On the Applicability of Synthetic Data for Face Recognition

Zhang, Haoyu; Grimmer, Marcel; Ramachandra, Raghavendra; Raja, Kiran B.; Busch, Christoph

doi:10.1109/iwbf50991.2021.9465085

Cited by 23 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To balance this trade-off, a truncation factor can be used to stabilise the sampling: the truncated latent code w is calculated as w = w + ψ(w − w) where w indicates the latent spaces' center of mass and ψ denotes the truncation factor. Following the empirical analysis of Zhang et al [9], we choose a truncation factor of ψ = 0.75. In [9], the authors have shown that the biometric performance of synthetic samples generated with StyleGAN and StyleGAN2 are similar and comparable to bona fide images from FRGC v2.0 [23].…”

Section: Synthetic Image Generationmentioning

confidence: 99%

“…Following the empirical analysis of Zhang et al [9], we choose a truncation factor of ψ = 0.75. In [9], the authors have shown that the biometric performance of synthetic samples generated with StyleGAN and StyleGAN2 are similar and comparable to bona fide images from FRGC v2.0 [23]. Hence, this work uses StyleGAN for generating synthetic base images to enable the implementation of PCA-FR-Guided sampling to operate within the framework of InterFaceGAN [25].…”

Section: Synthetic Image Generationmentioning

confidence: 99%

“…Though it has been shown in [9] that single synthetic face images can achieve comparable performances as bona fide samples for face recognition, mated samples are more commonly required in biometric performance evaluations. Given a synthetic base image, mated samples can be derived by editing facial attributes to simulate the factors of variation present in bona fide samples.…”

Section: Mated Sample Generationmentioning

confidence: 99%

See 2 more Smart Citations

Generation of Non-Deterministic Synthetic Face Datasets Guided by Identity Priors

Grimmer¹,

Zhang²,

Ramachandra³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Enabling highly secure applications (such as border crossing) with face recognition requires extensive biometric performance tests through large scale data. However, using real face images raises concerns about privacy as the laws do not allow the images to be used for other purposes than originally intended. Using representative and subsets of face data can also lead to unwanted demographic biases and cause an imbalance in datasets. One possible solution to overcome these issues is to replace real face images with synthetically generated samples. While generating synthetic images has benefited from recent advancements in computer vision, generating multiple samples of the same synthetic identity resembling real-world variations is still unaddressed, i.e., mated samples. This work proposes a non-deterministic method for generating mated face images by exploiting the well-structured latent space of StyleGAN. Mated samples are generated by manipulating latent vectors, and more precisely, we exploit Principal Component Analysis (PCA) to define semantically meaningful directions in the latent space and control the similarity between the original and the mated samples using a pre-trained face recognition system. We create a new dataset of synthetic face images (SymFace) consisting of 77,034 samples including 25,919 synthetic IDs. Through our analysis using well-established face image quality metrics, we demonstrate the differences in the biometric quality of synthetic samples mimicking characteristics of real biometric data. The analysis and results thereof indicate the use of synthetic samples created using the proposed approach as a viable alternative to replacing real biometric data.

show abstract

Section: Synthetic Image Generationmentioning

confidence: 99%

Section: Synthetic Image Generationmentioning

confidence: 99%

Section: Mated Sample Generationmentioning

confidence: 99%

See 1 more Smart Citation

Generation of Non-Deterministic Synthetic Face Datasets Guided by Identity Priors

Grimmer¹,

Zhang²,

Ramachandra³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Whether synthetic biometric data does realistically simulate real world applications, is an question that requires further investigations. [55].…”

Section: Hufhqwdjhmentioning

confidence: 99%

Demographic Fairness in Biometric Systems: What do the Experts say?

Rathgeb¹,

Drozdowski²,

Damer³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Algorithmic decision systems have frequently been labelled as "biased", "racist", "sexist", or "unfair" by numerous media outlets, organisations, and researchers. There is an ongoing debate about whether such assessments are justified and whether citizens and policymakers should be concerned. These and other related matters have recently become a hot topic in the context of biometric technologies, which are ubiquitous in personal, commercial, and governmental applications. Biometrics represent an essential component of many surveillance, access control, and operational identity management systems, thus directly or indirectly affecting billions of people all around the world.Recently, the European Association for Biometrics organised an event series with "demographic fairness in biometric systems" as an overarching theme. The events featured presentations by international experts from academic, industry, and governmental organisations and facilitated interactions and discussions between the experts and the audience. Further consultation of experts was undertaken by means of a questionnaire. This work summarises opinions of experts and findings of said events on the topic of demographic fairness in biometric systems including several important aspects such as the developments of evaluation metrics and standards as well as related issues, e.g. the need for transparency and explainability in biometric systems or legal and ethical issues.

show abstract

“…Motivated by the above-mentioned challenges, the use of synthetic data in biometrics has recently attracted attention. Zhang et al [47] investigated the behavior of face image quality assessment methods on synthetic images created by StyleGAN [15] and StyleGAN2 [16] and compare the face image quality values with those of authentic face images. Another biometric use case based on synthetic data that has Fig.…”

Section: Introductionmentioning

confidence: 99%

SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data

Huber¹,

Siebke²,

Rieber³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent deep face recognition models proposed in the literature utilized large-scale public datasets such as MS-Celeb-1M and VGGFace2 for training very deep neural networks, achieving state-of-the-art performance on mainstream benchmarks. Recently, many of these datasets, e.g., MS-Celeb-1M and VGGFace2, are retracted due to credible privacy and ethical concerns. This motivates this work to propose and investigate the feasibility of using a privacy-friendly synthetically generated face dataset to train face recognition models. Towards this end, we utilize a class-conditional generative adversarial network to generate class labeled synthetic face images, namely SFace. To address the privacy aspect of using such data to train a face recognition model, we provide extensive evaluation experiments on the identity relation between the synthetic dataset and the original authentic dataset used to train the generative model. Our reported evaluation proved that associating an identity of the authentic dataset to one with the same class label in the synthetic dataset is hardly possible. We also propose to train face recognition on our privacyfriendly dataset, SFace, using three different learning strategies, multi-class classification, label-free knowledge transfer, and combined learning of multi-class classification and knowledge transfer. The reported evaluation results on five authentic face benchmarks demonstrated that the privacy-friendly synthetic dataset has high potential to be used for training face recognition models, achieving, for example, a verification accuracy of 91.87% on LFW using multi-class classification and 99.13% using the combined learning strategy. The training code and the synthetic face image dataset are publicly released 1 .

show abstract

On the Applicability of Synthetic Data for Face Recognition

Cited by 23 publications

References 8 publications

Generation of Non-Deterministic Synthetic Face Datasets Guided by Identity Priors

Generation of Non-Deterministic Synthetic Face Datasets Guided by Identity Priors

Demographic Fairness in Biometric Systems: What do the Experts say?

SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data

Contact Info

Product

Resources

About