The Hybrid Features and Supervised Learning for Batik Pattern Classification

Abstract

Several countries have traditional textiles as a piece of their cultural heritage. Indonesia has a traditional textile called batik. Central Java is one of the regions producing batik known for its variety of distinctive themes. It has unique designs and several motifs that emphasize the beauty of historic sites. Since the diversity of central java batik motifs and the lack of knowledge from the surrounding community, only a select group of people, especially the batik craftsmen themselves, can recognize these motifs. Consequently, the method to identify the batik according to the primary ornament pattern is required. Therefore, this study proposes a computer vision-based method for classifying batik patterns. The proposed method required discriminating appropriate features to produce optimal results. The discriminating features were constructed based on color, shape, and texture. Those features were derived using the method of Color Moments, Area Based Invariant Moments, Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP). This study’s proposed hybrid features were formed based on the most discriminating and appropriate features. These were yielded by the Correlation-based feature selection (CFS) method. The hybrid features were then fed into several classifiers to determine the batik pattern. The pattern consists of ten classes: Asem Arang, Asem Sinom, Asem Warak, Blekok, Blekok Warak, Gambang Semarangan, Kembang Sepatu, Semarangan, Tugu Muda, and Warak Beras Utah. Based on the experimental results, the most optimal predicted class of the batik pattern was generated using the Artificial Neural Network (ANN) classifier. It was indicated by achieving an accuracy value of 99.76% based on the 3000 images (each class consists of 300 images) with cross-validation using a k-fold value of 10. This study has proved that the hybrid features incorporated with ANN can be selected as a suitable model to classify the batik patterns.