Detecting Diseases in Rice Leaf Using Deep Learning and Machine Learning Techniques

Plant diseases have a serious affect on the farming industry. Because of these diseases there is a bad impact on the productivity of the crops. This leads to huge losses to farmers. To ensure better quality, quantity and productivity of the yield, it is very crucial for identifying the diseases at early stage for reducing the use of pesticides to reduce damage of the crops and environment. In this research the motive was to detect and classify the diseases in the rice leaf, having four categories of classes as healthy, hispa, brown spot and leaf blast. In this research study convolutionl neural network was used for the feature extraction from the rice images. Whereas, some machine learning classifiers such as Random Forest and K-Nearest Neighbors were used for the classification of the diseases based on the categories. The first model CNN performed well for the feature extraction with the accuracy of 80 percent. Along with this second model was classification of diseases using some machine learning classifiers such as Random Forest and KNearest Neighbors, accomplished the accuracy of 96% and 72% respectively