WARMAN, ADITYA (2025) THE IMPLEMENTATION OF CONVOLUTIONAL NEURAL NETWORK FOR IDENTIFYING REAL AND AI-GENERATED IMAGES. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411097_Aditya Warman_Abstrak.pdf Download (102kB) |
Abstract
The rapid advancement of digital imaging technologies—such as high-resolution cameras, advanced sensors, and sophisticated image editing software—has significantly transformed the way images are captured, processed, and analyzed. In parallel, the rise of artificial intelligence (AI) in image generation has created new challenges, particularly in verifying the authenticity of visual content. AI-generated images are increasingly realistic and often indistinguishable from real photographs, leading to concerns such as deepfakes, misinformation, and privacy violations. This research aims to address these challenges by developing a system capable of distinguishing between human-generated and AI-generated images using a Convolutional Neural Network (CNN). The proposed system utilizes a CNN architecture with four convolutional layers, trained on a dataset comprising 5,285 images across two classes. The model achieved a training accuracy of 85% with a loss of 34%, and evaluation on test data yielded an 80% accuracy across 100 samples. The findings demonstrate the potential of CNN-based approaches in supporting digital image verification and enhancing security in the era of AI-generated content. Keywords: Image, Artificial Intelligence, Convolutional Neural Network, Deep Learning, Machine Learning, Computer Vision.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 18 Jul 2025 08:44 |
| Last Modified: | 18 Jul 2025 08:44 |
| URI: | http://eprints.uty.ac.id/id/eprint/18268 |
Actions (login required)
 |
View Item |
