Convolutional Neural Networks for Real and Fake Face Classification
Апстракт
This paper deals with the problem of classifying images of real and fake faces as it
is impossible to distinguish them with the bare eye. Two different convolutional
neural networks architecture models are applied. The first one is pre-trained
VGG16 model, where transfer learning method is applied on our dataset. The
architecture of the second model is based on VGG16 and represents its smaller
and lighter version. Techniques such as learning rate decay, dropout and batch
normalization was applied in training process. Comparison of obtained results
of both models is made.
Кључне речи:
Convolutional Neural Network / Deep Learning / Fake Face Image Classification / Transfer Learning / VGG16Извор:
Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research, 2022, 29-35Издавач:
- Belgrade: Singidunum University
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-ScienceFundRS-AI-6523109)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Perišić, Natalija AU - Jovanović, Radiša PY - 2022 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4494 AB - This paper deals with the problem of classifying images of real and fake faces as it is impossible to distinguish them with the bare eye. Two different convolutional neural networks architecture models are applied. The first one is pre-trained VGG16 model, where transfer learning method is applied on our dataset. The architecture of the second model is based on VGG16 and represents its smaller and lighter version. Techniques such as learning rate decay, dropout and batch normalization was applied in training process. Comparison of obtained results of both models is made. PB - Belgrade: Singidunum University C3 - Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research T1 - Convolutional Neural Networks for Real and Fake Face Classification EP - 35 SP - 29 DO - 10.15308/Sinteza-2022-29-35 ER -
@conference{ author = "Perišić, Natalija and Jovanović, Radiša", year = "2022", abstract = "This paper deals with the problem of classifying images of real and fake faces as it is impossible to distinguish them with the bare eye. Two different convolutional neural networks architecture models are applied. The first one is pre-trained VGG16 model, where transfer learning method is applied on our dataset. The architecture of the second model is based on VGG16 and represents its smaller and lighter version. Techniques such as learning rate decay, dropout and batch normalization was applied in training process. Comparison of obtained results of both models is made.", publisher = "Belgrade: Singidunum University", journal = "Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research", title = "Convolutional Neural Networks for Real and Fake Face Classification", pages = "35-29", doi = "10.15308/Sinteza-2022-29-35" }
Perišić, N.,& Jovanović, R.. (2022). Convolutional Neural Networks for Real and Fake Face Classification. in Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research Belgrade: Singidunum University., 29-35. https://doi.org/10.15308/Sinteza-2022-29-35
Perišić N, Jovanović R. Convolutional Neural Networks for Real and Fake Face Classification. in Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research. 2022;:29-35. doi:10.15308/Sinteza-2022-29-35 .
Perišić, Natalija, Jovanović, Radiša, "Convolutional Neural Networks for Real and Fake Face Classification" in Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research (2022):29-35, https://doi.org/10.15308/Sinteza-2022-29-35 . .