Abstract: In the field of agriculture, paddy cultivation plays a very important role. But the growth of paddy plants is affected by various diseases. There will be a decline in the production, if the diseases are not recognized at an early stage. The main goal of this work is to build up an image recognition system that can classify the paddy plant diseases affecting the cultivation of paddy plant namely brown spot, bacterial blight and leaf blast. The features from the disease affected portion are extracted using Histogram Oriented Gradient (HOG) features. Then these features are given as input to the Support Vector Machine (SVM) in order to recognize their category. By this approach one can detect the disease at an early stage and thus can take necessary steps in time to minimize the loss of production. The disease recognition accuracy rate is 97.73%.

Keywords: Agriculture, Accuracy Rate, Computer Vision, HOG, Pattern Classification, SVM Classifier.