10.17862/cranfield.rd.9968051.v1 Carlos Vrancken Carlos Vrancken Stuart Wagland Stuart Wagland Philip Longhurst Philip Longhurst Results from deep learning tests using balanced databases for the classification of paper and cardboard materials. Cranfield Online Research Data (CORD) 2019 waste material recognition deep learning artificial intelligence balanced dataset Artificial Intelligence and Image Processing 2019-10-14 13:28:49 Dataset https://cord.cranfield.ac.uk/articles/dataset/Results_from_deep_learning_tests_using_balanced_databases_for_the_classification_of_paper_and_cardboard_materials_/9968051 <div>For methodology used to obtain these results please refer to the publication: "Deep learning in material recovery: Development of method to create training database".</div><div><br></div><div>These results were obtained using grayscale version of the images.</div><div><br></div><div>The "Balanced dataset - classification results" spreadsheet includes:<br></div><div><br></div><div>Sheet 1 - classification results when classifying 3 classes of fibre materials using increasing number of samples per class in a balanced training dataset</div><div><br></div><div>Sheet 2 - classification results when using a balanced dataset with 5,000 training samples per class to classify 10 classes of fibre waste material</div>