Deep neural networks have been successfully applied in many different fields like computational imaging, healthcare, signal processing, or autonomous driving. In a proof-of-principle study, we demonstrate that computational optical form measurement can also benefit from deep learning. A data-driven machine-learning approach is explored to solve an inverse problem in the accurate measurement of optical surfaces. The approach is developed and tested using virtual measurements with a known ground truth.
Authors:
Lara Hoffmann; 8.4 Data Analysis and Measurement Uncertainty & 4.2 Imaging and Wave Optics
Clemens Elster; 8.4 Data Analysis and Measurement Uncertainty
For further information:
Hoffmann, L. and Elster, C.: Deep neural networks for computational optical form measurements, J. Sens. Sens. Syst., 9, 301–307, https://doi.org/10.5194/jsss-9-301-2020, 2020.