Tecnalia Electronic Equipment Waste Hyperspectral Dataset

*This dataset supports online use.Click here to jump.

The dataset was jointly released by researchers from TECNALIA and the University of the Basque Country in 2024.Hyperspectral Dataset and Deep Learning methods for Waste from Electric and Electronic Equipment Identification (WEEE)".

The Tecnalia hyperspectral dataset contains different non-ferrous metal fractions from Waste from Electric and Electronic Equipment (WEEE), such as copper, brass, aluminum, stainless steel, and nickel silver. The images contain 76 evenly distributed wavelengths in the spectral range [415.05 nm, 1008.10 nm].

The images were taken by a hyperspectral Specim PHF Fast10 camera, which is able to capture wavelengths in the range of 400 to 1,000 nanometers with a spectral resolution of less than 1 nanometer. The PHF Fast10 camera is equipped with a CMOS sensor (1024×1024 resolution), a Camera Link interface and a special Fore objective OL10. The illumination setup was specifically designed to reduce specular reflections generated by the surface of non-ferrous materials and to provide uniform and homogeneous illumination covering the wavelengths to which the hyperspectral camera is sensitive. The illumination system consists of a parabola that evenly distributes the light generated by 9 halogen lamps and 18 white LEDs covering the spectral range of 400 to 1,000 nanometers.