Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Informatika Terpadu
Obi Agustian
Universitas Pamulang
Computer Science & IT Decision Sciences, Operations Research & Management Education

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Identifikasi Objek Pada Citra Menggunakan Convolutional Neural Networks Obi Agustian; Ari Syaripudin
Jurnal Informatika Terpadu Vol 12 No 2 (2026): September, 2026 (On Going)
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jit.v12i2.2767

Abstract

The advancement of Artificial Intelligence (AI) in generating image-based content has reached a level comparable to that of digital artists, particularly in anime-style artwork, making it increasingly difficult to identify an image's creator. However, this rapid development has not been widely accepted. Many individuals, including artists and art enthusiasts, reject AI-generated images. This often leads to debates about an image's origin or accusations that a work is AI-generated, which can escalate into conflict. This study implements an object identification technique limited to the domain of digital art to distinguish specific visual features produced by AI algorithms and human artists, resulting in a percentage likelihood for each class. This percentage can serve as a reference for evaluating an image's classification. The model is developed by fine-tuning a pre-trained ResNet50 and training it on an updated dataset. The dataset was collected from two Hugging Face repositories, “danbooru2025” and “pixiv-niji-journey,” with each class containing 12,500 images. Experimental results show the model achieves 95.64% accuracy and an F1-score of 0.9570, indicating it can effectively and reliably identify both AI-generated and human-created images.
Co-Authors Ari Syaripudin