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

2026-01-30

AI Summary

This study addresses the challenge of severe data imbalance in industrial optical quality inspection, where scarce defect samples significantly hinder the performance of supervised learning models. To overcome the limitations of conventional data augmentation techniques, the authors propose leveraging generative artificial intelligence to synthesize realistic defect samples. The work presents the first systematic evaluation of Stable Diffusion and CycleGAN for generating defects in industrial thermal imaging. High-quality synthetic defect images are integrated into the training pipeline of a semantic segmentation model, with validation conducted on a thermal image dataset of combine harvester components. Experimental results demonstrate that augmenting the dataset with Stable Diffusion–generated images improves segmentation performance by 4.6%, achieving a Mean IoU of 84.6%.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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 %.

Problem

• supervised machine learning
• optical quality control
• imbalanced dataset
• defect detection
• dataset expansion

Innovation

• Generative AI
• Dataset Expansion
• Stable Diffusion
• Optical Quality Control
• Imbalanced Data