Plant leaf diseases detection and auto-medicine

Abstract

Leaf diseases in plants cause major production and economic losses as well as reduction in both quality and quantity of agricultural crop. It's better to detect the leaf diseases in early on leaf health and disease detection can facilitate the control of diseases through proper management strategies.This paper presents a method for early detection of leaf diseases in plants based on some important features extracted from its leaf images. In the proposed system, the image of leaves are captured and compared with images in the database of the leaves that are pre-stored in the device memory. Leaf diseases are detected it checks for initial or final stage. If it is in initial stage, it sends message to the user through GSM regarding diseases. User can enable the medicine flow through relays by sending message back to GSM to turn on the medicine valve if necessary. The diseases are at final stage, it does not wait for user message, and it automatically enables the medicine flow to the farm.In addition to this, soil moisture and temperature sensors are used to avoid the spreading of diseases due to change in climatic conditions. Through these sensors this system can maintain the moisture of the land depending on the type of corp. If the values of moisture/temperature exceed the predefined range, the device enables auto medicine or water to the plants. Information regarding the plants and motor operations are intimated to farmer through GSM.