Supervised classification of monomodal and multimodal hyperspectral data in vibrational microspectroscopy: A comprehensive comparison

• Published in: Chemometrics and intelligent laboratory systems 2019-01, Vol.184, p.112-122
• Main Authors: Pomrehn, Ch, Klein, D., Kolb, A., Kaul, P., Herpers, R.
• Format: Article
• Language: English
• Subjects: Chemical imaging; Multimodal hyperspectral data; Pattern recognition; Supervised classification; Vibrational microspectroscopy
• ISSN: 0169-7439; 1873-3239
• DOI: 10.1016/j.chemolab.2018.11.013

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.