SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

Ou, Fu-Zhao; Chen, Xingyu; Zhang, Ruixin; Huang, Yuge; Li, Shaoxin; Li, Jilin; Li, Yong; Cao, Liujuan; Wang, Yuan‐Gen

doi:10.1109/cvpr46437.2021.00758

Cited by 87 publications

(25 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several studies in Ref. [34, 65] pointed out that the FIQ measures such as MagFace [14], SDD‐FIQA [63], SER‐FIQ [62], and CR‐FIQA [55] are highly correlated with the face utility as defined in ISO/IEC 29794‐1 [83]. A recent work [65] has shown that for normal FR samples, IQ measures also correlate to utility but to a much lower degree than FIQ.…”

Section: Resultsmentioning

confidence: 99%

“…[14,62], (2) unsupervised methods based on FR model behaviour as in Ref. [29,63], or (3) ranking-based approaches as in Ref. [30].…”

Section: Face Image Quality Assessmentmentioning

confidence: 99%

“…FaceQnet [29] and SDD-FIQA [63] are categorised into the supervised FIQA methods. While FaceQnet uses ICAO compliant face images as high-quality reference images and builds quality labelling scores based on the FR genuine comparison score to ICAO compliant images, the SDD-FIQA uses pseudo quality label based on the Wasserstein distance between similarity distributions of genuine and imposter image pairs.…”

Section: Face Image Quality Assessmentmentioning

confidence: 99%

“…MagFace [14] SDD-FIQA [63] SER-FIQ [62] FaceQnet v2 [29] RankIQ [30] BRISQUE [17] DBCNN [58] CNNIQA [13] UNIQUE [61] dipIQ [36] Increase Increase Increase Increase Increase Decrease Increase Decrease Increase Increase respective source face datasets. We subsequently introduce the evaluation metrics before presenting the protocols used in our investigations.…”

Section: Fiqa Iqamentioning

confidence: 99%

See 3 more Smart Citations

Face morphing attacks and face image quality: The effect of morphing and the unsupervised attack detection by quality

Damer

2022

IET Biometrics

View full text Add to dashboard Cite

Morphing attacks are a form of presentation attacks that gathered increasing attention in recent years. A morphed image can be successfully verified to multiple identities. This operation, therefore, poses serious security issues related to the ability of a travel or identity document to be verified to belong to multiple persons. Previous studies touched on the issue of the quality of morphing attack images, however, with the main goal of quantitatively proofing the realistic appearance of the produced morphing attacks. The authors theorise that the morphing processes might have an effect on both, the perceptual image quality and the image utility in face recognition (FR) when compared to bona fide samples. Towards investigating this theory, this work provides an extensive analysis of the effect of morphing on face image quality, including both general image quality measures and face image utility measures. This analysis is not limited to a single morphing technique but rather looks at six different morphing techniques and five different data sources using ten different quality measures. This analysis reveals consistent separability between the quality scores of morphing attack and bona fide samples measured by certain quality measures. The authors’ study goes further to build on this effect and investigate the possibility of performing unsupervised morphing attack detection (MAD) based on quality scores. The authors’ study looks into intra‐ and inter‐dataset detectability to evaluate the generalisability of such a detection concept on different morphing techniques and bona fide sources. The authors’ final results point out that a set of quality measures, such as MagFace and CNNIQA, can be used to perform unsupervised and generalised MAD with a correct classification accuracy of over 70%.

show abstract

Section: Resultsmentioning

confidence: 99%

“…[14,62], (2) unsupervised methods based on FR model behaviour as in Ref. [29,63], or (3) ranking-based approaches as in Ref. [30].…”

Section: Face Image Quality Assessmentmentioning

confidence: 99%

Section: Face Image Quality Assessmentmentioning

confidence: 99%

Section: Fiqa Iqamentioning

confidence: 99%

See 2 more Smart Citations

Face morphing attacks and face image quality: The effect of morphing and the unsupervised attack detection by quality

Damer

2022

IET Biometrics

View full text Add to dashboard Cite

show abstract

“…Like the previously mentioned methods, SDD‐FIQA [29] bases its quality assessment on the recognition performance for a given sample. This is done by mapping the inter‐class and intra‐class similarity scores to quality pseudo‐labels through the use of a distribution distance metric.…”

Section: Related Workmentioning

confidence: 99%

Towards understanding the character of quality sampling in deep learning face recognition

Medvedev

Tremoço

Mano³

et al. 2022

IET Biometrics

View full text Add to dashboard Cite

Face recognition has become one of the most important modalities of biometrics in recent years. It widely utilises deep learning computer vision tools and adopts large collections of unconstrained face images of celebrities for training. Such choice of the data is related to its public availability when existing document compliant face image collections are hardly accessible due to security and privacy issues. Such inconsistency between the training data and deploy scenario may lead to a leak in performance in biometric systems, which are developed specifically for dealing with ID document compliant images. To mitigate this problem, we propose to regularise the training of the deep face recognition network with a specific sample mining strategy, which penalises the samples by their estimated quality. In addition to several considered quality metrics in recent work, we also expand our deep learning strategy to other sophisticated quality estimation methods and perform experiments to better understand the nature of quality sampling. Namely, we seek for the penalising manner (sampling character) that better satisfies the purpose of adapting deep learning face recognition for images of ID and travel documents. Extensive experiments demonstrate the efficiency of the approach for ID document compliant face images.

show abstract

QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment

Zhang

et al. 2021

Neural Information Processing

View full text Add to dashboard Cite

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance

Cited by 87 publications

References 24 publications

Face morphing attacks and face image quality: The effect of morphing and the unsupervised attack detection by quality

Face morphing attacks and face image quality: The effect of morphing and the unsupervised attack detection by quality

Towards understanding the character of quality sampling in deep learning face recognition

QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment

Contact Info

Product

Resources

About