Funding reference 01IS21065D
The aim of the project is to develop and validate methods for the synthesis of training data for Deep Learning-based particle measurement technology, exemplified by image-based methods for the detection of particles in (microscope) images to determine the particle size distribution, as well as time- and location-dependent
measurements of the transmission spectra of particle dispersions with commercially available measuring instruments as an example of multimodal sensor data. In addition, methods for quantifying the quality of the generated synthetic data sets with regard to their suitability for machine learning will be developed and
validated. In order to facilitate cooperation between research and industry with regard to classified particle images in the future, methods for anonymising and abstracting data sets from industry are being developed.
