Overview of Match Pursuit Algorithms and Application Comparison in Image Reconstruction

This paper investigates the performance of different reconstruction algorithms in applications. We compare the following algorithms: matching pursuit (MP), orthogonal matching pursuit (OMP), regularized orthogonal matching pursuit (ROMP), stagewise OMP (StOMP), the compressed sensing matching pursuit (CoSaMP) and subspace pursuit (SP). The comparison is performed via numerical simulations for different sampling conditions, according to the simulations subspace pursuit performance is slightly better than the others for signals with no noise. Comparison also performed on 2D image reconstruction, the subspace pursuit algorithm performs slightly better when the compression ratio is low.