TY - JOUR
T1 - Hyperspectral band selection for detecting different blueberry fruit maturity stages
AU - Yang, Ce
AU - Lee, Won Suk
AU - Gader, Paul
N1 - Publisher Copyright:
© 2014 Elsevier B.V.
PY - 2014/11/1
Y1 - 2014/11/1
N2 - 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.
AB - 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.
KW - Band selection
KW - Blueberry
KW - Hyperspectral imagery
KW - Kullback-Leibler divergence
KW - Precision agriculture
KW - Yield mapping
UR - http://www.scopus.com/inward/record.url?scp=84907601250&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907601250&partnerID=8YFLogxK
U2 - 10.1016/j.compag.2014.08.009
DO - 10.1016/j.compag.2014.08.009
M3 - Article
AN - SCOPUS:84907601250
SN - 0168-1699
VL - 109
SP - 23
EP - 31
JO - Computers and Electronics in Agriculture
JF - Computers and Electronics in Agriculture
ER -