BI-DIRECTIONAL CLASSIFICATION OF ROMAN PERIOD COINS BY DEEP LEARNING METHODS

Authors : Kıyas KAYAALP, Fehmi ÖZKANER

Pages : 161-169

Doi:10.47933/ijeir.1269680

View : 87 | Download : 37

Publication Date : 2023-06-30

Article Type : Research Paper

Abstract :In this study, the problem of classification of coins, which have historical importance and can only be distinguished by experts, is discussed with pre-learning deep learning algorithms. In the solution of the problem, the RRC-60 dataset, which consists of the images of the coins used in the Roman Republic period, was used. In this study, pre-learning Xception, MobileNetV3-L, EfficientNetB0 and DenseNet201 models were trained using the images on both sides of the coins in the data set. As a result of the training, the best values, Precision, Recall and F1-Score metrics in the MobileNetV3-L model were 98.2%, 96.8%, 97.5%, respectively, and the test accuracy was 95.2%
Keywords : classification, CNN, coin, deep learning

ORIGINAL ARTICLE URL