Face morphing detection in the presence of printing/scanning and heterogeneous image sources

@article{Ferrara2019FaceMD,
  title={Face morphing detection in the presence of printing/scanning and heterogeneous image sources},
  author={Matteo Ferrara and Annalisa Franco and Davide Maltoni},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.08811}
}
Face morphing represents nowadays a big security threat in the context of electronic identity documents as well as an interesting challenge for researchers in the field of face recognition. Despite of the good performance obtained by state-of-the-art approaches on digital images, no satisfactory solutions have been identified so far to deal with cross-database testing and printed-scanned images (typically used in many countries for document issuing). In this work, novel approaches are proposed… 
Deep Face Representations for Differential Morphing Attack Detection
TLDR
Subsets of the FERET and FRGCv2 face databases are used to create a realistic database for training and testing of MAD algorithms, and it is shown that algorithms based on deep face representations can achieve very high detection performance and robustness with respect to various post-processings.
Face morph detection for unknown morphing algorithms and image sources: a multi-scale block local binary pattern fusion approach
The vulnerability of face recognition systems against so-called morphing attacks has been revealed in the past years. Recently, different kinds of morphing attack detection approaches have been…
Face Morphing Detection: Issues and Challenges
Recently, facial recognition systems have been found vulnerable to morphing attacks. In these attacks, the facial images of two (or more) individuals are combined (morphed) and the resulting morphed…
Attention Aware Wavelet-based Detection of Morphed Face Images
TLDR
A wavelet-based morph detection methodology which adopts an end-to-end trainable soft attention mechanism, and analyzes the estimated attention maps for both a bona fide image and its corresponding morphed image.
Simulation of Print-Scan Transformations for Face Images based on Conditional Adversarial Networks
TLDR
A simulation of print-scan transformations for face images based on a Conditional Generative Adversarial Network (cGAN) is proposed, where subsets of two public face databases are manually printed and scanned using different printer-scanner combinations.
Style Your Face Morph and Improve Your Face Morphing Attack Detector
TLDR
This paper proposes a style transfer based method that improves the quality of morphed face images and counters the image degeneration during the creation of morphing face images caused by blending.
Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network
Along with the deployment of the Face Recognition Systems (FRS), concerns were raised related to the vulnerability of those systems towards various attacks including morphed attacks. The morphed face…
Border Control Morphing Attack Detection With a Convolutional Neural Network De-Morphing Approach
TLDR
A de-morphing architecture that is founded on a convolutional neural network (CNN) architecture, based on the use of two images: the potentially morphed image stored in the passport, and the snapshot of the person located in the ABC system.
Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network
TLDR
A new method to reliably detect a morphed face attack using a newly designed demising framework is proposed and a new deep Multi-scale Context Aggregation Network (MS-CAN) is introduced to obtain denoised images, which are subsequently used to determine if an image is morphed or not.
Morph Detection Enhanced by Structured Group Sparsity
TLDR
The challenge of face morphing attacks is considered, which substantially undermine the integrity of face recognition systems such as those adopted for use in border protection agencies and a deep supervised feature selection scheme is employed to find the most discriminative wavelet sub-bands of input images.
...
1
2
3
...

References

SHOWING 1-10 OF 75 REFERENCES
Transferable Deep-CNN Features for Detecting Digital and Print-Scanned Morphed Face Images
TLDR
This work proposes a novel approach leveraging the transferable features from a pre-trained Deep Convolutional Neural Networks (D-CNN) to detect both digital and print-scanned morphed face image.
Deep Face Representations for Differential Morphing Attack Detection
TLDR
Subsets of the FERET and FRGCv2 face databases are used to create a realistic database for training and testing of MAD algorithms, and it is shown that algorithms based on deep face representations can achieve very high detection performance and robustness with respect to various post-processings.
Morphing Detection Using a General- Purpose Face Recognition System
TLDR
It is shown that a general-purpose face recognition system combined with a simple linear classifier can be successfully used as a morphing detector, and the proposed method reuses an existing feature extraction pipeline instead of introducing additional modules.
Face Morphing Detection: An Approach Based on Image Degradation Analysis
In 2014 a novel identity theft scheme targeting specific application scenarios in face biometrics was introduced. In this scheme, a so called face morph melts two or more face images of different…
Towards Robust Evaluation of Face Morphing Detection
TLDR
This work creates face morphing databases with varying characteristics and shows how for a LBP/SVM based morphing detection method that performs on par with the state of the art, the performance collapses with an EER as high as if it is tested across databases with different characteristics.
Detecting Morphed Face Images Using Facial Landmarks
TLDR
This work proposes a novel method for morphed face image detection, based on the computation of the differences between the landmarks of a probe bona fide image and the suspected morphed image, and shows that the proposed algorithm achieves Equal Error Rates at 32.7%.
Generalized Benford's Law for Blind Detection of Morphed Face Images
TLDR
This work introduces the face morphing detection approach based on fitting a logarithmic curve to nine Benford features extracted from quantized DCT coefficients of JPEG compressed original and morphed face images and shows that a single parameter of the logarital curve may be sufficient to clearly separate morphed and original images.
Detecting Face Morphing Attacks with Collaborative Representation of Steerable Features
TLDR
This work addresses the problem of detecting the morphing of face images such that the attacks are detected even after the print and scan process and proposes a new approach based on extracting textural features across scale-space and classifying them using collaborative representation.
Face Recognition Systems Under Morphing Attacks: A Survey
TLDR
A conceptual categorization and metrics for an evaluation of such methods are presented, followed by a comprehensive survey of relevant publications, and technical considerations and tradeoffs of the surveyed methods are discussed.
Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts
TLDR
This work discusses the operational opportunity of having a live face probe to support the morphing detection decision and proposes a detection approach that take advantage of that, and considers the facial landmarks shifting patterns between reference and probe images.
...
1
2
3
4
5
...