Medicinal and Aromatic Plants Identification Using Machine Learning Methods

Authors : Gökhan KAYHAN, Erhan ERGÜN

Pages : 81-87

Doi:10.17694/bajece.651286

View : 21 | Download : 8

Publication Date : 2020-01-31

Article Type : Research Paper

Abstract :In this study, different machine learning insert ignore into journalissuearticles values(ML); methods were used to classify medicinal and aromatic plants insert ignore into journalissuearticles values(MAP); namely St. John’s wort insert ignore into journalissuearticles values( Hypericum perforatum L.);, Melissa insert ignore into journalissuearticles values( Melissa officinalis L.);, Echinacea insert ignore into journalissuearticles values( Echinacea purpurea L.);, Thyme insert ignore into journalissuearticles values( Thymus sp.); and Mint insert ignore into journalissuearticles values( Mentha angustifolia L.);  based on leaf shape, gray and fractal features. Naive Bayes Classifier insert ignore into journalissuearticles values(NBC);, Classification and Regression Tree insert ignore into journalissuearticles values(CART);, K-Nearest Neighbor insert ignore into journalissuearticles values(KNN);, and Probabilistic Neural Network insert ignore into journalissuearticles values(PNN); classification were used as methods. The results indicated that plant species were successfully recognized the average of correct classification rate. The best classification rate on the NBC was taken: training data for classification rate 98.39% and test data classification rate for 98.00% are obtained. ML could be accurate tools for MAP classification tasks.
Keywords : classification, feature extraction, image processing, machine learning