Optimal combining fusion on degraded compressed sensing image reconstruction

Abstract

Compressed Sensing (CS) or Compressive Sampling is an integral component in the reconstruction of image from sub-sample (incomplete) measurements. In many practical situations, multiple channel sensing, followed by suitable fusion strategy, reconstruct images with high spatial and spectral information. This paper proposes an efficient combining scheme on CS measurements to reconstruct an image from highly incomplete multi-channel degraded and noisy observations (measurements). A linear regression scheme has been used here to estimate the weights for different channels/sensors. The estimated weights are then used to form a set of composite measurements through a weighted averaging technique. The optimal weighted measurements are then used in an l1-minimization framework to reconstruct the image. A set of extensive simulation results show appreciable reduction in artifacts and visual improvement with enhanced contrast. Simulation results also demonstrate that the proposed method outperforms some popular image fusion methods in both subjective and objective qualities for image reconstruction, irrespective of the degree of degradation in multi-channel input CS measurements.