Important: The project "VIADUCT" is a public project funded by the German Federal Ministry of Education and Research. In order to implement the potential analysis, we create images of your products, which will be transferred to a publicly accessible data set after project completion. If you do not want images of your products to be published, please contact us to discuss potential cooperation outside the framework of the project.
To ensure functional and aesthetic properties of a product, Fraunhofer IPK is developing novel approaches for data-reduced AI applications. Thus, it is possible to integrateThis facilitates integrating the advantage of AI-based image processing into the inspection process without having to accept the resulting large effort of training data collection. This is possible by reformulating the inspection task.
Purpose and advantages of “VIADUCT” research project
Instead of explicitly detecting learned defects in images, any deviation (anomaly) from a defined quality standard is detected. For this purpose, the AI is trained only with defect-free products, which naturally exist in significantly larger numbers than defective products.
This has two further advantages: