Spritz-PS: Validation of Synthetic Face Images Using a Large Dataset of Printed Documents
Not on the map. Why?
Abstract (arXiv)
The capability of doing effective forensic analysis on printed and scanned (PS) images is essential in many applications. PS documents may be used to conceal the artifacts of images which is due to the synthetic nature of images since these artifacts are typically present in manipulated images and the main artifacts in the synthetic images can be removed after the PS. Due to the appeal of Generative Adversarial Networks (GANs), synthetic face images generated with GANs models are difficult to differentiate from genuine human faces and may be used to create counterfeit identities. Additionally, since GANs models do not account for physiological constraints for generating human faces and their impact on human IRISes, distinguishing genuine from synthetic IRISes in the PS scenario becomes extremely difficult. As a result of the lack of large-scale reference IRIS datasets in the PS scenario, we aim at developing a novel dataset to become a standard for Multimedia Forensics (MFs) investigation which is available at [45]. In this paper, we provide a novel dataset made up of a large number of synthetic and natural printed IRISes taken from VIPPrint Printed and Scanned face images. We extracted irises from face images and it is possible that the model due to eyelid occlusion captured the incomplete irises. To fill the missing pixels of extracted iris, we applied techniques to discover the complex link between the iris images. To highlight the problems involved with the evaluation of the dataset's IRIS images, we conducted a large number of analyses employing Siamese Neural Networks to assess the similarities between genuine and synthetic human IRISes, such as ResNet50, Xception, VGG16, and MobileNet-v2. For instance, using the Xception network, we achieved 56.76% similarity of IRISes for synthetic images and 92.77% similarity of IRISes for real images.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 94 references that are in the map. First posted on arXiv 6 Apr 2023.
Builds on
41 of 94 references.
References · 41
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2021Alias-Free Generative Adversarial Networkscited by 1,184
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
- 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
- 2017Generative Adversarial Networks: An Overviewcited by 590
- 2018Hypergraph Neural Networkscited by 488
- 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
- 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
- 2019Hypergraph Convolution and Hypergraph Attentioncited by 228
29 more
- 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
- 2020Media Forensics and DeepFakes: an overviewcited by 209
- 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
- 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
- 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
- 2018Graph-Based Global Reasoning Networkscited by 120
- 2016Energy-based Generative Adversarial Networkcited by 119
- 2016Invertible Conditional GANs for image editingcited by 118
- 2020Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlightscited by 59
- 2019Incremental learning for the detection and classification of GAN-generated imagescited by 58
- 2021Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Facescited by 48
- 2020CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysiscited by 42
- 2019On the generalization of GAN image forensicscited by 36
- 2020Detecting CNN-Generated Facial Images in Real-World Scenarioscited by 32
- 2019Exposing GAN-synthesized Faces Using Landmark Locationscited by 30
- 2020Training Strategies and Data Augmentations in CNN-based DeepFake Video Detectioncited by 17
- 2020Attentive Semantic Exploring for Manipulated Face Detectioncited by 14
- 2020A Survey of Machine Learning Techniques in Adversarial Image Forensicscited by 14
- 2018On the Transferability of Adversarial Examples Against CNN-Based Image Forensicscited by 12
- 2021Demystifying the Transferability of Adversarial Attacks in Computer Networkscited by 9
- 2018CNN-Based Detection of Generic Constrast Adjustment with JPEG Post-processingcited by 8
- 2020Hyperrealistic Image Inpainting with Hypergraphscited by 6
- 2018Source Printer Classification using Printer Specific Local Texture Descriptorcited by 5
- 2022Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomizationcited by 5
- 2019Improving the security of Image Manipulation Detection through One-and-a-half-class Multiple Classificationcited by 3
- 2019Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examplescited by 3
- 2021Do Not Deceive Your Employer with a Virtual Background: A Video Conferencing Manipulation-Detection Systemcited by 3
- 2022Detecting High-Quality GAN-Generated Face Images using Neural Networkscited by 3
- 2020Printing and Scanning Attack for Image Counter Forensicscited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.