Segmentasi Citra Wayang Kulit Pandawa Berkompleksitas Visual Tinggi Menggunakan Model U-Net Berbasis Convolutional Neural Network
-
Krisna Refiansyah
*
Universitas Mercu Buana Yogyakarta, Yogyakarta,
Indonesia
- Mutaqin Akbar Universitas Mercu Buana Yogyakarta, Yogyakarta, Indonesia (*) Corresponding Author
Abstract
Shadow puppetry (wayang kulit) is one of Indonesia's cultural heritages with significant historical and artistic value. The complexity of digital image backgrounds in wayang kulit poses a major challenge in automatic segmentation, particularly due to lighting variations, intricate carving (tatahan) details, and the limitations of conventional methods in handling high visual variability. This study aims to implement a U-Net architecture based on Convolutional Neural Network (CNN) for segmenting images of Pandawa shadow puppet characters encompassing five main characters: Puntadewa, Janaka, Werkudara, Nakula, and Sadewa. The dataset consists of 1,500 independently collected shadow puppet images with ground truth masks divided into 1,093 training, 157 validation, and 250 test data. The U-Net model was trained using the Adam optimizer with an initial learning rate of 1×10⁻⁴, combined Binary Cross-Entropy and Dice Loss function, and 128×128 pixel input size. Early stopping and automatic learning rate adjustment via ReduceLROnPlateau were applied to optimize training and prevent overfitting throughout the learning process. The model achieved Accuracy 95.8%, AUC 98.6%, Dice Coefficient 91.9%, IoU 86.9%, Precision 91.5%, and Recall 95.0% on 250 test data. Previous studies on wayang kulit have been limited to image classification, while U-Net applications have been predominantly found in medical and satellite domains, making this study a novel contribution that addresses an existing research gap and supports the digitalization of Indonesian cultural heritage. The contribution of this study is to provide the first deep learning-based image segmentation model specifically designed to automatically separate Pandawa wayang kulit silhouettes from their backgrounds, demonstrating the effectiveness of U-Net architecture on cultural heritage objects with high visual complexity, and establishing a segmentation performance baseline for the Indonesian visual cultural heritage domain that can serve as a reference for future wayang kulit digitalization system development.
Downloads
References
N. E. Imandayanti, H. E. Wahanani, and A. M. Rizki, “Klasifikasi Jenis Wayang menggunakan Convolutional Neural Network (CNN) dan Optimasi Adaptive Moment Estimation (ADAM),” KERNEL, vol. 5, no. 2, pp. 64–71, Apr. 2025, doi: 10.31284/j.kernel.2024.v5i2.6862.
R. N. Sapphira, “Titik Temu Tradisi dan Modernisasi: Adaptasi Kultural Pelestarian Wayang Kulit di Era Digital,” Anthropos: Jurnal Antropologi Sosial dan Budaya (Journal of Social and Cultural Anthropology), vol. 8, no. 2, pp. 75–92, Jan. 2023, doi: https://doi.org/10.24114/antro.v8i2.41500.
M. U. Nasution, L. S. Harahap, and F. Syakbani, “Tinjauan Metode Pengolahan Citra Digital untuk Deteksi Objek Otomatis,” JITET, vol. 13, no. 3, Jul. 2025, doi: 10.23960/jitet.v13i3.7135.
D. Prayogi, S. R. Lubis, M. A. Rizko, and A. G. Suteja, “Optimalisasi Segmentasi Citra Digital Metode Canny Edge Detection dan Thresholding,” RIGGS, vol. 4, no. 2, pp. 6334–6339, Jul. 2025, doi: 10.31004/riggs.v4i2.1613.
P. Purwono, A. Ma’arif, W. Rahmaniar, H. I. K. Fathurrahman, A. Z. K. Frisky, and Q. M. U. Haq, “Understanding of Convolutional Neural Network (CNN): A Review,” IJRCS, vol. 2, no. 4, pp. 739–748, Jan. 2023, doi: 10.31763/ijrcs.v2i4.888.
A. H. Nasrullah and H. Annur, “Implementasi Metode Convolutional Neural Network Untuk Identifikasi Citra Digital Daun,” Mib, vol. 7, no. 2, p. 726, Apr. 2023, doi: 10.30865/mib.v7i2.5962.
W. Nurhasanah, W. Witanti, and H. Ashaury, “Klasifikasi Citra Pada Wayang Kulit Menggunakan Convolutional Neural Network,” Ceritaj, vol. 11, no. 1, pp. 112–119, Feb. 2025, doi: 10.33050/cerita.v11i1.3700.
F. A. J. Handani, E. Wijayanti, and R. Fiati, “Implementation of Convolutional Neural Network Method in Classifying Pandawa Shadow Puppets,” J. Tek. Inform. (JUTIF), vol. 6, no. 1, pp. 211–219, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.1851.
A. S. S. Pratama, A. P. Wibawa, and A. N. Handayani, “Convolutional Neural Network (CNN) untuk Menentukan Gagrak Wayang Kulit,” Mnemonic, vol. 5, no. 2, pp. 98–102, Aug. 2022, doi: 10.36040/mnemonic.v5i2.4671.
