Abstrait

Disease Identification in Cotton Plants Using Spatial FCM & PNN Classifier

Premalatha.V, Valarmathy.S, Sumithra.M.G

Agricultural crops in India are under constant threat of pests affecting their roots as well as leaves. Plant diseases cause significant damage and economic losses in crops. Subsequently, reduction in plant diseases by early diagnosis results in substantial improvement in quality of the product. Enormous cotton crop yield is lost every year, due to rapid infestation by pests and insects. Infected cotton plants can exhibit a variety of symptoms and making diagnosis was extremely difficult. Common symptoms are includes abnormal leaf growth, color distortion, stunted growth, rots and damaged pods. In this paper, we have used spatial FCM & PNN classifier to identify the pest & type of disease in cotton plant. Image acquisition devices are used to acquire images of plantations at regular intervals. These images are then subjected to pre-processing using median filtering technique. The pre-processed leaf images are then segmented using Spatial FCM clustering method. Then the color features(mean, skewness), texture features such as energy, entropy, correlation, contrast, edges are extracted from diseased leaf image using repeated occurrence of gray level configuration in the texture & then compared with normal cotton leaf image. The Probabilistic Neural Network (PNN) method is used to classify the pest & Disease in cotton crop.