Automated Detection of Plant Diseases Using Image Processing and Faster R-CNN Algorithm

Abstract

The economy of Bangladesh highly depends on the field of agriculture and the production of the crops each year. This is one of the reasons that plant disease identification has become the most crucial factor in cultivating crops. Wrong identification or late identification can cause excessive loss of the production as well as in the financial status of the farmers. Bangladesh being an agriculture-based country, needs to have scientific methods and proper knowledge of this problem. In this condition, providing the farmers some automatic disease detection techniques can reduce their workload and the fear of loss of their production. This paper presents a method that detects diseases from plant leaf images using Tensorflow which is an object detection API, and the model was trained using a faster RCNN method. The rate of accuracy is also calculated. After extensive training on different samples of datasets, our machine learning approach learns gradually and can be more effective in detecting plant diseases.