Using Naive Bayesian Method for Plant Leaf Classification Based on Shape and Texture Features

As an initial step in protecting different plant species from extinction, establishment of database for plant becomes necessary in order to catalogue various plant diversities. Therefore, automatic and accurate recognition and classification system of plants is important. Thus, the research aims to study plant classification using naive Bayes (NB) method. Leaf shape and texture serves as input features to the model classifier. The test result shows that the classification accuracy of the model is high. The ROC curve area is 0.981. It indicates that the true positive rating is excellent and the weighted average of the false positive rating is 0.09%, which is considered very minimal and acceptable.