Detection of Harvest Status of Oil Rose (Rosa damascena Mill.) with Machine Learning and Deep Learning Methods

Abstract

Plants have an important place in human life in many sectors for many years. Rosa damascena Mill plant, which is called Pink Oil Rose, is a species that has economic value for sectors such as cosmetics, perfume, medicine and food industry with its distinctive sharp and intense scent among rose varieties. Oil rose is harvested in May in Turkey when its buds bloom. Roses in bud form are left unharvested until they bloom. In this study, binary classification of each oil rose according to "harvestable/non-harvestable" status was carried out using machine learning and deep learning methods. The data set created with the images obtained from the rose gardens was used in the training and testing of artificial intelligence models. DVM classifier was used as machine learning model, and VGG16, VGG19 and InceptionV3 were used as deep learning models. Classification performance is 71.06% in the DVM model, 96.44% in the VGG16 model, 97.96% in the VGG19 model and 72.08% in the InceptionV3 model.