Performance improvement of the decoding side of the BCS-SPL technique

Abstract

This paper proposes different approaches to reduce the blurring effect of the reconstructed images and the computational complexity at the decoding side of the block compressive sensing with smooth projected landweber (BCS-SPL). It was found that the reason of the lack of reconstruction quality and computational complexity are due to the use of wiener filter and thresholding method. Therefore, each proposed approach uses a different thresholding method to improve the reconstruction quality and reduce computational complexity. Many simulation experiments have been conducted to evaluate the proposed approaches and compare them to several other conventional compressive sensing techniques. Our simulation results show that the proposed approaches improves the reconstruction quality by up to 5 dB relative to the other conventional techniques and also reduce the computational complexity time.