Comparative Analysis of Model Architectures Using Transfer Learning Approach in Convolutional Neural Networks for Traditional Ulos Fabric Classification

Taufik Abdullah; Kana Saputra S; Hermawan Syahputra; Zulfahmi Indra; Dinda Kartika

doi:10.59934/jaiea.v4i2.719

Authors

Taufik Abdullah Ilmu Komputer, Universitas Negeri Medan
Kana Saputra S Ilmu Komputer, Universitas Negeri Medan
Hermawan Syahputra Ilmu Komputer, Universitas Negeri Medan
Zulfahmi Indra Ilmu Komputer, Universitas Negeri Medan
Dinda Kartika Matematika, Universitas Negeri Medan

DOI:

https://doi.org/10.59934/jaiea.v4i2.719

Keywords:

Accuracy, Classification, Inception-V3, Transfer Learning, Ulos Motifs

Abstract

Ulos cloth is a traditional woven fabric of the Batak tribe in North Sumatra, valued for its aesthetic and symbolic significance in various ceremonies. The diversity of ulos motifs presents challenges in preservation due to their unique patterns and functions. This study aims to develop an accurate method for classifying ulos motifs using Transfer Learning on Convolutional Neural Network (CNN) architectures. Five popular models—VGG16, VGG19, MobileNetV3, Inception-V3, and EfficientNetV2—were evaluated on a dataset of 962 ulos images across six motif categories.The results show that Inception-V3 outperformed other models with an average validation accuracy of 98.13% and the lowest loss of 5.67%. Inception-V3 also demonstrated superior generalization, achieving the highest K-fold validation accuracy, while VGG16 and VGG19 exhibited overfitting at higher learning rates. Two-way ANOVA analysis confirmed significant performance differences among the models and highlighted the interaction between model type and training methods. This research recommends Inception-V3 as the optimal model for ulos motif classification, offering an efficient and reliable tool to support cultural preservation through advanced image recognition technology.

Downloads

Download data is not yet available.

References

J. Wahyudi and I. Maulida, “Pengenalan Pola Citra Kain Tradisional Menggunakana GLCM dan KNN,” JTIULM, vol. 4, no. 2, pp. 43–48, 2019, doi: https://doi.org/10.20527/jtiulm.v4i2.37.

B. Siregar, I. P. S. Panggabean, Fahmi, and A. Hizriadi, “Classification of traditional ulos of Batak Toba ssing probabilistic neural network,” in Journal of Physics: Conference Series, IOP Publishing Ltd, May 2021, pp. 1–9. doi: 10.1088/1742-6596/1882/1/012131.

E. R. L. Tinambunan, “Ulos Batak Toba: Makna Religi dan Implikasinya pada Peradaban dan Estetika,” FORUM Filsafat dan Teologi, vol. 52, no. 2, pp. 122–142, Oct. 2023, doi: 10.35312/forum.v52i2.583.

D. Esterlina Br Jabat, L. Yanti Sipayung, and K. Raih Syahputra Dakhi, “Penerapan Algoritma Recurrent Neural Networks (RNN) Untuk Klasifikasi Ulos Batak Toba,” SNISTIK : Seminar Nasional Inovasi Sains Teknologi Informasi Komputer, vol. 1, no. 2, pp. 3025–8715, 2024.

D. H. Manurung, I. M. Lattu, and R. Tulus, “Struktur Cosmos Masyarakat Batak dalam Simbol Ulos,” Anthropos: Jurnal Antropologi Sosial dan Budaya (Journal of Social and Cultural Anthropology), vol. 6, no. 1, p. 31, Apr. 2020, doi: 10.24114/antro.v6i1.16603.

R. Mawan, “Klasifikasi motif batik menggunakan convolutional neural network,” JNANALOKA, vol. 1, no. 1, pp. 45–50, 2020, doi: 10.36802/jnanaloka.

A. A. Prahartiningsyah and T. B. Kurniawan, “Pengenalan Pola Angka Menggunakan Pendekatan Optimisasi Sistem Kekebalan Buatan (Artificial Immune System),” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 3, p. 856, Jul. 2021, doi: 10.30865/mib.v5i3.2997.

N. K. Qudsi, R. A. Asmara, and A. R. Syulistyo, “Identifikasi Citra Tulisan Tangan Digital Menggunakan Convolutional Neural Network (CNN),” 2019.

M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 1–41, Aug. 2023, doi: 10.3390/computers12080151.

A. F. Siregar and T. Mauritsius, “Ulos fabric classification using android-based convolutional neural network,” International Journal of Innovative Computing, Information and Control, vol. 17, no. 3, pp. 753–766, 2021, doi: 10.24507/ijicic.17.03.753.

Anhar and R. A. Putra, “Perancangan dan Implementasi Self-Checkout System pada Toko Ritel menggunakan Convolutional Neural Network (CNN),” ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 11, no. 2, pp. 466–478, Apr. 2023, doi: 10.26760/elkomika.v11i2.466.

A. E. Wijaya, W. Swastika, and O. H. Kelana, “Implementasi Transfer Learning Pada Convolutional Neural Network Untuk Diagnosis Covid-19 Dan Pneumonia Pada Citra X-Ray,” SAINSBERTEK Jurnal Ilmiah Sains & Teknologi, vol. 2, no. 1, 2021.

D. Dais, İ. E. Bal, E. Smyrou, and V. Sarhosis, “Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning,” Autom Constr, pp. 1–18, May 2021, doi: 10.1016/j.autcon.2021.103606.

H. Noprisson, E. Ermatita, A. Abdiansah, V. Ayumi, M. Purba, and H. Setiawan, “Fine-Tuning Transfer Learning Model In Woven Fabric Pattern Classification,” International Journal of Innovative Computing, Information and Control, vol. 18, no. 6, pp. 1885–1894, 2022, doi: 10.24507/ijicic.18.06.1885.

D. S. Prashanth, R. V. K. Mehta, and N. Sharma, “Classification of Handwritten Devanagari Number - An analysis of Pattern Recognition Tool using Neural Network and CNN,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 2445–2457. doi: 10.1016/j.procs.2020.03.297.

S. Sennan, D. Pandey, Y. Alotaibi, and S. Alghamdi, “A Novel Convolutional Neural Networks Based Spinach Classification and Recognition System,” Computers, Materials and Continua, vol. 73, no. 1, pp. 343–361, 2022, doi: 10.32604/cmc.2022.028334.

A. Julianto, A. Sunyoto, D. Ferry, and W. Wibowo, “Optimasi Hyperparameter Convolutional Neural Network Untuk Klasifikasi Penyakit Tanaman Padi,” TEKNIMEDIA, vol. 3, no. 2, pp. 98–105, 2022, doi: https://doi.org/10.46764/teknimedia.v3i2.77.

I. I. Daqiqi, MACHINE LEARNING: Teori, Studi Kasus dan Implementasi Menggunakan Python. UR PRESS, 2021. doi: 10.5281/zenodo.5113507.