A Comparative Study of Open Source Computer Vision Models for Application on Small Data: The Case of CFRP Tape Laying

TL;DR

This study evaluates various open-source computer vision models for CFRP tape laying quality control, demonstrating that effective AI models can be trained with minimal data using transfer learning, even with smaller models.

Contribution

It provides a comparative analysis of open-source models for small data scenarios in industrial AI applications, highlighting the effectiveness of transfer learning.

Findings

Small datasets can suffice for effective model training.

Smaller models do not necessarily compromise performance.

Transfer learning significantly reduces data requirements.

Abstract

In the realm of industrial manufacturing, Artificial Intelligence (AI) is playing an increasing role, from automating existing processes to aiding in the development of new materials and techniques. However, a significant challenge arises in smaller, experimental processes characterized by limited training data availability, questioning the possibility to train AI models in such small data contexts. In this work, we explore the potential of Transfer Learning to address this challenge, specifically investigating the minimum amount of data required to develop a functional AI model. For this purpose, we consider the use case of quality control of Carbon Fiber Reinforced Polymer (CFRP) tape laying in aerospace manufacturing using optical sensors. We investigate the behavior of different open-source computer vision models with a continuous reduction of the training data. Our results show that the amount of data required to successfully train an AI model can be drastically reduced, and the use of smaller models does not necessarily lead to a loss of performance.