Automated Detection of Leaf Diseases in Plants

Crop damage due to diseases is one of the most crucial problems in agriculture sector. Infection in leaf gradually deteriorates the health condition of crops and reduces the yield. Proper recognition of diseases through automated computer vision can be an innovative idea to solve this problem in agriculture. An automated leaf disease identification and detection system for tomato and strawberry plants using IoT and an algorithm based on Artificial Neural Networks (ANN) is proposed in this paper. The leaf images are captured using IoT enabled device and saved on a cloud server. Image acquisition, pre-processing, segmentation, texture analysis, Gray-Level Co-Occurrence Matrix feature extraction and ANN classification features have been used. The results have been made available on a user's cell phone. The results of this work indicate that image processing algorithm shows better efficiency than the visual analysis. The main contribution of this study is the fast and accurate detection of the various diseases on the leaves. Using this project, a farmer can upload infected leaf images and understand the disease name on a cellphone without any expensive setup. The farmers can take the proper precautionary measures in time and achieve an improved farming with this setup.