Implementation of Transfer Learning on AlexNet for Yogyakarta Batik Motif Classification

Authors

  • (*) Angela Gracia Cahyaningtyas,  Informatika, Universitas Kristen Duta Wacana
  • Sri Suwarno,  Informatika, Universitas Kristen Duta Wacana
  • Budi Susanto,  Informatika, Universitas Kristen Duta Wacana

(*) Corresponding Author

DOI:

https://doi.org/10.21460/jutei.2025.92.432

Keywords:

AlexNet, Transfer Learning, SGD, Adam, Max Pooling, Average Pooling, Classifier, Batik Yogyakarta

Abstract

This study discusses the implementation of Transfer Learning using the AlexNet architecture for classifying Yogyakarta Batik motifs, specifically Kawung, Parang, and Truntum. The dataset consists of 1,110 batik images that underwent preprocessing, augmentation, and data splitting. The research was conducted in two main experimental scenarios: applying Average Pooling and Max Pooling with a more complex classifier, and training the model without additional pooling layers using a simpler classifier. Furthermore, the experiments compared the model’s performance across different frozen layers and two optimizers (Adam and SGD). The results show that the best configuration was obtained using the SGD optimizer with Average Pooling and three frozen layers, achieving a test accuracy of 99.10%. In contrast, the Adam optimizer tended to produce lower and less stable performance. Experiments without pooling also reached high accuracy, but were less optimal than those with pooling. Therefore, this study demonstrates that the choice of pooling technique, classifier complexity, frozen layers, and optimizer plays a crucial role in achieving optimal performance of AlexNet for Batik classification.

References

I. Goodfellow, Y. Bengio, dan A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016.

S. Achjadi, Batik: Motif dan Filosofi. Yogyakarta: Penerbit Andi, 2001.

S. Achjadi, Batik: Sejarah dan Perkembangannya. Jakarta: Penerbit Kompas, 2010.

I. Aziz, Ensiklopedia Batik Yogyakarta. Yogyakarta: Penerbit LKi, 2010.

G. M. Darmokusumo, Batik Yogyakarta dan Perjalanannya dari Masa ke Masa. Yogyakarta: Penerbit LKi, 2015.

A. Kusrianto dan B. R. W. Rini, Batik: Falsafah, Makna dan Kegunaan. Yogyakarta: Penerbit Kanisius, 2013.

D. Meranggi, R. Santoso, dan N. Indriastuti, “Classification of batik motifs using convolutional neural networks,” J. Inf. Technol., vol. 13, no. 2, hal. 105–115, 2020.

D. Meranggi, A. Yulianto, dan F. Kharisma, “Klasifikasi motif batik menggunakan CNN dengan penerapan augmentasi data,” J. Informatika, vol. 10, no. 2, hal. 45–54, 2020.

A. Priyanto dan S. Budiharjo, “Batik as a cultural heritage of Indonesia: Unique patterns and motifs,” Cultural Studies J., vol. 9, no. 1, hal. 45–60, 2021.

W. Rawat dan Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Comput. Appl., vol. 30, no. 2, hal. 325–338, 2017.

M. Shafique, A. Khan, dan M. Hussain, “AlexNet: A comprehensive review,” J. Comput. Sci. Technol., vol. 18, no. 3, hal. 275–290, 2018.

C. Shorten dan T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” J. Big Data, vol. 6, no. 1, hal. 1–48, 2019.

A. Surya dan I. Fikri, “Efficient classification of batik motifs using AlexNet,” Int. J. Comput. Appl., vol. 176, no. 12, hal. 24–31, 2020.

J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, dan M. Hein, “Transfer learning via the selective fine-tuning of convolutional neural networks,” dalam Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 3, hal. 1120–1127, 2014.

A. Priyanto, H. Setyawan, dan A. Rahayu, “Penerapan AlexNet untuk klasifikasi motif batik menggunakan transfer learning,” J. Teknol. Inf., vol. 12, no. 1, hal. 10–20, 2021.

M. A. Shafique, H. K. Kwon, dan H. Kim, “AlexNet for image classification: A comprehensive review,” Int. J. Comput. Appl., vol. 180, no. 9, hal. 31–36, 2018.

M. Surya dan R. Dewi, “Efisiensi waktu pelatihan dan akurasi pada klasifikasi gambar menggunakan AlexNet,” J. Ilmiah Komput., vol. 15, no. 3, hal. 100–110, 2020.

J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, dan H. Lipson, “Transfer learning by swapping neuron contributions,” dalam Adv. Neural Inf. Process. Syst., hal. 1–9, 2014.

R. A. Prasetyo dan S. Budiharjo, “Studi pola Batik Kawung: Pola geometris dalam karya seni,” J. Seni Rupa, vol. 5, no. 2, hal. 90–95, 2017.

D. Rahmawati dan L. Indriastuti, “Karakteristik motif Batik Tambal: Antara tradisi dan modernitas,” J. Ilmu Budaya, vol. 3, no. 1, hal. 35–45, 2019.

B. W. Santoso dan R. Wardhani, “Motif Batik Parang: Sejarah dan makna,” J. Pendidik. Seni, vol. 8, no. 1, hal. 50–60, 2020.

N. Ardini dan A. Purnomo, “Motif Batik Truntum: Representasi keindahan dan simbolisme,” J. Desain Komunikasi Visual, vol. 6, no. 1, hal. 25–35, 2021.

Downloads

Published

2025-10-24

How to Cite

[1]
A. G. Cahyaningtyas, S. Suwarno, and B. Susanto, “Implementation of Transfer Learning on AlexNet for Yogyakarta Batik Motif Classification”, JUTEI, vol. 9, no. 2, pp. 93–102, Oct. 2025.

Most read articles by the same author(s)

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.