<![CDATA[Yogyakarta batik motifs represent Indonesia’s cultural heritage, but automatic classification remains challenging. This study develops a Yogyakarta batik motif classification system using a combination of the Gray Level Co-occurrence Matrix (GLCM) for texture feature extraction and Convolutional Neural Network (CNN) based on MobileNetV2 for image classification. GLCM was chosen for its ability to extract detailed texture features, while MobileNetV2 was used for its efficiency in visual pattern recognition with minimal computational resources. The dataset consists of 3,223 images from five batik motifs: Batik Ceplok, Batik Kawung, Batik Truntum, Batik Parang, and Batik Ciptoning, sourced from the Batik Keraton Museum Yogyakarta and Kaggle. The model achieved 99% accuracy, demonstrating the effectiveness of the approach in recognizing complex batik patterns. The results suggest that this system can be implemented into a mobile application with a client-server architecture for automatic motif detection. Despite promising results, the study is limited by dataset size and the complexity of specific motifs. Future research should expand the dataset and explore data augmentation techniques to improve classification accuracy for more complex motifs.]]>
Copyrights © 2024
