Cotton Leaf Disease Predictions Using Image on Plants

Cotton leaf diseases on cotton plant must be identified early and accurately as it can prove detrimental to the yield. The proposed work presents a pattern recognition system for identification and classification of three cotton leaf diseases i.e. Bacterial Blight, Myrothecium and Alter aria. The images required for this work are captured from the fields at Central Institute of Cotton Research Nagpur, Dr. Panjabrao Deshmukh Krishi Vidyapeeth, Akola and the cotton fields in Buldana and vardha district. Active contour model is used for image segmentation and Hus moments are extracted as features for the training of adaptive neuro-fuzzy inference system. The classification accuracy is found to be 85 per cent. Cotton is very important crop in our country and if some disease will affected on that crop the total economy of the farmer as well as country will get collapse. Normally in my country if disease will get detected by the farmer he will contact to the Experienced person and get solution for the same but if the detection and identification of disease not correct will badly affecting on the plant. In second case farmer will contact to the owner of pesticide shop the person will suggest some wrong treatment with respect to his experience. In third case is that farmers are just going with nature they thing is that the disease will get cleared automatically in some period of span.