Restoring STM images via Sparse Coding: noise and artifact removal
This work addresses image quality issues in STM for researchers in materials science and microscopy, though it is incremental as it modifies existing sparse coding techniques for a specific domain.
The authors tackled the problem of denoising scanning tunneling microscopy (STM) images by developing a sparse coding-based algorithm that handles noise and structured artifacts like dropouts, resulting in improved image quality and outperforming local filtering methods.
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.