Effective classification of Chinese tea samples in hyperspectral imaging
Kelman, Timothy and Ren, Jinchang and Marshall, Stephen (2013) Effective classification of Chinese tea samples in hyperspectral imaging. Artificial Intelligence Research, 2 (4). ISSN 1927-6974
![]() |
PDF (Effective Classification of Chinese Tea Samples in Hyperspectral Imaging)
Effective_Classification_of_Chinese_Tea_Samples_in_Hyperspectral_Imaging.pdf Preprint Download (751kB) |
Abstract
Maximum likelihood and neural classifiers are two typical techniques in image classification. This paper investigates how to adapt these approaches to hyperspectral imaging for the classification of five kinds of Chinese tea samples, using visible light hyperspectral spectroscopy rather than near-infrared. After removal of unnecessary parts from each imaged tea sample using a morphological cropper, principal component analysis is employed for feature extraction. The two classifiers are then respectively applied for pixel-level classification, followed by modal-filter based post-processing for robustness. Although the samples look similar to the naked eye, promising results are reported and analysed in these comprehensive experiments. In addition, it is found that the neural classifier outperforms the maximum likelihood classifier in this context.
Creators(s): |
Kelman, Timothy ![]() ![]() ![]() | Item type: | Article |
---|---|
ID code: | 48404 |
Keywords: | hyperspectral imaging, tea classification, principal component analysis, maximum likelihood classification, artificial neural network, Electrical engineering. Electronics Nuclear engineering, Artificial Intelligence |
Subjects: | Technology > Electrical engineering. Electronics Nuclear engineering |
Department: | Faculty of Engineering > Electronic and Electrical Engineering Technology and Innovation Centre > Sensors and Asset Management |
Depositing user: | Pure Administrator |
Date deposited: | 03 Jun 2014 13:09 |
Last modified: | 20 Jan 2021 21:18 |
Related URLs: | |
URI: | https://strathprints.strath.ac.uk/id/eprint/48404 |
Export data: |