Automatic Cotton Leaf Disease Diagnosis and Controlling Using Raspberry Pi and IoT

Abstract

The cotton crop is one of the maximum crucial cash crops among India. Plant diseases are generally due to pest insect and pathogens and every year reduce the productiveness to huge scale if not managed within time. When farmers observe that crop is infected, they detect the disease by naked eyes and decide the pesticide as solution by their previous experience. It is not the accurate way and instead of increasing crop production, they become responsible for the loss of production due to use of wrong pesticide in large quantity. So it is very essential to use automatic system for cotton leaf disease detection. This paper proposed such a system for diagnosis as well as controlling of disease infection on cotton leaves together with soil quality monitoring. The present system uses a support vector machine classifier for recognition of five cotton leaf diseases, i.e., Bacterial Blight, Alternaria, Gray Mildew, Cereospra, and Fusarium wilt. After disease detection, the name of a disease with its remedies is given to the farmers using Android app. The Android app is also used to display the soil parameters values inclusive of humidity, moisture, and temperature along with the water degree in a tank. By using Android app, farmers can ON/OFF the relay to control the motor and sprinkler in order to achieve crop suitable environment or to spray pesticides. All this leaf disease detection system and sensors for soil quality monitoring are interfaced with the usage of Raspberry Pi, which makes it impartial and price powerful system. This system shows the overall accuracy of 83.26% for disease detection.