Web Facilitated Anthracnose Disease Segmentation from the Leaf of Mango Tree Using Radial Basis Function (RBF) Neural Network

In this article, we present an automatic web facilitated leave disease segmentation system for mango tree using a neural network (NN). The proposed system compromised of four major steps. First, the real-time images of the mango leaves are acquired using the digital camera enabled with the web. Second, the images are preprocessed and features are extracted using a scale-invariant feature transform method. Third, the training of the NN is optimized with bacterial foraging optimization algorithm using the most dissimilar features. Finally, the radial basis function NN is used for the extraction of the diseased region from the mango leave images. The experimental results validated the high-level accuracy of the proposed system for the segmentation of anthracnose (fungal) disease obtaining an average Specificity = 0.9115 and Sensitivity = 0.9086. A comparison with other states of art methods is also presented, and some relevant future developments are also offered. This presented system is intuitive, user-friendly and is being developed to be espoused in precision agriculture.