Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD

Juefei-Xu, Felix; Pal, Dipan K.; Savvides, Marios

doi:10.1109/cvprw.2014.6

Cited by 31 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to other commonly used distance measurement such as ℓ 1 -norm, ℓ 2 -norm, NCD exhibits the best result [48][49][50][51][52][53][54][55]68,69]. The result of each algorithm is a similarity matrix whose entry SimM ij is the NCD between the feature vector of probe image i and target image j.…”

Section: Experimental Setup Overviewmentioning

confidence: 97%

Multi-class Fukunaga Koontz discriminant analysis for enhanced face recognition

Juefei-Xu

Savvides

2016

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Section: Experimental Setup Overviewmentioning

confidence: 97%

Multi-class Fukunaga Koontz discriminant analysis for enhanced face recognition

Juefei-Xu

Savvides

2016

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

“…The reconstructed image patchŷ = Dx. The aforementioned dictionary learning and reconstruction were previously used in various domain-domain mapping problems such as [3,[22][23][24][25][26][27][28].…”

Section: Shallow Reconstruction From Dense Vs Sparse Representationmentioning

confidence: 99%

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Huang

Juefei-Xu

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. However, the existing detection methods put much emphasis on the artifact patterns, which can become futile if such artifact patterns were reduced. Towards reducing the artifacts in the synthesized images, in this paper, we devise a simple yet powerful approach termed FakePolisher that performs shallow reconstruction of fake images through a learned linear dictionary, intending to effectively and efficiently reduce the artifacts introduced during image synthesis. In particular, we first train a dictionary model to capture the patterns of real images. Based on this dictionary, we seek the representation of DeepFake images in a low dimensional subspace through linear projection or sparse coding. Then, we are able to perform shallow reconstruction of the 'fake-free' version of the DeepFake image, which largely reduces the artifact patterns DeepFake introduces. The comprehensive evaluation on 3 state-of-the-art DeepFake detection methods and fake images generated by 16 popular GAN-based fake image generation techniques, demonstrates the effectiveness of our technique. Overall, through reducing artifact patterns, our technique significantly reduces the accuracy of the 3 state-of-theart fake image detection methods, i.e., 47% on average and up to 93% in the worst case. Our results confirm the limitation of current fake detection methods and calls the attention of DeepFake researchers and practitioners for more general-purpose fake detection techniques. CCS CONCEPTS • Security and privacy → Human and societal aspects of security and privacy; • Computing methodologies → Computer vision.

show abstract

“…The fast-paced development of deep learning (DL) has bolstered the deployment of high-performance DL-based face recognition systems (FRS) [1,2]. Compared to non DL-based FRS from a decade ago, the DL-based FRS nowadays can handle more challenging unconstrained scenarios and is very well suited for handling various FR tasks in unconstrained real-world scenarios, especially when faces are under various known or unknown degradations such as being very lowresolution [3,4,5], at an off-angle pose [6,7,8], heavily occluded by objects or crowd [9,10,11], etc. Among the mentioned degradation factors, illumination variations is Fig.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Relighting against Face Recognition

Gao¹,

Gao²,

Zhang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deep face recognition (FR) has achieved significantly high accuracy on several challenging datasets and fosters successful real-world applications, even showing high robustness to the illumination variation that is usually regarded as a main threat to the FR system. However, in the real world, illumination variation caused by diverse lighting conditions cannot be fully covered by the limited face dataset. In this paper, we study the threat of lighting against FR from a new angle, i.e., adversarial attack, and identify a new task, i.e., adversarial relighting. Given a face image, adversarial relighting aims to produce a naturally relighted counterpart while fooling the state-of-the-art deep FR methods. To this end, we first propose the physical modelbased adversarial relighting attack (ARA) denoted as albedoquotient-based adversarial relighting attack (AQ-ARA). It generates natural adversarial light under the physical lighting model and guidance of FR systems and synthesizes adversarially relighted face images. Moreover, we propose the auto-predictive adversarial relighting attack (AP-ARA) by training an adversarial relighting network (ARNet) to automatically predict the adversarial light in a one-step manner according to different input faces, allowing efficiency-sensitive applications . More importantly, we propose to transfer the above digital attacks to physical ARA (Phy-ARA) through a precise relighting device, making the estimated adversarial lighting condition reproducible in the real world. We validate our methods on three state-of-the-art deep FR methods, i.e., FaceNet, ArcFace, and CosFace, on two public datasets. The extensive and insightful results demonstrate our work can generate realistic adversarial relighted face images fooling FR easily, revealing the threat of specific light directions and strengths.

show abstract

Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD

Cited by 31 publications

References 18 publications

Multi-class Fukunaga Koontz discriminant analysis for enhanced face recognition

Multi-class Fukunaga Koontz discriminant analysis for enhanced face recognition

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Adversarial Relighting against Face Recognition

Contact Info

Product

Resources

About