Henrike Stephani 1* , Michael Herrmann 2 , Frank Bauer 3 , and Bettina Heise 3
1 Fraunhofer ITWM and Technical University, Kaiserslautern, Germany, Address: Fraunhofer Platz 1, 67663 Kaiserslautern, Germany
2 Fraunhofer IPM, Kaiserslautern, Germany, 3Johannes Kepler University, Linz, Austria
*1 Email: email@example.com
View Full Text: PDF
Abstract: With terahertz time-domain spectroscopy, hyperspectral images can be acquired where each pixel contains a full spectrum of the range of several terahertz (THz). An enormous amount of data is generated. Therefore, advanced methods for automated data analysis and image processing are required. We present a wavelet-based approach for channel reduction and feature selection for a subsequent clustering leading to an image segmentation. The main focus of our method is set on the appropriate dimensionality reduction adapted to the THz spectral characteristics of the samples under investigation. A feature reduction to less than 5% is achieved, thereby enabling a channel-wise image processing on the reduced data set. Furthermore, unsupervised classification is chosen for an automatized segmentation including all channel information represented in the wavelet domain. Relevant characteristics of the THz spectra are preserved by our feature selection, in particular the distribution of the peak position and peak depth. The proposed method for channel reduction is verified by extensive simulations at first. Finally, it is demonstrated on various real-world measurements of chemical compounds. The improved performance of the analysis on the reduced feature set could be shown in comparison with the evaluation on the full data set.
Keywords: THz-TDS Imaging, Hyperspectral Image Processing, Feature Selection.
Acknowledgments: We thank the colleagues of the Department of Knowledge-Based Mathematical Systems at the JKU, especially Erich Peter Klement for discussion and support as well as Karin Wiesauer and Stefan Katletz from RECENDT GmbH and the Image Processing Department of the Fraunhofer ITWM, Kaiserslautern. Part of this work was supported by the BMWi German Federal Ministry of Economics and Technology (THESEUS program, use case ORDO) and the BMBF German Federal Ministry of Education and Research (TEKZAS program).
Cite this article:
Henrike Stephani, Michael Herrmann, Frank Bauer, and Bettina Heise. Wavelet-Based Dimensionality Reduction for Hyperspectral THz Imaging[J]. International Journal of Terahertz Science and Technology, 2010, Vol.3, No.3: 117-129. DOI:10.11906/TST.117-129.2010.09.12