Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

From measurement to material – preparing hyperspectral signatures for classification

: Walocha, J.; Richter, M.

Fulltext urn:nbn:de:0011-n-3350015 (616 KByte PDF)
MD5 Fingerprint: 33af009560fcb98311afcfd03af05f3c
Created on: 14.4.2015

Beyerer, Jürgen (Ed.); Puente Leon, Fernando (Ed.); Längle, Thomas (Ed.):
OCM 2015, 2nd International Conference on Optical Characterization of Materials : March 18th - 19th, 2015, Karlsruhe, Germany
Karlsruhe: KIT Scientific Publishing, 2015
ISBN: 978-3-7315-0318-7
DOI: 10.5445/KSP/1000044906
International Conference on Optical Characterization of Materials (OCM) <2, 2015, Karlsruhe>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Due to the possibility of classifying unknown materials fast and accurately the industries interest in spectroscopy is growing. However, reliable classification is a matter of suitable preprocessing. Existing solutions found in the literature are often very specific a particular combination of materials. In this paper we present a method to preprocesses hyperspectral data in order to enables general classification of many materials. The system is divided into five modules: selection, transformation, reduction, decorrelation and classification. We demonstrate our method in a demonstrator system that is available as both web- and standalone application.