Identifikasi Objek Pada Citra Menggunakan Convolutional Neural Networks

Obi Agustian; Ari Syaripudin

doi:10.54914/jit.v12i2.2767

Penulis

Obi Agustian Universitas Pamulang
Ari Syaripudin Universitas Pamulang

DOI:

https://doi.org/10.54914/jit.v12i2.2767

Kata Kunci:

Gambar Anime, Gambar Buatan AI, Klasifikasi Biner, ResNet50, Seniman

Abstrak

Perkembangan Artificial Intelligence (AI) dalam membuat konten berupa gambar kini sudah dapat menyamai hasil karya para seniman lukis digital, terkhusus lukisan dengan art-style anime, sehingga suatu gambar sangat sulit untuk dibedakan siapa pembuatnya. Perkembangan yang sangat cepat ini belum dapat diterima secara umum. Banyak orang yang menolak gambar buatan AI, baik dari para seniman atau pun para penikmat seni lukis. Hal tersebut sering kali memicu perdebatan terkait asal suatu gambar, atau tuduhan bahwa suatu karya merupakan gambar buatan AI, yang berujung menjadi sebuah permasalahan. Penelitian ini mengimplementasikan teknik identifikasi objek yang terbatas hanya pada domain seni digital untuk membedakan fitur-fitur visual spesifik yang dihasilkan oleh algoritma AI dan seniman manusia, dengan hasil berupa persentase kemungkinan kelas dari gambar yang diberikan. Hasil persentase tersebut dapat digunakan sebagai bahan pertimbangan dalam menilai kelas suatu gambar. Model dibuat dengan menerapkan metode Fine-Tuning terhadap model pre-trained ResNet50, kemudian dilatih menggunakan dataset terbaru. Dataset berasal dari dua repository di Hugging Face, dengan nama dataset "danbooru2025" dan "pixiv-niji-journey". Setiap kelas akan dibuat memiliki 12500 sampel gambar. Pengujian terhadap model menunjukkan nilai accuracy mencapai 95.64% dan nilai F1-Score mencapai 0.9570. Hasil pengujian tersebut menunjukkan bahwa model dapat mengidentifikasi gambar buatan AI dan Seniman dengan seimbang dan sangat baik.

Unduhan

Data unduhan belum tersedia.

Referensi

Y. Hong and J. Zhang, “WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection,” arXiv preprint arXiv:2402.11843, Feb. 2024, [Online]. Available: http://arxiv.org/abs/2402.11843

K. Sudhakar, R. Vadivel, S. Sarumathi, and S. Manjunatha, Intelligent Systems: Bridging Machine Learning, Deep Learning and Natural Language Processing. Leilani Katie Publication, 2024. Accessed: Feb. 24, 2026. [Online]. Available: https://books.google.co.id/books?id=jLU6EQAAQBAJ

K. Sharifani and M. Amini, “Machine learning and deep learning: A review of methods and applications,” World Information Technology and Engineering Journal, vol. 10, no. 07, pp. 3897–3904, 2023, Accessed: Feb. 24, 2026. [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4458723

N. Anantrasirichai, F. Zhang, and D. Bull, “Advances in artificial intelligence: a review for the creative industries,” Artif. Intell. Rev., vol. 59, no. 3, p. 89, 2026, doi: 10.1007/s10462-026-11494-w.

I. D. Mienye and T. G. Swart, “A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications,” Information (Switzerland), vol. 15, no. 12, Dec. 2024, doi: 10.3390/info15120755.

H. H. Jiang et al., “AI Art and its Impact on Artists,” in AIES 2023: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, Association for Computing Machinery, Inc, Aug. 2023, pp. 363–374. doi: 10.1145/3600211.3604681.

K. Roose, “AI-Generated Art Won a Prize. Artists Aren’t Happy.-The New York Times,” The New York Times, Sep. 2, 2022.

C. Zhu, X. Zhang, Y. Sun, C.-C. Chang, and I. Echizen, “AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era,” in Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media, in DFF ’25. New York, NY, USA: Association for Computing Machinery, 2025, pp. 45–54. doi: 10.1145/3746265.3759666.

