An evaluation of image denoising techniques applied to CT baggage screening imagery
André Mouton, Greg T. Flitton, Suzanne Bizot, Najla Megherbi, Toby P. Breckon · 2013
This paper investigates the efficacy of several popular denoising methods in the previously unconsidered context of Computed Tomography (CT) baggage imagery. The performance of a dedicated CT baggage denoising approach (alpha-weighted mean separation and histogram equalisation) is compared to the following popular denoising techniques: anisotropic diffusion; total variation denoising; bilateral filtering; translation invariant wavelet shrinkage and non-local means filtering. In addition to a standard qualitative performance analysis (visual comparisons), denoising performance is evaluated with a recently developed 3D SIFT-based analysis technique that quantifies the impact of denoising on the implementation of automated 3D object recognition. The study yields encouraging results in both the qualitative and quantitative analyses, with wavelet thresholding producing the most satisfactory results. The results serve as a strong indication that simple denoising will aid human and computerised analyses of 3D CT baggage imagery for transport security screening.