Laplacian Prior Variational Automatic Relevance Determination for Transmission Tomography

TL;DR

This paper introduces Lap-VARD, an automatic relevance determination algorithm that optimizes the sparsity penalty in transmission tomography, balancing reconstruction accuracy and sparsity without empirical parameter tuning.

Contribution

The paper presents a novel Laplacian variational automatic relevance determination method for transmission tomography, automating penalty weight selection for improved sparse signal reconstruction.

Findings

Balances sparsity and accuracy effectively

Automates penalty weight selection

Improves reconstruction quality in transmission tomography

Abstract

In the classic sparsity-driven problems, the fundamental L-1 penalty method has been shown to have good performance in reconstructing signals for a wide range of problems. However this performance relies on a good choice of penalty weight which is often found from empirical experiments. We propose an algorithm called the Laplacian variational automatic relevance determination (Lap-VARD) that takes this penalty weight as a parameter of a prior Laplace distribution. Optimization of this parameter using an automatic relevance determination framework results in a balance between the sparsity and accuracy of signal reconstruction. Our algorithm is implemented in a transmission tomography model with sparsity constraint in wavelet domain.