Leaf Disease Detection and Automatic Pesticide Suggestion Using Deep Learning

Abstract

Diseases that are caused by fungus are developed through soil-borne, above-ground infections. Pest and insect feeding causes the transmission of fungus. However, the existing research lacks an accurate and fast detector of leaf diseases for ensuring the healthy development of the agricultural industry. This project proposes a novel approach for developing an effective method for identifying the plant leaf diseases. Based on the identification of diseases, suggestion forthe pesticide is also given. A deep learning approach which is based on Multilayer Deep convolutional neural networks (CNNs) for the real-time detection of leaf diseases is used in the work. It also detects the types of leaf diseases with high accuracy. In addition, the proposed approach can handle the images of the diseased leaves. The results showed good improvement in identifying the plant leaf diseases.