<![CDATA[The preservation of Yogyakarta batik motifs as part of Indonesia’s cultural heritage can be supported through digital image classification technology. This study aims to develop an automatic classification system for Yogyakarta batik motifs using the Gray Level Co-occurrence Matrix (GLCM) method for texture feature extraction and the K-Nearest Neighbor (KNN) algorithm for the classification process. The dataset consists of 1,350 digital images of six different batik motif types, sourced from Kaggle. The system was developed and tested on the Google Colab platform through several stages, including preprocessing, feature extraction, model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The evaluation results show that the model achieved an accuracy of 60%, with the best performance on the batik-ceplok motif (F1-score of 77%) and the lowest on the batik-kawung motif (F1-score of 46%). The system was then implemented as a web application using the Streamlit framework, allowing users to upload images and receive classification results in real time. This implementation not only contributes to the field of image processing but also aids in cultural preservation through digitization and easy access to batik motif classification ]]>
Copyrights © 2024