S. Yan et al., “A Sanity Check for AI-generated Image Detection,” arXiv preprint arXiv:2406.19435, Feb. 2025, [Online]. Available: http://arxiv.org/abs/2406.19435

D. C. Epstein, I. Jain, O. Wang, and R. Zhang, “Online Detection of AI-Generated Images,” arXiv preprint arXiv:2310.15150, Oct. 2023, [Online]. Available: http://arxiv.org/abs/2310.15150

S. W. Kusuma, F. Natalia, C. S. Ko, and S. Sudirman, “Detection of AI-generated anime images using deep learning,” ICIC Express Letters, Part B: Applications, vol. 15, no. 3, pp. 295–301, Mar. 2024, doi: 10.24507/icicelb.15.03.295.

Z. Wang et al., “A Comprehensive Survey on Data Augmentation,” arXiv preprint arXiv:2405.09591, Oct. 2025, [Online]. Available: http://arxiv.org/abs/2405.09591

S. Fabbrizzi, S. Papadopoulos, E. Ntoutsi, and I. Kompatsiaris, “A Survey on Bias in Visual Datasets,” arXiv preprint arXiv:2107.07919, Jun. 2022, [Online]. Available: http://arxiv.org/abs/2107.07919

U. Michelucci and F. Venturini, “Best Practices for Machine Learning Experimentation in Scientific Applications,” arXiv preprint arXiv:2511.21354, Nov. 2025, [Online]. Available: http://arxiv.org/abs/2511.21354

C. Hastings Blow, L. Qian, C. Gibson, P. Obiomon, and X. Dong, “Data augmentation via diffusion model to enhance AI fairness,” Front. Artif. Intell., vol. 8, 2025, doi: 10.3389/frai.2025.1530397.

I. Werdiningsih, D. C. R. Novitasari, and D. Z. Haq, Pengelolaan Data Mining dengan Pemrograman Matlab. Airlangga University Press, 2022. Accessed: Feb. 24, 2026. [Online]. Available: https://books.google.co.id/books?id=CgOdEAAAQBAJ

D. Chicco and G. Jurman, “The ABC recommendations for validation of supervised machine learning results in biomedical sciences,” Front. Big Data, vol. 5, 2022, doi: 10.3389/fdata.2022.979465.

J. Camacho, “A Set of Rules for Model Validation,” J. Chemom., vol. 40, no. 2, 2026, doi: 10.1002/cem.70110.

X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, Apr. 2024, doi: 10.1007/s10462-024-10721-6.

M. Miceli, T. Yang, L. Naudts, M. Schuessler, D. Serbanescu, and A. Hanna, “Documenting computer vision datasets: An invitation to reflexive data practices,” in FAccT 2021 - Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. New York, NY, USA: Association for Computing Machinery, Inc, Mar. 2021, pp. 161–172. doi: 10.1145/3442188.3445880.

R. Jafari, Hands-On Data Preprocessing in Python: Learn how to effectively prepare data for successful data analytics. Packt Publishing, 2022. Accessed: Feb. 24, 2026. [Online]. Available: https://books.google.co.id/books?id=H6lVEAAAQBAJ

A. Stando, M. Cavus, and P. Biecek, “The Effect of Balancing Methods on Model Behavior in Imbalanced Classification Problems,” arXiv preprint arXiv:2307.00157, Jun. 2023, [Online]. Available: http://arxiv.org/abs/2307.00157

B. Mandal, A. Okeukwu, and Y. Theis, “Masked Face Recognition using ResNet-50,” arXiv preprint arXiv:2104.08997, Apr. 2021, [Online]. Available: http://arxiv.org/abs/2104.08997

A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” arXiv preprint arXiv:1912.01703, Dec. 2019, [Online]. Available: http://arxiv.org/abs/1912.01703

J. Ansel et al., “PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation,” in Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Vol. 2. New York, NY, USA: Association for Computing Machinery, Apr. 2024, pp. 929–947. doi: 10.1145/3620665.3640366