Image-based identification of maydis leaf blight disease of maize (Zea mays) using deep learning

Abstract

In recent years, deep learning techniques have become very popular in the field of image recognition and classification. Image-based diagnosis of diseases in crops using deep learning techniques has become trendy in the current scientific community. In this study, a deep convolutional neural network (CNN) model has been developed to identify the images of maydis leaf bight (MLB) (Cochliobolus heterostrophus) disease of maize (Zea mays L.) crop. A total of 1547 digital images of maize leaves (596 healthy and 951 infected with maydis leaf blight disease) have been collected from different agricultural farms using hand-held camera and smartphones. The images have been collected from the experimental plots of BCKV, West Bengal and ICAR-IARI, New Delhi during 2018-19. The architectural framework of popular state-of-the network 'GoogleNet' has been used to build the deep CNN model. The developed model has been successfully trained, validated and tested on the above-mentioned dataset. The trained model has achieved an overall accuracy of 99.14% on the separate test dataset.