Refine
H-BRS Bibliography
- yes (11) (remove)
Departments, institutes and facilities
- Institut für Sicherheitsforschung (ISF) (11) (remove)
Document Type
- Article (6)
- Conference Object (4)
- Conference Proceedings (1)
Year of publication
- 2019 (11) (remove)
Keywords
- Hyperspectral image (2)
- Raman microscopy (2)
- image fusion (2)
- pansharpening (2)
- Anoplophora glabripennis (1)
- Chemical imaging (1)
- Chemometrics (1)
- DNA typing (1)
- Degraded DNA (1)
- Discriminant analysis (1)
- Forensic genomics (1)
- Geruchssinn (1)
- Kriminalistik (1)
- Microorganisms (1)
- Multimodal hyperspectral data (1)
- Next Generation Sequencing (NGS) (1)
- Pattern recognition (1)
- Poultry meat (1)
- Principal Components Analysis (1)
- Principal component analysis (1)
- Probabilistic methods (1)
- Raman spectroscopy (1)
- Raman-microspectroscopy (1)
- Short tandem repeat (STR) (1)
- Spoilage (1)
- Spoilage bacteria (1)
- Spürhund (1)
- Supervised classification (1)
- Support vector machines (1)
- TD-GC/MS (1)
- Telogen hair (1)
- Vibrational microspectroscopy (1)
- Volatile organic compounds (1)
- automated sensor-screening (1)
- brightfield microscopy (1)
- high degree of diagnostic coverage and reliability (1)
- multi-channel power sourcing (1)
- multiresolution analysis (1)
- semiconducting metal oxide gas sensor array (1)
The application of Raman and infrared (IR) microspectroscopy is leading to hyperspectral data containing complementary information concerning the molecular composition of a sample. The classification of hyperspectral data from the individual spectroscopic approaches is already state-of-the-art in several fields of research. However, more complex structured samples and difficult measuring conditions might affect the accuracy of classification results negatively and could make a successful classification of the sample components challenging. This contribution presents a comprehensive comparison in supervised pixel classification of hyperspectral microscopic images, proving that a combined approach of Raman and IR microspectroscopy has a high potential to improve classification rates by a meaningful extension of the feature space. It shows that the complementary information in spatially co-registered hyperspectral images of polymer samples can be accessed using different feature extraction methods and, once fused on the feature-level, is in general more accurately classifiable in a pattern recognition task than the corresponding classification results for data derived from the individual spectroscopic approaches.