<![CDATA[Noken is a traditional bag from Papua that holds high cultural value and has been recognized as an Intangible Cultural Heritage by UNESCO. The diversity of noken types based on motifs, shapes, and regions of origin presents a challenge in the identification process, which until now is still carried out manually. This study aims to develop an automatic noken image classification system using Convolutional Neural Network (CNN) with a transfer learning approach. Three CNN architectures used in this study are VGG16, InceptionV3, and MobileNetV2. The dataset consists of 250 noken images, comprising two types of noken, Bitu Agia and Junum Ese. The training process was conducted using the TensorFlow library with the best parameters, namely 50 epochs, a batch size of 32, the Adam optimizer, and a learning rate of 0.0001. Evaluation was carried out using accuracy, precision, recall, and F1-score metrics, as well as confusion matrix visualization. The results showed that MobileNetV2 achieved the best performance with an accuracy of 97 persen, followed by InceptionV3 with 93 persen, and VGG16 with 87 persen. This study demonstrates that the deep learning approach is effective in the image classification of cultural objects and can support the digital preservation of Papuan culture.]]>
Copyrights © 2026
