They are faced with the rapid development of plant science, especially the science of rose flora. The rose has a sweet-smelling charm; beautiful color. Many people, like roses, are deliberately cultivated by the beauty industry as the main ingredient in making cosmetics. Roses have various varieties, and the types have similarities, so it is difficult to distinguish, know and determine the varieties of roses; in plain view, it requires a long time and precision. In this study, the Naïve Bayes and K-Nearest Neighbor applications were used. Algorithms will be carried out for the classification of roses in addition to proving the identification and classification of rose varieties based on morphological characteristics using K-NN and Naïve Bayes to understand the diversity of roses. The Naive Bayes method produced maximum accuracy with little training data. Meanwhile, K-Nearest Neighbor was chosen because it is robust against noise data. The performance of the two methods will be compared to determine which method is better for classifying roses. The results show that the Naive Bayes method performs better, with an accuracy rate of 75%, while the K-Nearest Neighbor method has an accuracy rate of 62.5%.
Copyrights © 2023