Evaluating Synthetic Images as Effective Substitutes for Experimental Data in Surface Roughness Classification

TL;DR

This paper demonstrates that synthetic images generated with Stable Diffusion XL can effectively augment real data for surface roughness classification, maintaining high accuracy while reducing the need for costly experimental data.

Contribution

It introduces the use of generative AI to supplement experimental datasets, improving data efficiency and model robustness in materials surface classification tasks.

Findings

Synthetic images achieve comparable classification accuracy to real images.

Augmentation with generative images enhances data efficiency and model robustness.

Optimal hyperparameter configurations preserve performance with less data.

Abstract

Hard coatings play a critical role in industry, with ceramic materials offering outstanding hardness and thermal stability for applications that demand superior mechanical performance. However, deploying artificial intelligence (AI) for surface roughness classification is often constrained by the need for large labeled datasets and costly high-resolution imaging equipment. In this study, we explore the use of synthetic images, generated with Stable Diffusion XL, as an efficient alternative or supplement to experimentally acquired data for classifying ceramic surface roughness. We show that augmenting authentic datasets with generative images yields test accuracies comparable to those obtained using exclusively experimental images, demonstrating that synthetic images effectively reproduce the structural features necessary for classification. We further assess method robustness by systematically varying key training hyperparameters (epoch count, batch size, and learning rate), and identify configurations that preserve performance while reducing data requirements. Our results indicate that generative AI can substantially improve data efficiency and reliability in materials-image classification workflows, offering a practical route to lower experimental cost, accelerate model development, and expand AI applicability in materials engineering.