<![CDATA[Batik is a distinctive Indonesian art form rich in diverse types and patterns. In the Solo region, several popular motifs exist, including Sawat, Semenrante, and Satriomanah. However, the high visual similarity among these three motifs poses challenges for manual identification. To address this issue, this study implements the Decision Tree (DT) method for automated classification. The extraction of texture characteristics from batik images is conducted using the Gray Level Co-occurrence Matrix (GLCM) method. The research stages encompass dataset collection, preprocessing, feature extraction, and classification. The experimental results demonstrate that the Decision Tree algorithm is highly capable of distinguishing types of batik fabric motifs. The model's performance yields an accuracy level of 96.11% in the 70%:30% dataset split scenario and increases to an optimal accuracy of 97.5% in the 80%:20% dataset split.]]>
Copyrights © 2026
