Hyperspectral imagery divides spectrum into many bands with very narrow bandwidth. It is more capable to detect or classify objects, where visible information is not sufficient for the task. However, hyperspectral image contains a large amount of redundant information, which eliminates its discriminability. Band selection is used to both reduce the dimensionality of hyperspectral images and save useful bands for further application. This study explores the feasibility of hyperspectral imaging for the task of classifying blueberry fruit growth stages and background. Three information theory based band selection methods using Kullback-Leibler divergence: pair-wise class discriminability, hierarchical dimensionality reduction and non-Gaussianity measures were applied. Three classifiers, K-nearest neighbor, support vector machine and AdaBoost were used to test the performance of the selected bands by the three methods. The selected bands achieved classification accuracies of 88% and higher. Therefore, the band selection methods are very useful in reducing the volume of the hyperspectral data, and constructing a multispectral imaging system for detecting blueberry fruit maturity stages.
|Original language||English (US)|
|Number of pages||9|
|Journal||Computers and Electronics in Agriculture|
|State||Published - Nov 1 2014|
Bibliographical noteFunding Information:
The authors would like to thank Dr. Changying Li from University of Georgia for offering the blueberry demonstration field for data collection. Many thanks go to Mr. John Ed Smith from University of Georgia, Ms. Han Li, Mr. James Park, and Mr. Hao Ma, from the Precision Agriculture Laboratory, University of Florida, who helped collect the images in the field. This study was funded by the Graduate School Fellowship at the University of Florida.
© 2014 Elsevier B.V.
- Band selection
- Hyperspectral imagery
- Kullback-Leibler divergence
- Precision agriculture
- Yield mapping