Joint Gaussian dictionary learning and tomographic reconstruction

This paper studies ill-posed tomographic imaging problems where the image is sparsely represented by a non-negative linear combination of Gaussians. Our main contribution is to develop a scheme for directly recovering the Gaussian mixture representation of an image from tomographic data, which here is modeled as noisy samples of the parallel-beam ray transform. An important aspect of this non-convex reconstruction problem is the choice of initial guess. We propose an initialization procedure that is based on a filtered back projection type of operator tailored for the Gaussian dictionary. This operator can be evaluated efficiently using an approximation of the Riesz-potential of an anisotropic Gaussian which is based on an exact closed form expression for the Riesz-potential of an isotropic Gaussian. The proposed method is evaluated on simulated data.

Automated summary

This paper proposes a method for recovering images from ill-posed tomographic imaging problems using a Gaussian mixture representation. The study focuses on the choice of initial guess and proposes an initialization procedure based on a filtered back projection operator tailored for the Gaussian dictionary. The proposed method is evaluated using simulated data.