N. K. Nisa’, E. Evanita, and A. A. Riadi, “Klasifikasi Wayang Kulit Kurawa Menggunakan Algoritma CNN,” Jurnal Pendidikan dan Teknologi Indonesia, vol. 5, no. 6, pp. 1799–1808, Jul. 2025, doi: 10.52436/1.jpti.856.
F. G. Setiawan, E. M. Dharma, and N. W. Utami, “Klasifikasi Tokoh Wayang Kulit dalam Cerita Mahabharata Versi Pewayangan Jawa Menggunakan Convolutional Neural Network (CNN) Berbasis ConvNeXt-Small,” JATI, vol. 10, no. 2, pp. 2378–2384, Mar. 2026, doi: 10.36040/jati.v10i2.17413.
E. Ermatita and W. Ningsih, “Arsitektur U-Net Pada Segmentasi Citra Paru Untuk Mendeteksi Nodul Paru,” Jurnal Pendidikan dan Teknologi Indonesia, vol. 5, no. 1, pp. 123–130, Jan. 2025, doi: 10.52436/1.jpti.600.
P. H. Setadewa, K. Y. E. Aryanto, and L. J. E. Dewi, “Segmentasi Bangunan Perkotaan pada Citra Satelit Beresolusi Tinggi: CNN, U-Net (VGG16), dan DeepLabV3+ (ResNet-50),” STORAGE: Jurnal Ilmiah Teknik dan Ilmu Komputer, vol. 4, no. 4, pp. 337–347, Nov. 2025, doi: 10.55123/storage.v4i4.6552.
I. N. Fahrudin and M. Akbar, “Image Segmentation of Yogyakarta Batik Pattern Using SegNet,” J. Ris. Inform., vol. 8, no. 2, pp. 309–320, Mar. 2026, doi: 10.34288/jri.v8i2.491.
S. Ashillah, S. A. Gulo, Y. Rahmi, and D. Y. Niska, “Implementasi Algoritma Pengolahan Citra Digital untuk Perbaikan Kualitas Gambar,” Siskom-KB, vol. 8, no. 3, pp. 274–280, May 2025, doi: 10.47970/siskom-kb.v8i3.823.
M. Akbar, A. Witanti, and I. Susilawati, “GPU Accelerated Fuzzy C-Means (FCM) Color Image Segmentation,” Compiler, vol. 8, no. 2, Oct. 2019, doi: 10.28989/compiler.v8i2.455.
F. N. Fajri, M. Dzikrillah, and A. Khairi, “Digital Fish Image Segmentation Using U-Net for Shape Feature Extraction,” JTOS, vol. 7, no. 2, pp. 195–201, Dec. 2024, doi: 10.36378/jtos.v7i2.3968.
M. A. Djohar et al., “Liver Segmentation Using Convolutional Neural Network Method with U-Net Architecture,” JITE, vol. 6, no. 1, pp. 221–234, Jul. 2022, doi: 10.31289/jite.v6i1.6751.
D. Gunawan and H. Setiawan, “Convolutional Neural Network dalam Analisis Citra Medis,” Konstelasi, vol. 2, no. 2, pp. 380–386, Dec. 2022, doi: 10.24002/konstelasi.v2i2.5367.
A. F. Ramdhani, Y. Widhiyasana, and S. Rachmat, “Perbandingan Model U-Net dan ELU-Net untuk Segmentasi Semantik Citra Medis Kanker Pankreas,” JNTETI, vol. 14, no. 1, pp. 48–50, Feb. 2025, doi: 10.22146/jnteti.v14i1.15262.
D. W. Ayu and G. A. Pradipta, “Analisis Performansi Parameter pada Arsitektur U-Net untuk Segmentasi Nukleus pada Citra Kanker Serviks,” JSI, vol. 18, no. 2, pp. 131–138, May 2024, doi: 10.30864/jsi.v18i2.607.
T. Sulistyorini, E. Sova, N. Sofie, and R. I. Napitupulu, “Penerapan Hyperparameter Convolutional Neural Network (CNN) dalam Membangun Model Segmentasi Gambar Menggunakan Arsitektur U-Net dengan TensorFlow,” Infokom, vol. 28, no. 2, pp. 112–121, 2023, doi: 10.35760/ik.2023.v28i2.6959.
D. W. Putranto, A. Sunyoto, and A. Nasiri, “Pemanfaatan Deep Learning untuk Segmentasi Paru-Paru dari Citra X-Ray Dada,” Teknimedia, vol. 4, no. 2, pp. 144–150, Dec. 2023, doi: 10.46764/teknimedia.v4i2.114.
S. B. Boly and M. Akbar, “Segmentasi Citra Sel Darah Menggunakan Convolutional Neural Network,” Restikom, vol. 6, no. 2, pp. 390–398, Aug. 2024, doi: 10.52005/restikom.v6i2.336.
Y. Z. Malih and M. Akbar, “Klasifikasi dan Segmentasi Motif Batik Yogyakarta Menggunakan Convolutional Neural Network,” JATI, vol. 10, no. 1, pp. 1511–1518, Jan. 2026, doi: 10.36040/jati.v10i1.17061.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Segmentasi Citra Wayang Kulit Pandawa Berkompleksitas Visual Tinggi Menggunakan Model U-Net Berbasis Convolutional Neural Network
Copyright (c) 2026 Krisna Refiansyah, Mutaqin Akbar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- 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.
- 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 (Refer to The Effect of Open Access).
