Deep Learning Model for Image-Based Plant Diseases Detection on Edge Devices

Plant diseases are a major threat to global food security. Infection of plants by pathogens can have serious consequences on plant health which inherently affects human health. With more than 80 percent of agricultural production done by smallholder farmers who depend on healthy crop yield for their livelihood, yield loss of more than 50 percent due to pests and diseases is reported. Currently, infectious diseases reduce the potential yield by an average of 40% with many farmers in the developing world experiencing yield losses as high as 100%. The widespread distribution of smartphones among crop growers around the world with an expected 5 billion smartphones by 2020 offers the potential of turning the smartphone into a valuable tool for diverse communities growing food. One potential application is the development of mobile disease diagnostics through machine learning and crowdsourcing. With the help of state of art technologies like deep learning and cloud computing, the same can be achieved on a real-time basis. With the help of Convolutional Neural Network architectures, a system is proposed that focuses on detection and identification of the plant disease with a mere click of leaf picture and provides solutions.