Progressive sparse image sensing using Iterative Methods

Progressive image transmission enables the receivers to reconstruct a transmitted image at various bit rates. Most of the works in this field are based on the conventional Shannon-Nyquist sampling theory. In the present work, progressive image transmission is investigated using sparse recovery of random samples. The sparse recovery methods such as Iterative Method with Adaptive Thresholding (IMAT) and Iterative IKMAX Thresholding (IKMAX) are exploited in this framework since they have the ability for successive reconstruction. The simulation results indicate that the proposed method performs well in progressive recovery. The IKMAX has better final reconstruction than IMAT at the cost of requiring sparse signal with extra information about the sparsity number. However, the IMAT has the ability to recover the compressible signals. Furthermore, two sampling strategies, random sampling and uniform sampling are exploited. The simulations show that IMAT is a better choice for random sampling and IKMAX behaves better than IMAT in the case of uniform sampling.