Klasifikasi Jenis Eucalyptus Berdasarkan Citra Daun Menggunakan Metode Transfer Learning VGG16

Abstract

Eucalyptus has 700 species worldwide and each has its own characteristics in the shape and characteristics of its leaves. The differences in Eucalyptus leaves can be distinguished by people who have studied this plant for a long time, in contrast to people who have never seen and held Eucalyptus leaves directly, it looks very difficult because of their distinctive shape and characteristics and very difficult to distinguish. Therefore, we need a system that can classify the types of Eucalyptus plants. In this study, the VGG16 transfer learning method was used to classify Eucalyptus plants. The data used are 3 types of Eucalyptus plants, namely Eucalyptus Grandis, Eucalyptus Robusta and Eucalyptus Citriodora. The leaf image data used is 1800 data including 600 Eucalyptus Citriodora image data, 600 Eucalyptus Grandis image data and 600 Eucalyptus Robusta image data. Several experiments have been carried out in this study so that precision, recall, FI-score and accuracy values of 95% have been obtained.