Data-driven and Automatic Surface Texture Analysis Using Persistent Homology

TL;DR

This paper introduces a fully automated, topological data analysis method using persistent homology to classify surface roughness with high accuracy, reducing reliance on user input and standard tools.

Contribution

It presents a novel TDA-based approach for surface roughness classification that is fully automatic and outperforms traditional FFT and Gaussian filtering methods.

Findings

Achieves up to 97% classification accuracy.

Provides an automated and adaptive feature extraction process.

Outperforms traditional methods like FFT and Gaussian filtering.

Abstract

Surface roughness plays an important role in analyzing engineering surfaces. It quantifies the surface topography and can be used to determine whether the resulting surface finish is acceptable or not. Nevertheless, while several existing tools and standards are available for computing surface roughness, these methods rely heavily on user input thus slowing down the analysis and increasing manufacturing costs. Therefore, fast and automatic determination of the roughness level is essential to avoid costs resulting from surfaces with unacceptable finish, and user-intensive analysis. In this study, we propose a Topological Data Analysis (TDA) based approach to classify the roughness level of synthetic surfaces using both their areal images and profiles. We utilize persistent homology from TDA to generate persistence diagrams that encapsulate information on the shape of the surface. We then obtain feature matrices for each surface or profile using Carlsson coordinates, persistence images, and template functions. We compare our results to two widely used methods in the literature: Fast Fourier Transform (FFT) and Gaussian filtering. The results show that our approach yields mean accuracies as high as 97%. We also show that, in contrast to existing surface analysis tools, our TDA-based approach is fully automatable and provides adaptive feature extraction.