A Polyhouse: Plant Monitoring and Diseases Detection using CNN

Poly-house farming is broadly used way for farming in now days. Poly-house will provide the required amount of water and fertilizers that result in high yields. The lack of air circulation causes breeding ground for insects. To overcome this, continuous monitoring of crops is needed. Hence, monitoring parameters like temperature and intensity is essential for efficient farming by indicating the required amount of water, nutrients, and pesticides at right time. This would also indirectly suppress the onset and spread of diseases. Thus, motivated by this arduous exercise, our objective is to suggest a solution for monitoring the plant and detecting the plant disease at early stage. Automated plant disease detection techniques are useful to detect the symptoms of diseases at early stage in big farms. The dataset used for this work contain images of various plants consisting of both diseased and healthy leaves. Convolution Neural Network (CNN) is used train the model for detecting the plant diseases. The plants considered include Corn, Strawberry, Grape, Tomato and Potato plants. The model predicts the health of most of the plants with optimal accuracy of prediction being 85% and negligible loss of 0.25 was observed in the course of training the data.