Detecting BSR-infected Oil Palm Seedlings using Thermal Imaging Technique

Basal Stem Rot (BSR) is the most destructive disease instigated by a white wood rotting fungus called Ganoderma boninense, which cause great economic setback in oil palm productivity. It attacks basal stem of trees, causing them to slowly rot. also affects xylem tissues that eventually interrupt water transportation upper part palm, turning leaves at frond become yellow. This problem should be prevented during nursery stage separating between healthy and BSR-infected seedling. Therefore, this study focuses on potential use thermal imaging for detecting BSR Thermal images seedling from were captured processed extract several properties seedling, i.e., maximum, minimum, mean, standard deviation pixel intensity value. These values then undergone statistical analysis identify its significant different differentiating Several classification models tested including Linear Discriminant Analysis (LDA), Quadratic (QDA), Support Vector Machine (SVM) k-Nearest Neighbour (kNN). Principal Component (PCA) was used reduce dimensionality dataset. The results demonstrated highest accuracy achieved 80.0 % using SVM (fine gaussian) model with PC1 PC3 as input parameter. summarizes trees stage.