FaceQnet: Quality Assessment for Face Recognition based on Deep Learning

Hernandez-Ortega, Javier; Galbally, Javier; Fiérrez, Julián; Haraksim, Rudolf; Beslay, Laurent

doi:10.48550/arxiv.1904.01740

Cited by 3 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hernandez-Ortega et al created the open source FQAA "FaceQnet" v0 [50] and v1 [42]. As part of the training data preparation for both FaceQnet versions, the BioLab-ICAO framework from [23] is employed to select suitable high-quality images per subject, which are used to compute the ground truth QSs for the subjects' remaining training images.…”

Section: DL Fqa Literaturementioning

confidence: 99%

“…Removing that, the first and last layer of the network have the same dimensions as the FR embedding. Evaluations used FaceNet [119] and ArcFace [123] for FR, and selected images using QSs from both SER-FIQ variants, FaceQnet v0 [50], an approach proposed by Best-Rowden in [109], 3 general IQAAs (BRISQUE [113], NIQE [124], PIQE [125]), as well as a COTS (Neurotec Biometric SDK 11.1 [111]). The SER-FIQ "on-top model" was noted to mostly outperform all baseline approaches, and to always deliver close to top performance.…”

Section: DL Fqa Literaturementioning

confidence: 99%

“…While most of the older surveyed literature didn't appear to publish accompanying source code (irrespective of the implementation complexity), more recent deep learning FQA works tend to do so, with code being publicly available for e.g. FaceQnet [50][42], PFE (Probabilistic Face Embeddings) [49], and SER-FIQ [44]. Likewise, public datasets should preferably be used, and precise evaluation configurations could be published alongside the implementation.…”

Section: Dataset Yearmentioning

confidence: 99%

“…While this may partially stand in conflict with the goal of maximising FR-system-specific utility prediction performance, interoperability can be relevant to avoid vendor lock-in and may coincide with increased robustness. An example in the literature is the FaceQnet approach, which went from using only one FR system as part of the training process in v0 [50] to using three in v1 [42].…”

Section: B Robustness and Capabilitiesmentioning

confidence: 99%

“…RELVANT WORKS ON DL FQA. Ortega et al[42] 2020 Same as[50], but with dropout before the first fully connected layer, and multiple FR feature extractors to obtain the ground truth QSs…”

mentioning

confidence: 99%

See 4 more Smart Citations

Face Image Quality Assessment: A Literature Survey

Schlett,

Rathgeb,

Henniger

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The performance of face analysis and recognition systems depends on the quality of the acquired face data, which is influenced by numerous factors. Automatically assessing the quality of face data in terms of biometric utility can thus be useful to filter out low quality data. This survey provides an overview of the face quality assessment literature in the framework of face biometrics, with a focus on face recognition based on visible wavelength face images as opposed to e.g. depth or infrared quality assessment. A trend towards deep learning based methods is observed, including notable conceptual differences among the recent approaches. Besides image selection, face image quality assessment can also be used in a variety of other application scenarios, which are discussed herein. Open issues and challenges are pointed out, i.a. highlighting the importance of comparability for algorithm evaluations, and the challenge for future work to create deep learning approaches that are interpretable in addition to providing accurate utility predictions.

show abstract

Section: DL Fqa Literaturementioning

confidence: 99%

Section: DL Fqa Literaturementioning

confidence: 99%

Section: Dataset Yearmentioning

confidence: 99%

Section: B Robustness and Capabilitiesmentioning

confidence: 99%

“…RELVANT WORKS ON DL FQA. Ortega et al[42] 2020 Same as[50], but with dropout before the first fully connected layer, and multiple FR feature extractors to obtain the ground truth QSs…”

mentioning

confidence: 99%

See 3 more Smart Citations

Face Image Quality Assessment: A Literature Survey

Schlett,

Rathgeb,

Henniger

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

FF-PPQA: Face frontalization without glasses based on perceptual quality and pixel-level quality assessment

Liu,

Duan,

Liang

2024

SIViP

View full text Add to dashboard Cite

Face Image Quality Assessment: A Literature Survey

et al. 2022

Self Cite

View full text Add to dashboard Cite

The performance of face analysis and recognition systems depends on the quality of the acquired face data, which is influenced by numerous factors. Automatically assessing the quality of face data in terms of biometric utility can thus be useful to detect low-quality data and make decisions accordingly. This survey provides an overview of the face image quality assessment literature, which predominantly focuses on visible wavelength face image input. A trend towards deep learning based methods is observed, including notable conceptual differences among the recent approaches, such as the integration of quality assessment into face recognition models. Besides image selection, face image quality assessment can also be used in a variety of other application scenarios, which are discussed herein. Open issues and challenges are pointed out, i.a. highlighting the importance of comparability for algorithm evaluations, and the challenge for future work to create deep learning approaches that are interpretable in addition to providing accurate utility predictions.

show abstract

FaceQnet: Quality Assessment for Face Recognition based on Deep Learning

Cited by 3 publications

References 0 publications

Face Image Quality Assessment: A Literature Survey

Face Image Quality Assessment: A Literature Survey

FF-PPQA: Face frontalization without glasses based on perceptual quality and pixel-level quality assessment

Face Image Quality Assessment: A Literature Survey

Contact Info

Product

Resources

About