Automated Recognition of Batik Aceh Patterns Using Machine Learning Techniques

This research focuses on the automatic recognition of Aceh batik patterns using machine learning techniques. Utilizing a Convolutional Neural Network (CNN) model based on EfficientNet, a dataset consisting of 1,200 Aceh batik images was processed through various stages, from data collection to model training and evaluation. The images are divided into three main classes: Bungong Jeumpa, Ceplok, and Kerawang. The data processing steps include normalization, resizing, and data augmentation to ensure better variation. The model was trained using 75% of the data as a training set and 25% as a testing set. The results indicate that the model performed excellently, achieving an accuracy rate of 98%. According to the classification report, the model achieved an average precision, recall, and F1-score of 0.98. The Kerawang category achieved the highest precision at 100%, while the Bungong Jeumpa and Ceplok categories had F1-scores of 0.98 and 0.97, respectively. These findings demonstrate the potential of machine learning methods in recognizing Aceh batik patterns with high accuracy, supporting the preservation of local culture through technology.