Using appropriately designed spectral filters allows to optically determine material abundances. While an infinite number of possibilities exist for determining spectral filters, we take advantage of using neural networks to derive spectral filters leading to precise estimations. To overcome some drawbacks that regularly influence the determination of material abundances using hyperspectral data, we incorporate the spectral variability of the raw materials into the training of the considered neural networks. As a main result, we successfully classify quantized material abundances optically. Thus, the main part of the high computational load, which belongs to the use of neural networks, is avoided. In addition, the derived material abundances become invariant against spatially varying illumination intensity as a remarkable benefit in comparison with spectral filters based on the Moore-Penrose pseudoinverse, for instance.

Date Published: 26 June 2017
PDF: 9 pages
Proc. SPIE 10334, Automated Visual Inspection and Machine Vision II, 1033408 (26 June 2017); doi: 10.1117/12.2270237

Published in SPIE Proceedings Vol. 10334:
Automated Visual Inspection and Machine Vision II
Jürgen Beyerer; Fernando Puente León, Editor(s)