A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Cotton is one of the major crops in India, where 23% cotton gets exported to other countries. The yield depends on crop growth, and it affected by diseases. In this paper, disease classification performed using different machine learning algorithms. For research, leaf image database was used segment images from natural background modified factorization-based active contour method. First, color texture features are extracted segmented images. Later, has be fed algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, K-nearest neighbor. Four eight were extracted, experimentation done three cases: (1) only features, (2) (3) both features. performance classifiers better when compared feature extraction. enough classify healthy unhealthy evaluated parameters precision, recall, F-measure, Matthews correlation coefficient. accuracies neighbor 93.38%, 90.91%, 95.86%, 92.56%, 94.21%, respectively, whereas that perceptron classifier 96.69%.