Radial Basis Function Neural Network for the Segmentation of Plant leaf disease

Plants being a balancing factor of the ecosystem are prone to a number of diseases which cause a significant loss in plant production. This drops down the quantity and the quality of the crop and their yields. Diseases in plants are generally classified among two factors biotic and abiotic. Among these, the most harm is introduced by the biotic elements. These elements can be Fungal, Bacteria, or Viral. Disease diagnosis via naked eye is a time-consuming process and tends to have probability of human error. Since last decade, several efforts have been made for making an autonomous system to detect the diseases stirring in plants. In this work, we propose an automated system using Radial Basis Function Neural Network (RBFNN) for the segmentation of plant diseases from leaf images. For this work, the images are collected from the IPM agriculture database repository. From the experimental results it is validated that the proposed RBFNN achieves higher segmentation accuracy when compared with the other methods. In future, the proposed work can be tested on different plants comprising of unrelated diseases.