Artifact Removal and Image Restoration in AFM:A Structured Mask-Guided Directional Inpainting Approach
🤖 AI Summary
This work proposes a lightweight, fully automated framework for artifact correction in atomic force microscopy (AFM) images, which are commonly degraded by noise, scanning artifacts, and tip–sample interactions that compromise nanoscale structural analysis. The method first employs a compact classification network to detect the presence of artifacts, followed by a tailored semantic segmentation network to generate structure-aware masks. Geometrically consistent inpainting is then achieved through structure-guided adaptive mask expansion and directional neighborhood interpolation, complemented by localized Gaussian smoothing to ensure seamless restoration. The approach effectively removes artifacts while preserving three-dimensional surface continuity and nanoscale details, supports real-time parameter tuning and batch processing, and significantly enhances the fidelity of AFM data interpretation.
Application Category
📝 Abstract
Atomic Force Microscopy (AFM) enables high-resolution surface imaging at the nanoscale, yet the output is often degraded by artifacts introduced by environmental noise, scanning imperfections, and tip-sample interactions. To address this challenge, a lightweight and fully automated framework for artifact detection and restoration in AFM image analysis is presented. The pipeline begins with a classification model that determines whether an AFM image contains artifacts. If necessary, a lightweight semantic segmentation network, custom-designed and trained on AFM data, is applied to generate precise artifact masks. These masks are adaptively expanded based on their structural orientation and then inpainted using a directional neighbor-based interpolation strategy to preserve 3D surface continuity. A localized Gaussian smoothing operation is then applied for seamless restoration. The system is integrated into a user-friendly GUI that supports real-time parameter adjustments and batch processing. Experimental results demonstrate the effective artifact removal while preserving nanoscale structural details, providing a robust, geometry-aware solution for high-fidelity AFM data interpretation.
Problem
Research questions and friction points this paper is trying to address.
Artifact Removal
Image Restoration
Atomic Force Microscopy
AFM Imaging
Nanoscale Imaging
Innovation
Methods, ideas, or system contributions that make the work stand out.
directional inpainting
artifact removal
semantic segmentation
AFM image restoration
structure-aware interpolation
🔎 Similar Papers
No similar papers found.
