Simulation-Based Evaluation of Wavelet Coefficients for Robust Analysis of Near Infrared Spectra
Abstract (englisch):
Near infrared spectroscopy is a common method for analysis of food, soil and pharmaceutical products. New developments in sensor technology, like hyperspectral camera systems and mobile spectrometers, allow broad applications of spectroscopy with devices out of specialized laboratories. Wavelet coefficients are a promising approach for the detection and estimation of spectral absorption bands. The robustness of wavelet based features against typical measuring influences and calibration errors will be analyzed in the following by using simulations.
| Zugehörige Institution(en) am KIT | Fakultät für Informatik – Institut für Anthropomatik (IFA) |
| Publikationstyp | Proceedingsbeitrag |
| Publikationsjahr | 2019 |
| Sprache | Englisch |
| Identifikator | ISBN: 978-3-7315-0936-3 ISSN: 1863-6489 KITopen-ID: 1000097098 |
| Erschienen in | Proceedings of the 2018 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. Ed.: J. Beyerer, M. Taphanel |
| Verlag | KIT Scientific Publishing |
| Seiten | 89-99 |
| Serie | Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ; 40 |
| Bemerkung zur Veröffentlichung | Technical Report IES-2018-08 Kurztitel lt. Inhaltsverzeichnis: Wavelet Coefficients as Features in Near Infrared Spectra |
| Relationen in KITopen |