X-ray image separation via coupled dictionary learning

TL;DR

This paper introduces a novel source separation technique for X-ray images of double-sided paintings, leveraging coupled dictionary learning and visual images from both sides to improve separation accuracy.

Contribution

The paper presents a new multi-scale dictionary learning approach that couples visual images from both sides of a panel, enhancing source separation in X-ray scans.

Findings

Successfully separates sources where previous methods fail

Outperforms state-of-the-art separation techniques

Demonstrates effectiveness in art investigation applications

Abstract

In support of art investigation, we propose a new source sepa- ration method that unmixes a single X-ray scan acquired from double-sided paintings. Unlike prior source separation meth- ods, which are based on statistical or structural incoherence of the sources, we use visual images taken from the front- and back-side of the panel to drive the separation process. The coupling of the two imaging modalities is achieved via a new multi-scale dictionary learning method. Experimental results demonstrate that our method succeeds in the discrimination of the sources, while state-of-the-art methods fail to do so.