Dataset for automated material flow characterization of shredded WEEE: RGB raw data of an industrial sensor-based sorting machine

Three datasets containing raw RGB image data from an industrial sensor-based sorting machine. The images contain particles of shredded WEEE, including ferrous metals (FEM), non-ferrous metals (NFM), printed circuit boards (PCB), and plastics (PLA), in two particle size ranges of 12.5 mm - 25 mm (SML) and 25 mm - 50 mm (LRG). Each dataset is structured by material types and particle size ranges. - Dataset 1 (DS1) contains images that were used to train and test convolutional neural networks to identify the four material types through image classification, object detection, and instance segmentation. - Dataset 2 (DS2) contains images that were used in the training and testing of regression models for particle mass prediction. Due to its size, this dataset is split into four files for the individual material types. - Dataset 3 (DS3) contains images of particles from three predefined mixed samples to validate the models trained on the two previous datasets. The images were recorded with an industry-sized sensor-based sorting machine (Sesotec Varisort Compact [Schoenberg, Germany]) at the pilot-scale sorting plant at Fraunhofer IWKS in Alzenau.