TECNALIA WEEE (Waste from Electrical and Electronic Equipment) HYPERSPECTRAL DATASET

TECNALIA WEEE HYPERSPECTRAL DATASET We present a dataset containing hyperspectral images of Waste from Electrical and Electronic Equipment (WEEE) scrap. These dataset contains pieces of copper, brass, aluminum, stainless steel and white cooper. Images contain 76 uniformly distributed wave-lengths in the spectral range [415.05 nm, 1008.10 nm]. Images were calibrated by using a white reference spectralon pattern and a dark spectralon pattern as depicted on the associated paper. Dataset content: XXXX.mat file: It contains two variables, 'hyperfile': Contains the hyperspectral data of the image, and 'bands': It contains the reference to each band. XXXX.png file: RGB representation of the image XXXX_gt.png file: It contains a image that assigns each pixel to a specific class according to the following index table: Dataset classes: - Background: 0 - Copper: 1 - Brass: 2 - Aluminum: 3 - Lead: 4 [NOT PRESENT] - Stainless Steel: 5 - White_Copper: 6 Creators: Artzai Picon (TECNALIA) Arantza Bereciartua (TECNALIA) Dataset citation: Picon, A., Ghita, O., Iriondo, P. M., Bereciartua, A., & Whelan, P. F. (2010, September). Automation of waste recycling using hyperspectral image analysis. In 2010 IEEE 15th Conference on Emerging Technologies & Factory Automation (ETFA 2010) (pp. 1-4). IEEE. You can get more theoretical information on the dataset and methods used here: Picón, A., Ghita, O., Whelan, P. F., & Iriondo, P. M. (2009). Fuzzy spectral and spatial feature integration for classification of nonferrous materials in hyperspectral data. IEEE Transactions on Industrial Informatics, 5(4), 483-494. Hyperspectral deep learning methods and code for management of this dataset on: https://github.com/samtzai/tecnalia_weee_hyperspectral_dataset Picon, A., Galan, P., Bereciartua-Perez, A., & Benito-del-Valle, L. (2024). On the analysis of adapting deep learning methods to hyperspectral imaging. Use case for WEEE recycling and dataset. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 125665. https://www.sciencedirect.com/science/article/pii/S1386142524018316