Near-infrared imaging spectroscopy (NIRIS) and image rank analysis for remote identification of plastics in mixed waste

An infrared camera with focal plane InSb array detector has been applied to the characterization of macroscopic samples of household waste over distances up to two meters. Per waste sample (singelized), a sequence of images was taken at six optical wavelength ranges in the near infrared region (1100 nm - 2500 nm). The obtained three-dimensional data stack served as individual fingerprint per sample. An abstract factor rotation of this stack of six images into a spectroscopical meaningful intermediate six-element vector by Multivariate Image Rank Analysis (MIRA) finally provided a decision limit for the discrimination of plastics and nonplastics. A correct classification of better than 80% has been reached. The experimental NIRIS set-up has been automated so far to allow an on-line identification of a real world waste sample within a few seconds.