Plant Leaf Diseases Identification using Deep Learning Approach for Sustainable Agriculture

Farming is one of the most important sectors of the Indian Economy. Farming accounts for almost 50% of the country's workforce. Farmers' economic growth depends on the quality of the products that they produce, which relies on the plant's growth and the yield they get. The raise in farmers' yield can bring a positive impact on the country’s economy. Therefore, in the field of agriculture, the detection of disease in plants plays an instrumental role. To detect a plant disease at its initial stages, more advanced tools such as image processing and deep learning are needed. The objective of this research is to classify plant diseases by assessing the images of the leaves with the application of Transfer Learning. The work is majorly focused on EfficientNet which is a CNN built by google to achieve better accuracy and efficiency while using less number of features. The simulated results reveal that based on the number of epochs the EfficientNet archives have a better accuracy ranging from 98-99.5% on the real-time data set used in this work.