Improving Supervised Machine Learning Performance in Optical Quality Control via Generative AI for Dataset Expansion

TL;DR

This paper explores using generative AI models like Stable Diffusion and CycleGAN to expand limited datasets for supervised machine learning in optical quality control, significantly improving defect segmentation performance.

Contribution

It introduces the application of generative AI for dataset expansion in optical quality control, demonstrating notable performance improvements over traditional methods.

Findings

Stable Diffusion-based dataset expansion improves segmentation by 4.6%.

Achieved a Mean IoU of 84.6% with generated data.

Generative AI outperforms traditional augmentation techniques.

Abstract

Supervised machine learning algorithms play a crucial role in optical quality control within industrial production. These approaches require representative datasets for effective model training. However, while non-defective components are frequent, defective parts are rare in production, resulting in highly imbalanced datasets that adversely impact model performance. Existing strategies to address this challenge, such as specialized loss functions or traditional data augmentation techniques, have limitations, including the need for careful hyperparameter tuning or the alteration of only simple image features. Therefore, this work explores the potential of generative artificial intelligence (GenAI) as an alternative method for expanding limited datasets and enhancing supervised machine learning performance. Specifically, we investigate Stable Diffusion and CycleGAN as image generation models, focusing on the segmentation of combine harvester components in thermal images for subsequent defect detection. Our results demonstrate that dataset expansion using Stable Diffusion yields the most significant improvement, enhancing segmentation performance by 4.6 %, resulting in a Mean Intersection over Union (Mean IoU) of 84.6 %.