Machine learning approach for automatic diagnosis of Chlorosis in Vigna mungo leaves

Abstract

Viral infection in crops is something that may lead to a huge loss in crop yield as there are no known recovery procedures. Also, at the onset of yellowing in a leaf, no observable changes occur in leaf structure and geometry. Therefore, the manual inspection and diagnosis of such diseases by the framers in agricultural fields are difficult on a large scale. The automatic artificial intelligence-based tool can be used for early-stage diagnosis of viral growth, where the symptoms may be available in certain parts like leaves. An automatic computer vision-based method is proposed for the identification of yellow disease, also called Chlorosis, in a prominent leguminous crop like Vigna mungo. The proposed method involves fully automatic partitioning of plant leaves, followed by feature extraction in the spatial domain and disease prediction using a support vector machine (SVM) learned upon several training samples. The method is entirely automatic and non-destructive which can predict the classification of plant health category with an accuracy rate of 95.69% with low computation complexity. This accuracy and computational complexity can be used in real-time situations for a large scale of Vigna mungo plantation using drones and remote camera.