Implementasi Pendekatan Ensemble Deep Learning untuk Klasifikasi Citra Ilustrasi Asli dan Hasil Generative AI
DOI:
https://doi.org/10.47065/bulletincsr.v6i6.1334Keywords:
Artificial Intelligence; Digital Illustration; Generative AI; Image Classification; Soft Voting EnsembleAbstract
The rapid development of Generative Artificial Intelligence (AI) has increasingly enabled the creation of digital illustrations with high visual similarity to human-created artworks, making identification more difficult and raising challenges related to originality and copyright protection. However, research on Generative AI image detection has largely focused on photographic images or real-world objects, while the classification of digital illustrations with artistic characteristics and high visual similarity remains limited. This study aims to implement and evaluate an automated classification method to distinguish original illustrations from Generative AI-generated illustrations. The proposed approach employs Ensemble Deep Learning with a Soft Voting technique that combines MobileNetV2, ResNet50, and DenseNet121. The modeling process follows the CRISP-DM methodology and is evaluated using 5-Fold Stratified Cross Validation. Internal validation achieved an accuracy of 96.00% and an AUC of 99.06%. In external testing, accuracy reached 87.60% with an AUC of 95.09%, while individual-sample testing achieved an accuracy of 80.00%. The decrease in accuracy on external data indicates challenges in generalizing the model to data with characteristics different from those in the training and validation sets. This study contributes by applying and evaluating a Soft Voting Ensemble for classifying anime- and manga-style digital illustrations through internal validation, external testing, and individual-sample testing. The results indicate that this approach has the potential to distinguish original illustrations from Generative AI-generated illustrations, although further improvements in the model's generalization capability are needed.
Downloads
References
A. Arifin, A. N. Mubiin, B. A. Setyanto, and I. A. Fatahillah, “Analisis Yuridis Hak Cipta Kepada User Atas Karya Hasil Generative Artificial Intelligence Di Indonesia,” At-Tanwir Law Review, pp. 412–427, 2025, doi: https://dx.doi.org/10.31314/atlarev.v5i2.4504.
D. W. M. Sandi, P. E. P. Utomo, and U. Khaira, “Perbandingan EfficientNetV2 Dan MobileNetV3 Pada CNN Untuk Klasifikasi Gambar Asli Dan Gambar AI,” JUSS) Jurnal Sains dan Sistem Informasi, vol. 9, no. 1, 2026, doi: https://doi.org/10.22437/juss.v9i1.58864.
F. Roumpies, G. Spathoulas, and A. Kakarountas, “Synthetically Generated Media, types, detection, and the threat they lurk for users, state and private actors,” Proceedings - 28th Pan-Hellenic Conference on Progress in Computing and Informatics with International Participation, PCI 2024, pp. 431–436, May 2025, doi: 10.1145/3716554.3716835.
Rachmawati, “Kreativitas atau Plagiarisme? Kontroversi AI dalam Seni Bergaya Studio Ghibli,” https://www.kompas.com/jawa-timur/read/2025/04/02/060000488/kreativitas-atau-plagiarisme-kontroversi-ai-dalam-seni-bergaya-studio?page=all. Accessed: Apr. 18, 2026. [Online]. Available: https://www.kompas.com/jawa-timur/read/2025/04/02/060000488/kreativitas-atau-plagiarisme-kontroversi-ai-dalam-seni-bergaya-studio?page=all
A. N. Nafisa, E. N. D. B. Purba, F. A. A. Harahap, and N. A. Putri, “Implementasi Algoritma Convolutional Neural Network Arsitektur Model MobileNetV2 dalam Klasifikasi Penyakit Tumor Otak Glioma, Pituitary dan Meningioma,” Jurnal Teknologi Informasi, Komputer dan Aplikasinya (JTIKA), vol. 5, no. 1, pp. 53–61, 2023, doi: https://doi.org/10.29303/jtika.v5i1.234.
O. V. Putra, M. Z. Mustaqim, and D. Muriatmoko, “Transfer Learning untuk Klasifikasi Penyakit dan Hama Padi Menggunakan MobileNetV2 Transfer Learning for Rice Disease and Pest Classification using MobileNetV2,” vol. 22, pp. 562–575, 2023, doi: https://doi.org/10.33633/tc.v22i3.8516.
A. Agustina, F. Yanto, E. Budianita, I. Iskandar, and F. Syafria, “Klasifikasi Penyakit Tanaman Padi Menggunakan Metode CNN Arsitektur DenseNet-121 Dan Augmentasi Data,” Journal Of Information Systems And Informatics Engineering, vol. 8, no. 1, pp. 124–134, Jun. 2024, doi: 10.35145/joisie.v8i1.4256.
