Detection of Early Stages of Canker on Apple Tree Using Hyperspectral Imaging Technique to Thwart Canker Spread

The early detection of canker can be helpful to thwart the canker disease in apple trees. The canker is a fungal disease that gradually wilts the tree. Using Hyperspectral Imaging (HSI) one can retrieve differences. Hyperspectral Imaging captures a lot more detailed image between 400-1400 nm whilst normal cameras capture only visible spectrum (400 - 700 nm). The ROI of the image falls under wavebands 560, 685, and 1200 nm. A model is created to find the nuances between early infected and later infected areas of an apple tree. The data is multivariate, hence Mahalanobis distance was used on NDSI which is retrieved after measuring spectral reflectance. The overall accuracy of the model is >0.95. This model can be applied to other varieties of apple tree bark and twig canker detection.