Analysis of Alternative Performance Metrics for Compressive Spectral Imaging

Compressive spectral imaging is a technique that reconstructs the three-dimensional (3D) spectral data cube from limited number of two-dimensional (2D) measurements. In order to obtain this data cube, the technique makes use of the theory of compressed sensing, and employs both an optical and a computational system. However, this optical system can be designed with multiple variations. To evaluate the performance of different designs, there is a need for metrics that are reliable and fast to compute. Current metrics, that are used for this purpose, measure the imaging performance depending on the tested images, and also require long computation time. In this paper, a compressive spectral imaging system and its different variants are examined with the goal of finding an alternative metric. This system is contains a coded aperture and a photon sieve which is a type of diffractive lens. In order to analyze the performance of the system, two metrics that are based on condition number and a third one that is based on mutual coherence are used, and their results are comparatively examined. The results suggests that two of these metrics can be used to analyze the performance of the tested systems.