UV Hyperspectral Imaging for Analyzing Cotton Types
Author Information
Author(s): Al Ktash Mohammad, Knoblich Mona, Eberle Max, Wackenhut Frank, Brecht Marc
Primary Institution: Reutlingen University
Hypothesis
This study aims to determine which light source provides better differentiation between cotton types in UV hyperspectral imaging.
Conclusion
The study found that UV hyperspectral imaging can effectively differentiate between various cotton types and hemp, with the deuterium light source providing better classification accuracy than the xenon light source.
Supporting Evidence
- The classification accuracy reached 76.1% for the xenon light source and 85.1% for the deuterium light source.
- PCA analysis explained approximately 94.8% of the variance with the xenon light and 89.4% with the deuterium light.
- A fully connected neural network achieved an accuracy of 83.6% with the xenon light and 90.1% with the deuterium light.
Takeaway
Scientists used special cameras to take pictures of different types of cotton using two kinds of lights, and they found that one light helped them tell the cotton types apart better than the other.
Methodology
The study used UV hyperspectral imaging with two light sources (xenon and deuterium) and applied principal component analysis (PCA) and quadratic discriminant analysis (QDA) for classification.
Limitations
The study's findings may be limited by the inherent similarities among different cotton types, which can complicate classification.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website