Generative Adversarial Network Implementation for Batik Motif Synthesis

Artificial intelligence is widely used due to its flexibility. Artificial intelligence can be used to generate and recognize patterns, for example batik motif. This study aims to generate a batik motif by utilizing a framework model made by Ian Goodfellow, namely Generative Adversarial Network (GAN) with reference to Deep Convolutional GAN (DCGAN) by Alec Radford. The training was implemented using two optimizer, RMSProp and Adam optimizer. The result shows that the networks were able to generate some pattern like batik motif and a non-batik motif pattern using RMSProp optimizer. The generated patterns were affected by the number and motifs of the dataset.