Generative Adversarial Network Implementation for Batik Motif Synthesis

Abdurrahman, Miqdad and Shabrina, Nabila Husna and Halim, Dareen K (2019) Generative Adversarial Network Implementation for Batik Motif Synthesis. In: 2019 5th International Conference on New Media Studies (CONMEDIA), 9-11 Oct. 2019, Bali, Indonesia.

Text Peer Review Prosiding Generative Adversarial Network.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (910kB)

Abstract

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.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	500 Science and Mathematic > 500 Science > 507 Education, Research, Related Topics
Divisions:	Faculty of Engineering & Informatics > Informatics
Depositing User:	Administrator UMN Library
Date Deposited:	10 Jun 2020 07:51
Last Modified:	14 Jan 2022 04:39
URI:	https://kc.umn.ac.id/id/eprint/12623

Actions (login required)

View Item