Tobacco Plant Disease Detection and Classification using Deep Convolutional Neural Networks
B Mohith Kumar, K Rama Krishna Rao, P. Nagaraj, K. Muthamil Sudar, V. Muneeswaran
Abstract
India is the 2nd largest tobacco producer in the world. Collectively half of the states in India produce tobacco with an average of 804Millon kg all over India in each year. Due to the attack on diseases, pests and sudden changes in the weather, the productivity of tobacco decreases. Diseases may cause due to fungus survival in soil and affected water. Many machine learning algorithms can be used for classification but a convolutional neural network proved that high performance in classifying and detecting the object in the images. This research work will be designing and developing a deep learning model, which can classify and detect the disease in the tobacco plant by using the convolutional neural network. Once the disease is detected, this model will be suggesting the post-work to be done to overcome the disease. As these convolutional networks work with a large number of images for the training of the model, real-time images will be collected from the nearest farm fields in Prakasam district, Andhra Pradesh and label them into categories from the expen farmers. This research study has surveyed different research articles for collecting the multiple solutions for the cure of the disease so that the most used one can be suggested.