Authors : Alidor M. Mbayandjambe; Grevi B. Nkwimi; Darren Kevin T. Nguemdjom; Fiston Oshasha; Célestin Muluba; Xavier F. Kutuka

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/4c635428

Scribd : https://tinyurl.com/yenph3w5

DOI : https://doi.org/10.38124/ijisrt/25apr1963

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : The increasing prevalence of AI-generated content presents unique challenges in the field of computer vision, especially when distinguishing between real and synthetic images. This study explores the detection of AI-generated sneakers, specifically from popular brands such as Nike, Adidas, and Converse, using Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNNs). The dataset for this project is a mix of real sneaker images sourced from Google Images and AI-generated images produced by the MidJourney AI platform. To enrich the dataset and enhance model training, synthetic images are generated through a GAN, providing a diverse range of examples. The primary objective is to train a robust detection model capable of distinguishing between real and AI-generated sneaker images by leveraging subtle visual differences. This research demonstrates the effectiveness of GANs in augmenting datasets for machine learning applications, while also testing the resilience of CNNs in distinguishing high-quality AI- generated images from authentic ones. The dataset, standardized to 240x240 pixel resolution, offers a comprehensive foundation for developing advanced image classification models aimed at tackling the growing challenge of AI-generated content detection.

Keywords : AI-Generated Images, Sneaker Detection, Generative Adversarial Networks, Convolutional Neural Networks, Dataset Augmentation, Machine Learning, Computer Vision.

References :

1. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," NeurIPS 27, 2014, pp. 2672–2680, ISSN: 1045-926X.
2. Mishra, N. K., Singh, P., Gupta, A., & Joshi, S. D. (2024). PP-CNN: Probabilistic pooling CNN for enhanced image classification. Neural Computing and Applications, 37(6), 4345–4361. https://doi.org/10.1007/s00521-024-10862-3
3. Hussain, W., Mushtaq, M. F., Shahroz, M., Ashraf, I., et al. (2025). Ensemble genetic and CNN model-based image classification by enhancing hyperparameter tuning. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-024-76178-3
4. T. Karras, T. Aila, S. Laine, and J. Lehtinen, "Progressive growing of GANs for improved quality, stability, and variation," International Conference on Learning Representations (ICLR), 2019.
5. Elgammal, B. Liu, M. Elhoseiny, and M. Mazzone, "CAN: Creative adversarial networks, generating 'art' by learning about styles and deviating from style norms," arXiv preprint arXiv:1706.07068, Jun. 2017.
6. Zhang, T. Xu, Y. Zhang, and Y. Li, "Detecting AI-generated images by learning from domain-specific features," International Journal of Computer Vision, vol. 128, no. 3, pp. 899–919, Jul. 2020, ISSN: 0920-5691.
7. Kaissis, G., Makowski, M. R., Rückert, D., & Braren, R. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2(6), 305–311. https://doi.org/10.1038/s42256-020-0186-1
8. Mahara and N. Rishe, "Methods and trends in detecting generated images: A comprehensive review," arXiv preprint arXiv:2502.15176, 2025.
9. Shi, C., Liao, D., & Wang, L. (2025). Hybrid CNN-GCN network for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, PP(99), 1–18. https://doi.org/10.1109/JSTARS.2025.3548571
10. M. Guo et al., "AI-generated image detection: Passive or watermark?" arXiv preprint arXiv:2411.13553, 2024.
11. S. Yan et al., "A sanity check for AI-generated image detection," arXiv preprint arXiv:2406.19435, 2024.
12. Y. Wang, Z. Lin, X. Lu, and W. Yang, "Cross-domain GAN detection with domain-adaptive CNNs," Journal of Machine Learning Research, vol. 22, no. 85, pp. 1-20, 2021.
13. Ramesh, M. Dhariwal, P. Nikishin, et al., "DALL-E: Creating images from text," arXiv preprint arXiv:2102.12092, 2021.
14. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
15. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolutional neural networks," NeurIPS 25, 2012, pp. 1097–1105.
16. Chollet, Deep Learning with Python, Manning Publications, 2017.
17. Solomon, V. (2025). A deep learning approach for image classification using CNN. https://doi.org/10.13140/RG.2.2.13835.20004
18. García-Aguirre, R., Navarro-López, E. M., & Torres-Treviño, L. (2024). Gen-CNN: A framework for the automatic generation of CNNs for image classification. Neural Computing and Applications, 37(1), 149–168. https://doi.org/10.1007/s00521-024-10398-6
19. Soudy, A. H., Sayed, O., Tag-Elser, H., & Ragab, R. (2024). Deepfake detection using convolutional vision transformers and convolutional neural networks. Neural Computing and Applications, 36(31), 19759–19775. https://doi.org/10.1007/s00521-024-10181-7 (CC BY 4.0)
20. Kwakernaak, H., & Misra, P. (2024). Real, fake and synthetic faces - does the coin have three sides? arXiv preprint arXiv:2404.01878. https://arxiv.org/abs/2404.01878 (CC BY-NC-ND 4.0)
21. Vyas, B., & Rajendran, R. M. (2023). Generative Adversarial Networks for Anomaly Detection in Medical Images. International Journal of Multidisciplinary Innovation and Research Methodology, ISSN: 2960-2068, 2(4), 52-58.
22. Bi, X., Liu, B., Yang, F., Xiao, B., Li, W., Huang, G., & Cosman, P. C. (2023). Detecting Generated Images by Real Images Only. arXiv:2311.00962. https://arxiv.org/abs/2311.00962
23. Liu, Y., Wan, Z., Yin, X., & Yue, G. (2023). Detection of GAN generated image using color gradient representation. Journal of Visual Communication and Image Representation, 95, 103876. https://doi.org/10.1016/j.jvcir.2023.103876
24. Naim, J., Adnan, M. N., Galib, M. A., & Uddin, A. F. M. S. (2023). Detecting GAN Generated Fake Images Using Feature Extraction. IEEE CS BDC Summer Symposium.
25. Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., & Greenspan, H. (2018). GAN-based Synthetic Medical Image Augmentation for Increased CNN Performance in Liver Lesion Classification. arXiv:1803.01229. https://arxiv.org/abs/1803.01229