Synthetic training data for neural networks in optical scanners used in the foundry industry
Open Access
- 3 September 2026
- journal article
- research article
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37 (6) , 150
Abstract
In industrial applications, AI-based methods are gaining increasing significance in optical systems for tasks such as identification, inspection, and classification. The appeal of these methods lies in their operator-friendly implementation and often superior performance, particularly in complex classification tasks. However, despite the substantial potential of AI-based methods, their application is frequently constrained by the significant resources needed to acquire an appropriate training dataset. For instance, in the sand casting industry, the complexity of optical inspection for cast parts is compounded by considerable variation in local surface topography and global object geometry. This challenge pertains not only to the volume of images required but also to the extensive process of accurate labelling. In this work, we investigate the effectiveness and limitations of synthetic training data for an AI-based optical code reader, designed for the identification and tracking of cast parts. This scanner is capable of detecting and classifying a unique code, called Cast Code, developed specifically for the casting industry, enabling the identification of individual cast part numbers. For synthetic image generation, we utilize physically based rendering, which allows comprehensive control over all rendering parameters. This approach facilitates both a systematic investigation of parameter relevance and an automated labelling process for the training datasets. Our results indicate that detailed geometric modelling of both, the local surface topography and the global object geometry of the pins has a notable positive impact on the neural network’s recognition accuracy, achieving accuracy rates of up to 84 %, on real pin images, using synthetic training datasets, only.Keywords
Funding Information
- Hochschule für angewandte Wissenschaften Kempten
This publication has 18 references indexed in Scilit:
- Synthetic Image Generation Using Deep Learning: A Systematic Literature ReviewComputational Intelligence, 2024
- A novel tracking system for the iron foundry field based on deep convolutional neural networksJournal of Intelligent Manufacturing, 2022
- Anomaly detection for industrial surface inspection: application in maintenance of aircraft componentsProcedia CIRP, 2022
- Synthetic Training Data Generation for Visual Object Identification on Load CarriersProcedia CIRP, 2021
- A comparative study of fine-tuning deep learning models for plant disease identificationComputers and Electronics in Agriculture, 2019
- Deep learning‐based vehicle detection with synthetic image dataIET Intelligent Transport Systems, 2019
- Generating randomly rough surfaces with given height probability distribution and power spectrumTribology International, 2019
- The Reasonable Effectiveness of Synthetic Visual DataInternational Journal of Computer Vision, 2018
- On rendering synthetic images for training an object detectorComputer Vision and Image Understanding, 2015
- Influence of casting surfaces on fatigue strength of ductile cast ironFatigue & Fracture of Engineering Materials & Structures, 2006