Botanical Disease Detection for Farmers using Machine Learning

Plant diseases cause major economic and production losses as well as curtailment in all quantiles and quantity of production, now a day’s for supervision of larger filed of crops. There is been increase demands for the plant leaf detection system. The critical is to monitor the health of the plant and detection of the disease. Observation shoes that most of the plant disease can be diagnosis by leaf properties. Thus, leaf-based disease analysis of crop is exciting new domain. The technique proposed for identify of crops disease through the leaf textual analysis and pattern recognition. In this project we focus on the various plant leaf disease detection. The system takes single leaf of a plant s an input and segmentation perform by removing background. The segmented leaf is analyzed through the filters to detect the disease potation. The segmented leaf textual is recovered using unique fraction-based feature. This textual format can provide good textual model as it is locally invariant in nature. This textual for every disease is different. Then this textual pattern is classified using SVM. The textual is mainly focus on the majorly disease observed on the plant. The proposed approach avails of agricultural expecting easily to farmers with accuracy of 80%.