Restoring STM images via Sparse Coding: noise and artifact removal

TL;DR

This paper introduces a sparse coding-based denoising algorithm tailored for STM images, effectively removing noise and structured artifacts like dropouts, thereby enhancing image clarity and interpretability.

Contribution

The paper presents a novel sparse regression approach for STM image denoising that explicitly handles structured artifacts as missing data, outperforming local filtering methods.

Findings

Outperforms local filtering in artifact removal

Effectively handles structured dropouts as missing data

Improves STM image quality and interpretability

Abstract

In this article, we present a denoising algorithm to improve the interpretation and quality of scanning tunneling microscopy (STM) images. Given the high level of self-similarity of STM images, we propose a denoising algorithm by reformulating the true estimation problem as a sparse regression, often termed sparse coding. We introduce modifications to the algorithm to cope with the existence of artifacts, mainly dropouts, which appear in a structured way as consecutive line segments on the scanning direction. The resulting algorithm treats the artifacts as missing data, and the estimated values outperform those algorithms that substitute the outliers by a local filtering. We provide code implementations for both Matlab and Gwyddion.