Klasifikasi Motif Batik Nusantara Menggunakan EfficientNetB0 Berbasis Dekstop

Authors

  • wahyu Setyo budi Indonesia
  • Danang Wahyu Widodo Universitas Nusantara PGRI Kediri Indonesia
  • Patmi Kasih Universitas Nusantara PGRI Kediri Indonesia

DOI:

https://doi.org/10.29407/c40g6n68

Abstract

Identifikasi motif batik secara manual masih bergantung pada pengetahuan pengguna dan membutuhkan waktu, padahal kebutuhan pengenalan motif secara cepat diperlukan untuk edukasi budaya dan arsip digital. Penelitian ini membangun aplikasi klasifikasi motif batik nusantara menggunakan EfficientNetB0 dengan pendekatan transfer learning dan implementasi Streamlit. Dataset terdiri atas 21 kelas motif batik dengan pembagian data latih dan data uji. Citra diproses melalui resize, preprocessing EfficientNet, dan augmentasi pada data latih. Model dilatih menggunakan optimizer Adam, categorical crossentropy, early stopping, reduce learning rate, dan model checkpoint. Hasil pengujian menunjukkan accuracy 66,67 persen, precision macro 71,94 persen, recall macro 66,67 persen, dan F1-score macro 66,29 persen. Aplikasi dapat menerima gambar batik, kemudian menampilkan motif terdeteksi, confidence, deskripsi motif, serta top-5 prediksi. Hasil ini menunjukkan bahwa aplikasi mampu mendukung identifikasi awal motif batik secara praktis.

Keywords:

Batik Nusantara, EfficientNetB0, Klasifikasi Citra, Transfer Learning

##plugins.themes.default.displayStats.downloads##

##plugins.themes.default.displayStats.noStats##

References

[1] A. Muriagista and D. Kurniadi, "IMPLEMENTASI ARSITEKTUR RESNET50 PADA KLASIFIKASI MOTIF BATIK INDONESIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)," 2025.

[2] S. B. Santosa, A. R. Chrismanto, and B. Susanto, "Classification of Batik Keraton motifs using ResNet-50 fine-tuning architecture," AITI, vol. 23, no. 1, pp. 46-60, Feb. 2026, doi: 10.24246/aiti.v23i1.46-60.

[3] Yann Lecun, Yoshua Bengio, and Geoffrey Hinton, "NCBI Literature Resources." [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/26017442/.

[4] N. H. Harani, C. Prianto, and M. Hasanah, "Deteksi Objek Dan Pengenalan Karakter Plat Nomor Kendaraan Indonesia Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Python," 2019.

[5] R. Pajes, Detection of Corn Leaf Diseases using Convolutional Neural Network with OpenMP Implementation, 2020, doi: 10.1109/HNICEM51456.2020.9400004.

[6] D. Dhelviana, T. Amelia, J. Sulaksono, and D. W. Widodo, "Sistem Pendeteksi Kekerasan Berbasis Cnn (Convolutional Neural Network)," 2023.

[7] L. Dwi Anggraini, U. Mahdiyah, and R. Wulanningrum, "Pengujian Simple CNN Dengan Arsitektur LeNet5 Pada Penyakit Daun Jagung," 2025.

[8] P. Arsitektur et al., "Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi) 1626," 2024.

[9] M. R. Andrianto, F. Firdaus, E. Pratama, R. S. Purnama, and E. Y. Puspaningrum, "Klasifikasi Motif Batik Tradisional Mataraman Menggunakan CNN," 2025.

[10] M. M. A. Wona et al., "Klasifikasi Batik Indonesia Menggunakan Convolutional Neural Network (CNN)," Jurnal Rekayasa Teknologi Informasi (JURTI), vol. 7, no. 2, pp. 172-179, 2023.

Downloads

Published

2026-07-20

Issue

Vol. 10 No. 1 (2026): Prosiding Seminar Nasional Inovasi Teknologi Tahun 2026

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Copyright on any article is retained by the author(s).
  2. The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
  3. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  4. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License

How to Cite

Klasifikasi Motif Batik Nusantara Menggunakan EfficientNetB0 Berbasis Dekstop. (2026). Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 10(1), 855-862. https://doi.org/10.29407/c40g6n68