Scopus
YÖKSİS DOI Eşleşti
SJR Q1
Image forgery detection by combining Visual Transformer with Variational Autoencoder Network
Applied Soft Computing · Kasım 2024
YÖKSİS Kayıtları
Image forgery detection by combining Visual Transformer with Variational Autoencoder Network
Applied Soft Computing · 2024 SCI-Expanded
Doç. Dr. ALİ YAŞAR →
YÖKSİS Kayıtları — ISSN Eşleşmesi
Detection of abnormalities in lumbar discs from clinical lumbar MRI with hybrid models
2015 ISSN: 15684946 SCI-Expanded
Prof. Dr. HASAN ERDİNÇ KOÇER →
Color image segmentation based on multiobjective artificial bee colony optimization
2015 ISSN: 15684946 SCI-Expanded
Doç. Dr. TAHİR SAĞ →
Color image segmentation based on multiobjective artificial bee colony optimization
2015 ISSN: 15684946 SCI-Expanded
Prof. Dr. MEHMET ÇUNKAŞ →
Liver fibrosis staging using CT image texture analysis and soft computing
2014 ISSN: 15684946 SCI-Expanded
Prof. Dr. MEHMET ÖZTÜRK →
New Approaches to determine Age and Gender in Image Processing Techniques using Multilayer Perceptron Neural Network
2018 ISSN: 1568-4946 SCI-Expanded
Prof. Dr. FATİH BAŞÇİFTÇİ →
A modification of tree-seed algorithm using Deb’s rules for constrained optimization
2018 ISSN: 1568-4946 SCI Q1
Doç. Dr. AHMET CEVAHİR ÇINAR →
A hybrid binary grey wolf optimizer for selection and reduction of reference points with extreme learning machine approach on local GNSS/leveling geoid determination
2021 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. KEMAL TÜTÜNCÜ →
Boosting the oversampling methods based on differential evolution strategies for imbalanced learning
2021 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. AHMET CEVAHİR ÇINAR →
A discrete spotted hyena optimizer for solving distributed job shop scheduling problems
2021 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. MEHMET AKİF ŞAHMAN →
A hybrid binary grey wolf optimizer for selection and reduction of reference points with extreme learning machine approach on local GNSS/leveling geoid determination
2021 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. MEHMET AKİF ŞAHMAN →
Boosting the oversampling methods based on differential evolution strategies for imbalanced learning
2021 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. MEHMET AKİF ŞAHMAN →
Classification rule mining based on Pareto-based Multiobjective Optimization
2022 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. TAHİR SAĞ →
Classification rule mining based on Pareto-based Multiobjective Optimization
2022 ISSN: 1568-4946 SCI-Expanded Q1
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
Image forgery detection by combining Visual Transformer with Variational Autoencoder Network
2024 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. ALİ YAŞAR →
Parametric picture fuzzy cross-entropy measures based on d-Choquet integral for building material recognition Applied Soft Computing
2024 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. DİLEK SÖYLEMEZ ÖZDEN →
A synergistic oversampling technique with differential evolution and safe level synthetic minority oversampling
2025 ISSN: 1568-4946 SCI-Expanded
Doç. Dr. AHMET CEVAHİR ÇINAR →
Efficiency analysis of binary metaheuristic optimization algorithms for uncapacitated facility location problems
2025 ISSN: 1568-4946 SCI-Expanded Q1
Doç. Dr. TAHİR SAĞ →
Makale Bilgileri
Dergi
Applied Soft Computing
ISSN15684946
Yayın TarihiKasım 2024
Cilt / Sayfa165
Scopus ID2-s2.0-85200601395
Özet
Recently, the applications and artificial intelligences used for image manipulation have become quite successful. In this case, the manipulation of personal data can lead to problems of insurmountable magnitude. Such problems not only put personal data at risk, but also lead us to unethical practices, with potentially irreversible negative consequences. For this reason, the reliability of image or video data is highly questionable. To solve this challenging problem, we introduce a Visual Transformer based Visual Transformer with Variational Autoencoder Network (ViT-VAE Net) model. The model includes Visual Transformer, one of the state-of-the-art architectures. In addition to this architecture, a Variational Auto Encoder structure is also included. is much more effective than models developed with the classical Convolutional Neural Network (CNN). Unlike models developed with CNN, it can perform operations on images of any size without being bound by a standard image resolution. In addition, thanks to the self-attention mechanism in the Visual Transformer architecture, manipulations on the image are caught more easily than CNN. The ViT-VAE Net model was trained with a large dataset and tested with 4 different datasets. With a success rate of 67 % on the training dataset, the model provided promising results. Very high rates were also obtained with the test datasets.
Yazarlar (2)
1
Ilker Galip Atak
2
Ali Yasar
Anahtar Kelimeler
Image forgery detection
Self-attention
Visual Transformer
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Scimago Dergi (ISSN Eşleşmesi)
Applied Soft Computing
Q1
SJR Skoru1,511
H-Index208
YayıncıElsevier B.V.
ÜlkeNetherlands
Software (Q1)
Metrikler
21
Atıf
2
Yazar
3
Anahtar Kelime