Detection of Paddy Leaf Diseases

Abstract

India is an agricultural country. Farmer has wide range of diversity to select suitable crops. However, cultivation of these crops for optimum yield and quality produce is highly technical by using technical support. Detection of plant disease is an essential research topic. Studies show that relying on pure naked-eye observation of expert to detect such diseases can be prohibitively expensive, especially in developing countries. Providing fast, automatic, cheap and accurate image processing-based solutions for that task can be great realistic significance. This paper presents computationally efficient method for paddy leaf disease identification. The proposed approaches consist of three phases: image segmentation, feature extraction and classification. Image segmentation technique is used to detect infected parts of leaf by using K-means clustering. The feature extraction phase derives features based on the paddy leaf image. These features are used as input to the classifier for classification purpose. In this experiment, the classifier is used as artificial neural network. Many researchers are working on real time plant leaf diseases from many years. In future, this project will be implemented for real time leaf disease detection. This project is very useful to farmer to detect paddy diseases at early stage.