S. A. Hakim et al., “Klasifikasi Citra Generasi Artificial Intelligence Menggunakan Metode Fine Tuning Pada Residual Network AI Generated Image Classification Using Fine Tuning On Residual Network,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 3, pp. 655–666, 2024, doi: 10.25126/jtiik.938118.
Steven Joses, D. Yulvida, and S. Rochimah, “Pendekatan Metode Ensemble Learning untuk Prakiraan Cuaca menggunakan Soft Voting Classifier,” Journal of Applied Computer Science and Technology, vol. 5, no. 1, pp. 72–80, Jun. 2024, doi: 10.52158/jacost.v5i1.741.
M. S. A. Aria, C. Slamet, and M. D. Firdaus, “Klasifikasi Fake dan Real Menggunakan Vision Transformer dan EfficientNet-B0 pada Gambar Asli dan Generatif AI,” SMATIKA JURNAL, vol. 15, no. 01, pp. 179–192, Jun. 2025, doi: 10.32664/smatika.v15i01.1531.
Q. Yun, “Vision Transformers (ViTs) for Feature Extraction and Classification of AI-Generated Visual Designs,” IEEE Access, vol. 13, pp. 69459–69477, 2025, doi: 10.1109/ACCESS.2025.3562130.
J. J. Bird and A. Lotfi, “CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images,” IEEE Access, vol. 12, pp. 15642–15650, 2024, doi: 10.1109/ACCESS.2024.3356122.
D. Maulana, N. S. Azzahrah, R. A. Syach, S. Syauri, M. Syafi’i, and C. Rozikin, “Identifikasi Konten Visual Buatan AI Dengan ResNet Dan Fine-Grained Feature Extraction,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 3S1, pp. 1248–1256, Oct. 2025, doi: 10.23960/jitet.v13i3S1.8056.
N. K. R. Ranupadma, E. M. Dharma, and A. A. I. I. Paramitha, “Implementasi Transfer Learning Dan Augmentasi Pada Model CNN Untuk Meningkatkan Robustness Klasifikasi AI-Generated Image,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 10, no. 2, pp. 2370–2377, 2026, doi: https://doi.org/10.36040/jati.v10i2.17412.
H. R. V. Kaluge, N. Yudistira, and Marji, “Implementasi Resnet-50 Dalam Deteksi Anomali Tekstur Pada Gambar Yang Dihasilkan Oleh AI (Artificial Intelligence),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 10, no. 4, pp. 1–7, Mar. 2026, [Online]. Available: http://j-ptiik.ub.ac.id
M. Shadri, A. Hanafiah, and P. Velusamy, “AI-Generated Image Detection Using Convolutional Neural Network (CNN) Algorithm,” Artificial Intelligence and Language Models, 2026, [Online]. Available: https://acspub.id/index.php/ailm/article/view/4
Arini, M. Azhari, I. I. A. Fitri, and F. Fahrianto, “Performance Analysis of Transfer Learning Models for Identifying AI-Generated and Real Images,” JURNAL TEKNIK INFORMATIKA, vol. 17, no. 2, pp. 139–152, Oct. 2024, doi: https://doi.org/10.15408/jti.v17i2.40453.
I. R. Kurniawan et al., “Pengaruh Penambahan Arsitektur Model dalam Klasifikasi Citra Bencana Alam Menggunakan Ensemble Learning,” JURNAL FASILKOM, vol. 15, no. 2, pp. 280–289, 2025, doi: https://doi.org/10.37859/jf.v15i2.9103.
S. Mildawati and P. T. Prasetyaningrum, “Analisis Peningkatan Performa Convolutional Neural Network Menggunakan Hyperparameter Tuning Dan Ensemble Learning Pada Klasifikasi Citra MRI Tumor Otak,” Rabit?: Jurnal Teknologi dan Sistem Informasi Univrab, vol. 11, no. 2, pp. 4769–4785, Jul. 2026, doi: https://doi.org/10.36341/rabit.v11i2.8341.
A. Rianti, N. W. A. Majid, and A. Fauzi, “CRISP-DM: Metodologi Proyek Data Science,” Prosiding Seminar Nasional Teknologi Informasi dan Bisnis (SENATIB), pp. 107–114, 2023, doi: https://doi.org/10.47701/senatib.v3i1.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi Pendekatan Ensemble Deep Learning untuk Klasifikasi Citra Ilustrasi Asli dan Hasil Generative AI
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Ibni Haziq Pryandara, Yayan Hendrian
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).
