Spectral amplitude estimation-based X-ray image restoration: An extension of a speech enhancement approach

This paper describes a class of spectral amplitude estimation-based algorithms for the restoration of low dose X-ray images. Since estimation of spectral amplitude from noisy observations is a widely reported approach to restore noisy speech signals, we discuss our algorithms from the viewpoint of extending a well established speech processing technique to images. We include an analysis of residual noise. Moreover, we provide qualitative and quantitative processing results.