Live Face De-Identification in Video

Gafni, Oran; Wolf, Lior; Taigman, Yaniv

doi:10.1109/iccv.2019.00947

Cited by 119 publications

(123 citation statements)

References 48 publications

(78 reference statements)

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…In this appendix we compare visual results of AnonFACES with recent results from [18] and [7]. As demonstrated in Figure 17, the results in [18] have a blurring effect which reduces the image quality while some identity features (e.g.…”

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 97%

“…This is important as it allows, for example, car manufacturers to effectively train their autonomous vehicles while complying with privacy laws. [18]: first row: input images, second row: results from [18], third row: AnonFACES results using =2 Figure 18: Comparison with Gafni et al [7]: first row: input images, second row: results from [7], third row: AnonFACES results using =2…”

Section: Resultsmentioning

confidence: 99%

“…AnonFACES clearly outperforms [18] in terms of naturalness and has a noticeably better anonymizing effect. In Figure 18 the results from [7] are shown to have minimal difference in terms of identity features such as general facial landmark features, eyes, and mouth area. AnonFACES again provides visibly better anonymization.…”

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 99%

“…In both cases, our results still preserve non-identity information such as emotion, age, gender, and skin color. Note, however, that [18] and [7] only replace some (identifying) facial features, presumably to work with videos, whereas AnonFACES replaces the entire image. Restricting the area to within the face would allow for a more direct comparison but is outside of the scope of this paper.…”

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 99%

See 3 more Smart Citations

AnonFACES

Khan

Tsaloli

et al. 2020

Proceedings of the 19th Workshop on Privacy in the Electronic Society

View full text Add to dashboard Cite

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 97%

Section: Resultsmentioning

confidence: 99%

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 99%

Section: Appendix a Additional Comparisons Of Visual Results With Relmentioning

confidence: 99%

See 2 more Smart Citations

AnonFACES

Khan

Tsaloli

et al. 2020

Proceedings of the 19th Workshop on Privacy in the Electronic Society

View full text Add to dashboard Cite

“…This method provides control over facial parameters for manipulation of identity and enables photo-realistic image synthesis. The recent architecture of Gafni et al [15] is based on an adversarial autoencoder and a trained face classifier. The key objective is to decorrelate the identity and to fix the expression, pose, and illumination components.…”

Section: Related Workmentioning

confidence: 99%

How important are faces for person re-identification?

Dietlmeier

Antony

McGuinness

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

This paper investigates the dependence of existing state-of-the-art person re-identification models on the presence and visibility of human faces. We apply a face detection and blurring algorithm to create anonymized versions of several popular person re-identification datasets including Market1501, DukeMTMC-reID, CUHK03, Viper, and Airport. Using a crosssection of existing state-of-the-art models that range in accuracy and computational efficiency, we evaluate the effect of this anonymization on re-identification performance using standard metrics. Perhaps surprisingly, the effect on mAP is very small, and accuracy is recovered by simply training on the anonymized versions of the data rather than the original data. These findings are consistent across multiple models and datasets. These results indicate that datasets can be safely anonymized by blurring faces without significantly impacting the performance of person reidentification systems, and may allow for the release of new richer re-identification datasets where previously there were privacy or data protection concerns.

show abstract

AEGAN: Generating imperceptible face synthesis via autoencoder‐based generative adversarial network

Che

Yang

Guo

et al. 2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Face recognition (FR) systems based on convolutional neural networks have shown excellent performance in human face inference. However, some malicious users may exploit such powerful systems to identify others' face images disclosed by victims' social network accounts, consequently obtaining private information. To address this emerging issue, synthesizing face protection images with visual and protective effects is essential. However, existing face protection methods encounter three critical problems: poor visual effect, limited protective effect, and trade‐off between visual and protective effects. To address these challenges, we propose a novel face protection approach in this article. Specifically, we design a generative adversarial network (GAN) framework with an autoencoder (AEGAN) as the generator to synthesize the protection images. It is worth noting that we introduce an interpolation upsampling module in the decoder in order to let the synthesized protection images evade recognition by powerful convolution‐based FR systems. Furthermore, we introduce an attention module with a perceptual loss in AEGAN to enhance the visual effects of synthesized images by AEGAN. Extensive experiments have shown that AEGAN not only can maintain the comfortable visual quality of synthesized images but also prevent the recognition of commercial FR systems, including Baidu and iKLYTEK.

show abstract

Live Face De-Identification in Video

Cited by 119 publications

References 48 publications

AnonFACES

AnonFACES

How important are faces for person re-identification?

AEGAN: Generating imperceptible face synthesis via autoencoder‐based generative adversarial network

Contact Info

Product

Resources

About