Ganoderma disease in oil palm caused by Ganoderma boninense fungus has resulted in a significant loss of economic income to Malaysia. There is a need to develop an airborne-based Ganoderma disease detection technology to reduce cost and time, and to cover wide-scale oil palm plantation area. This study examines the performance of red-green-blue (RGB) and near infrared (NIR) digital orthophoto image acquired using a modified digital cameras mounted on an unmanned aerial vehicle (UAV) for aerial detection and monitoring of Ganoderma disease in oil palm. In this study, the orthophoto images were filtered using eight adaptive filters with filter sizes of 7×7 and 9×9. The filtered orthophoto images were then processed using three supervised image classifiers i.e., Maximum Likelihood (ML), Mahalanobis Distance (MD) and Neural Net (NN). The classifiers were used to categorise the Ganoderma disease severities into T0 (healthy), T1 (mild), T2 (moderate) and T3 (severe). The classification outputs were assessed using confusion matrix. The classification results suggested that RGB, NIR orthophoto only provided moderate classification accuracy of Ganoderma disease detection in oil palm. Future works should explore the utilisation of hyperspectral orthophoto images for detection of Ganoderma disease in oil palm.