the atomic selection stage, the thresholds were used to verify the selected reliable atoms and removed the unreliable atoms, and the reliable atomic were verified as preprocessing steps of the SAMP algorithm to find the maximum approximation coefficient of the signal, to improve the accuracy of reconfiguration and to reduce the complexity of the algorithm. The simulation result shows that compared with SAMP algorithm, the proposed T-SAMP algorithm can average improve 3dB Peak Signal to Noise Ratio, the average running time of the algorithm is reduced by about 60%.
2018, Vol. 39 
