Tools
Tools
Martinez Martinez, Lazaro Javier (2024) Classifying AI-Generated images using EfficientNet-B0, ResNet50 and VGG16 CNN ML models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (10MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (464kB) | Preview |
Abstract
The creation of AI-Generated images has been democratised with the proliferation of online and scalable tools. These tools enable users to easily create high quality, fidelity and realistic fake images for multiple use cases and purposes. Detecting, labelling and classifying AI-Generated images is crucial in a wide range of circumstances and applications. This research evaluates the performance of three CNN ML models (EfficientNet-B0, RestNet50 and VGG16) on four public image datasets belonging to three themes: miscellaneous; shoes; and, fruit. The VGG16 model proved to have higher accuracy and performance compared to the other two models.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Anand, Devanshu UNSPECIFIED |
| Uncontrolled Keywords: | AI-Generated; image; CNN; EfficientNet-B0; ResNet50; VGG16 |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Artificial Intelligence |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 18 Jun 2025 13:38 |
| Last Modified: | 18 Jun 2025 13:38 |
| URI: | https://norma.ncirl.ie/id/eprint/7918 |
Actions (login required)
 |
View Item |