<![CDATA[Palembang jumputan cloth has a distinctive motif, which is part of the heritage culture of Indonesia. However, process identification motif is still done manually, requiring high accuracy and being prone to errors. This study aims to build an automatic detection system for Jumputan fabric motifs using the Canny Edge Detection method to extract borders and a Rule-Based Classifier for motif classification based on the number, area, and contour density features. This study uses 750 fabric images from five types of motifs: Tiga Negeri, Titik Tujuh, Tabur, Lereng, and Ecoprint. The images are processed through grayscale conversion, histogram smoothing, and Canny edge detection. The results of feature extraction are used to classify motifs using logical rules. Based range, mark each feature. Evaluation done with a confusion matrix and produces an accuracy rate of 54%, which shows that this method is quite Good as an approach, beginning, however, still needs improvement so that More accurate classification results. The system has also been implemented in a GUI interface for practical use.]]>
Copyrights © 2026
