Capabilities and limits of synthetic images used for neural networks in optical scanners for the iron sand-cast industry

Jonathan Zender; Alexander Murawa; Bernd Pinzer; Michael Layh

doi:10.1117/12.3016889

17 June 2024 Capabilities and limits of synthetic images used for neural networks in optical scanners for the iron sand-cast industry

Jonathan Zender, Alexander Murawa, Bernd Pinzer, Michael Layh

Author Affiliations +

Proceedings Volume 13024, Optical Instrument Science, Technology, and Applications III; 130240B (2024) https://doi.org/10.1117/12.3016889
Event: SPIE Optical Systems Design, 2024, Strasbourg, France

Abstract

In an industrial context, AI-based methods are becoming increasingly important in the optical systems used for identification, inspection and classification. The reasons for this are that AI-based image processing algorithms are easy to use on the operator side and often achieve superior results. E.g. in complex classification tasks. In the sand cast industry, the complexity in optical inspection of cast parts is connected with strong variations in the local surface topography and in the global object geometry change. Despite the great potential of AI-based methods, application is often hindered by the immense effort involved in acquiring a suitable training dataset. This refers not only to the acquisition of the required number of images but also to the tedious labelling. In this work, we investigate the capabilities and limits of synthetic training data on an AI-based optical scanner used to identify and track cast parts. The optical scanner is capable of detecting and classifying a codification specifically designed for the casting industry. By reading the code, the scanner can deduce the specific number of the cast part. For synthetic image generation, we use physically based rendering, which has advantage of full control over all rendering parameters. This allows for both a systematic investigation of the importance of the parameters and, an automatic labelling process of the training datasets. Our results show that, in particular, a detailed geometric modelling of the local surface topography and global object geometry of the pins have a positive influence on the recognition rate of the neural network. With that accuracy rates up to 56 % are achieved using synthetic training datasets, only.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jonathan Zender, Alexander Murawa, Bernd Pinzer, and Michael Layh "Capabilities and limits of synthetic images used for neural networks in optical scanners for the iron sand-cast industry", Proc. SPIE 13024, Optical Instrument Science, Technology, and Applications III, 130240B (17 June 2024); https://doi.org/10.1117/12.3016889

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available