Klasifikasi Motif Batik menggunakan metode Deep Convolutional Neural Network dengan Data Augmentation

Samuel Febrian Tumewu, Djoni Haryadi Setiabudi, Indar Sugiarto

Abstract


Related researches before used Convolutional Neural Network (CNN) VGG to classify batik motif which limited only on geometrical pattern and implemented 2 augmentation consist of scale and rotation. Therefore, this research uses CNN Residual Network (Resnet) with 4 augmentation technique on both geometrical and non geometrical batik pattern.

This research use (Resnet) as a main architecture of CNN to identify batik pattern. Batik motives for this research are from geometric category which is ceplok, kawung, lereng, nitik, and parang. And from nongeometri category are semen and lunglungan. Furthermore, the dataset will be applied scale, random erase, rotation, and flip augmentation to increase the quantity and variation of batik dataset.

The results show that CNN Resnet with data augmentation on training dataset gives accuracy up to 84,52% on Resnet-18 and 81,90% on Resnet-50. furthermore, rotation augmentation adds 4,06%, random erase augmentation adds 9,38%, scale augmentation adds 6,52%, and flip augmentation adds 8,58% on accuracy

Keywords


Image Classification; Data Augmentation; Convolutional Neural Network; Resnet; Batik Classification

Full Text:

PDF

References


Agastya, I. M. A., & Setyanto, A. 2018. Classification of Indonesian Batik Using Deep Learning Techniques and Data Augmentation. 2018 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE). doi: 10.1109/icitisee.2018.8720990.

Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. 2019. Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 113-123).

Goodfellow, I., Bengio, Y., & Courville, A. 2017. Deep learning. Cambridge, MA: MIT Press.

Gultom, Y., Arymurthy, A. M., & Masikome, R. J. 2018. Batik Classification using Deep Convolutional Network Transfer Learning. Jurnal Ilmu Komputer Dan Informasi, 11(2), 59. doi: 10.21609/jiki.v11i2.507.

He, K., Zhang, X., Ren, S., & Sun, J. 2016. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: 10.1109/cvpr.2016.90.

Karimah, F. U., & Harjoko, A. 2017. Classification of Batik Kain Besurek Image Using Speed Up Robust Features (SURF) and Gray Level Co-occurrence Matrix (GLCM). Communications in Computer and Information Science Soft Computing in Data Science, 81–91. doi: 10.1007/978-981-10-7242-0_7.

Li, F. F., Johnson, J., Yeung, S. 2019. CS231n: Convolutional neural networks for visual recognition. University Lecture.

Minarno, A. E., Maulani, A. S., Kurniawardhani, A., Bimantoro, F., & Suciati, N. 2018. Comparison of Methods for Batik Classification Using Multi Texton Histogram. TELKOMNIKA (Telecommunication Computing Electronics and Control), 16(3), 1358. doi: 10.12928/telkomnika.v16i0.7376.

Nurhaida, I., Noviyanto, A., Manurung, R., & Arymurthy, A. M. 2015. Automatic Indonesians Batik Pattern Recognition Using SIFT Approach. Procedia Computer Science, 59, 567–576. doi: 10.1016/j.procs.2015.07.547.

Paluseri, D. D. 2018. Penetapan warisan budaya takbenda Indonesia tahun 2018. Jakarta: Direktorat Warisan dan Diplomasi Budaya Direktorat Jenderal Kebudayaan Kementerian Pendidikan dan Kebudayaan.

Redaksi CNBC Indonesia. 2019, October 2. Jokowi: UNESCO Mulai Evaluasi Pengakuan Batik Warisan Dunia. Retrieved November 13, 2019, from https://www.cnbcindonesia.com/news/20191002142847-4-103878/jokowi-unesco-mulai-evaluasi-pengakuan-batik-warisan-dunia.

Shorten, C., & Khoshgoftaar, T. M. 2019. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(1). doi: 10.1186/s40537-019-0197-0.

Suryanto. 2009, October 2. Batik Indonesia Resmi Diakui UNESCO. Retrieved November 22, 2019, from https://www.antaranews.com/berita/156389/batik-indonesia-resmi-diakui-unesco.

Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. 2017. Random erasing data augmentation. arXiv preprint arXiv:1708.04896.


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :