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

Abstract Cotton is one of the major crops in India where 23% of cotton gets exported to other countries. Hence, the cotton yield depends on the crop growth, and it gets affected because of diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton database was created by capturing images in the field under controlled conditions. The same database is used for segmenting the images using modified factorization-based active contour. The color and texture features are extracted from segmented images and later its fed to the machine learning algorithms like Multilayer perceptron, Support vector machine, Naïve Bayes, Random forest, Ada Boost, K nearest neighbor. The performance of the classifiers is better when color features are extracted than texture features extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. Among the different classifiers, Multilayer perceptron gives nearly 96.69% which is greater than other classifiers.