<![CDATA[Batik is a recognized intangible cultural heritage of Indonesia, featuring diverse motifs and deep-rooted philosophical meanings. Solo is one of the regions known for its distinctive batik patterns. However, manual identification remains challenging due to visual similarities between motifs. This study aims to develop an automatic classification system for identifying four Solo batik motifs Parang, Sidoasih, Sidomukti, and Truntum using a Convolutional Neural Network (CNN). The dataset includes 250 labeled digital images collected from online repositories and prior research. The data were split into training, validation, and test sets. Preprocessing steps involved resizing to 224×224 pixels, normalization, and data augmentation. The CNN architecture comprises three convolutional layers, max pooling, a flatten layer, and two dense layers. The model was trained for 20 epochs using the Adam optimizer and categorical cross-entropy loss function. Evaluation results showed that the model achieved an accuracy of 89.36% and a loss value of 0.5172. The macro and weighted f1-scores exceeded 0.88, indicating high classification performance. These results demonstrate the potential of CNNs in recognizing complex batik motifs and highlight the role of AI in preserving cultural heritage through technology.]]>
Copyrights © 2025
