<![CDATA[Batik is one of Indonesia's most important cultural arts and has received recognition from UNESCO. Batik has high artistic and historical value with a variety of patterns. Currently, Indonesia has 5,849 batik motifs which are generally classified based on shape, color, motif and symbolic meaning. The diversity of batik motifs makes it difficult for ordinary people to fully recognize them. This paper intends to develop an automatic framework for classifying batik motifs as a solution to overcome this issue. To develop this classification automation framework, the paper proposes a new architecture based on deep learning, which is named Okta-net. The architecture consists of 8 convolutional layers with separate convolution operations (SeparableConv2D). The output of the last convolution block will be fed to the fully connected layer using global average pooling. Meanwhile, in developing a deep learning model to classify batik image patterns, a dataset of 5 batik classes (motifs) was organized, consisting of 4,284 batik images. Through a series of experiments carried out, the proposed Okta-Net architecture succeeded in achieving satisfactory results with a validation accuracy of 93.17%, Precision of 91.60%, Recall of 92.28%, F-1 Score of 91.54%, and a loss of just 0.12%. Thus, it can be concluded that Okta-Net architecture can help preserve Indonesia's batik cultural heritage by accurate batik motif’s classification. Apart from that, based on a comparison of research outcomes, Okta-Net outperformed most of earlier studies, the majority of which had an accuracy of below 90%.]]>
Copyrights © 2025
