Face morphing attacks present an emerging threat to the face recognition
system. On top of that, printing and scanning the morphed images could obscure
the artifacts generated during the morphing process, which makes morphed image
detection even harder. In this work, we investigate the impact that printing
and scanning has on morphing attacks through a series of heterogeneous tests.
Our experiments show that we can increase the possibility of a false match by
up to 5.64% for DiM and 16.00% for StyleGAN2 when providing an image that has
been printed and scanned, regardless it is morphed or bona fide, to a Face
Recognition (FR) system. Likewise, using Frechet Inception Distance (FID)
metric, strictly print-scanned morph attacks performed on average 9.185%
stronger than non-print-scanned digital morphs.

通过一系列的异构测试，我们研究了印刷和扫描对于脸部变形攻击的影响。我们的实验结果显示，通过提供经过打印和扫描的图像（无论是变形的还是真实的）给人脸识别系统，可以将虚假匹配的可能性增加多达 5.64％（DiM）和 16.00％（StyleGAN2）。同样，使用 Frechet Inception Distance 指标，严格的印刷扫描变形攻击的强度平均比非印刷扫描数字变形攻击增强了 9.185％。

异质形态评估场景中印印扫描的影响

The Impact of Print-and-Scan in Heterogeneous Morph Evaluation Scenarios

With the tremendous advancements in face recognition technology, face
modality has been widely recognized as a significant biometric identifier in
establishing a person's identity rather than any other biometric trait like
fingerprints that require contact sensors. However, due to inter-class
similarities and intra-class variations, face recognition systems generate
false match and false non-match errors respectively. Recent research focuses on
improving the robustness of extracted features and the pre-processing
algorithms to enhance recognition accuracy. Since face recognition has been
extensively used for several applications ranging from law enforcement to
surveillance systems, the accuracy and performance of face recognition must be
the finest. In this paper various face recognition systems are discussed and
analysed like RPRV, LWKPCA, SVM Model, LTrP based SPM and a deep learning
framework for recognising images from CCTV. All these face recognition methods,
their implementations and performance evaluations are compared to derive the
best outcome for future developmental works.

本研究讨论了多种人脸识别系统，并分析了其实施和性能评估，通过比较得出了最佳的方法以供未来开发工作使用，涉及到的技术包括人脸识别，生物识别，深度学习等。