Return to search

Improved tree species discrimination at leaf level with hyperspectral data combining binary classifiers

The purpose of the present thesis is to show that hyperspectral data can be used for discrimination between different tree species. The data set used in this study contains the hyperspectral measurements of leaves of seven savannah tree species. The data is high-dimensional and shows large within-class variability combined with small between-class variability which makes discrimination between the classes challenging. We employ two classification methods: G-nearest neighbour and feed-forward neural networks. For both methods, direct 7-class prediction results in high misclassification rates. However, binary classification works better. We constructed binary classifiers for all possible binary classification problems and combine them with Error Correcting Output Codes. We show especially that the use of 1-nearest neighbour binary classifiers results in no improvement compared to a direct 1-nearest neighbour 7-class predictor. In contrast to this negative result, the use of neural networks binary classifiers improves accuracy by 10% compared to a direct neural networks 7-class predictor, and error rates become acceptable. This can be further improved by choosing only suitable binary classifiers for combination.

Identiferoai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:rhodes/vital:5567
Date January 2011
CreatorsDastile, Xolani Collen
PublisherRhodes University, Faculty of Science, Statistics
Source SetsSouth African National ETD Portal
LanguageEnglish
Detected LanguageEnglish
TypeThesis, Masters, MSc
Format138 p., pdf
RightsDastile, Xolani Collen

Page generated in 0.0022 seconds