Classification of Indonesian Batik Using Deep Learning Techniques and Data Augmentation

Abstract

Although batik is one of the most prestige heritage in Indonesia, many Indonesian people cannot recognize the pattern name of batik that they wear or see. Moreover, the batik varieties increase each year so batik pattern becomes harder to be identified. Based on that fact, automatic batik classification become of more importance to assist people in recognizing the batik pattern. In addition, Batik patterns are critical to being understood because there is the history behind the pattern. In order to recognize the batik pattern automatically, we implement batik classification methods using Convolutional Neural Network (CNN) that is called VGG-16 and VGG-19 and they are able to predict almost 90% correctly in classifying batik patterns. But the variation of batik images such as rotated and scaled images make the classifier cannot effectively detect the type of batik pattern. To illustrate, the batik classification accuracy becomes less than 56% when it has classified a batik pattern that is scaled 2.0. Then we train the CNN with augmented data to improve the accuracy. After all, the augmented data technique can improve the accuracy as well as 10% for rotated images or scaled images.