2026
|
Babnik, Žiga; Peer, Peter; Štruc, Vitomir UVFace: Utility Driven Video-based Face Recognition Journal Article In: ICT Express, pp. 1–6, 2026. @article{BabnikICTEXpress,
title = {UVFace: Utility Driven Video-based Face Recognition},
author = {Žiga Babnik and Peter Peer and Vitomir Štruc},
url = {https://www.sciencedirect.com/science/article/pii/S2405959526000871/pdfft?md5=31d1362c33412d0c2455aaaffe30c0d4&pid=1-s2.0-S2405959526000871-main.pdf},
doi = {https://doi.org/10.1016/j.icte.2026.05.014},
year = {2026},
date = {2026-06-09},
urldate = {2026-06-09},
journal = {ICT Express},
pages = {1--6},
abstract = {Face recognition methods are primarily designed for single-image analysis, even though video-based recognition has seen a dramatic increase in popularity in edge security and surveillance applications. Typically, a video template is constructed from the features of individual frames. Feature norms are commonly used as weights in the construction process, as they correlate well with the usefulness of samples for recognition. Classical training approaches directly optimize only the angular distances, in turn also guiding the feature norms. This can lead to suboptimal alignment between feature norms and the usefulness (utility) of samples, resulting in subpar video performance. Motivated by this insight, we propose the UVFace methodology, which presents an extended feature norm alignment branch. Through careful design of the quality ranking step, which produces feature norm labels and a new feature norm loss, UVFace improves performance over the reproduced AdaFace baseline on video-oriented benchmarks while retaining strong image-based performance. Code is available at https://github.com/LSIbabnikz/UVFace},
keywords = {biometrics, CNN, deep learning, face image quality assessment, face images, face recognition, video based recognition},
pubstate = {published},
tppubtype = {article}
}
Face recognition methods are primarily designed for single-image analysis, even though video-based recognition has seen a dramatic increase in popularity in edge security and surveillance applications. Typically, a video template is constructed from the features of individual frames. Feature norms are commonly used as weights in the construction process, as they correlate well with the usefulness of samples for recognition. Classical training approaches directly optimize only the angular distances, in turn also guiding the feature norms. This can lead to suboptimal alignment between feature norms and the usefulness (utility) of samples, resulting in subpar video performance. Motivated by this insight, we propose the UVFace methodology, which presents an extended feature norm alignment branch. Through careful design of the quality ranking step, which produces feature norm labels and a new feature norm loss, UVFace improves performance over the reproduced AdaFace baseline on video-oriented benchmarks while retaining strong image-based performance. Code is available at https://github.com/LSIbabnikz/UVFace |
Kolf, Jan Niklas; Ozgur, Guray; Atzori, Andrea; Babnik, Žiga; Štruc, Vitomir; Damer, Naser; Boutros, Fadi PreFIQs: Face Image Quality Is What Survives Pruning Proceedings Article In: Proceedings of CVPR Workshops 2026 - CVPR Biometrics Workshop, pp. 1–11, 2026. @inproceedings{PreFIQCVPRW,
title = {PreFIQs: Face Image Quality Is What Survives Pruning},
author = {Jan Niklas Kolf and Guray Ozgur and Andrea Atzori and Žiga Babnik and Vitomir Štruc and Naser Damer and Fadi Boutros},
url = {https://openaccess.thecvf.com/content/CVPR2026W/BIOM2026/papers/Kolf_PreFIQs_Face_Image_Quality_Is_What_Survives_Pruning_CVPRW_2026_paper.pdf},
year = {2026},
date = {2026-06-06},
booktitle = {Proceedings of CVPR Workshops 2026 - CVPR Biometrics Workshop},
pages = {1--11},
abstract = {Face Image Quality Assessment (FIQA) evaluates the utility of a face image for automated face recognition (FR) systems. In this work, we propose PreFIQs, an unsupervised and training-free FIQA framework grounded in the Pruning Identified Exemplar (PIE) hypothesis. We hypothesize that low-utility face images rely disproportionately on fragile network parameters, resulting in larger geometric displacement of their embeddings under model sparsification. Accordingly, PreFIQs quantifies image utility as the Euclidean distance between L2-normalized embeddings extracted from a pre-trained FR model and its pruned counterpart. We provide a first-order theoretical justification via a Jacobian-vector product analysis, demonstrating that this empirical drift serves as a computationally efficient approximation of the exact geometric sensitivity of the latent embedding manifold. Extensive experiments across eight benchmarks and four FR models demonstrate that PreFIQs achieves competitive or superior performance compared to state-of-the-art FIQA methods, including establishing new state-of-the-art results on several benchmarks, without any training or supervision. These results validate parameter sparsification as a principled and practically efficient signal for face image utility, and demonstrate that quality is, in essence, what survives pruning. Code available at https://github.com/jankolf/PreFIQs.},
keywords = {biometrics, deep learning, face image quality assessment, face quality, face recognition, FIQA},
pubstate = {published},
tppubtype = {inproceedings}
}
Face Image Quality Assessment (FIQA) evaluates the utility of a face image for automated face recognition (FR) systems. In this work, we propose PreFIQs, an unsupervised and training-free FIQA framework grounded in the Pruning Identified Exemplar (PIE) hypothesis. We hypothesize that low-utility face images rely disproportionately on fragile network parameters, resulting in larger geometric displacement of their embeddings under model sparsification. Accordingly, PreFIQs quantifies image utility as the Euclidean distance between L2-normalized embeddings extracted from a pre-trained FR model and its pruned counterpart. We provide a first-order theoretical justification via a Jacobian-vector product analysis, demonstrating that this empirical drift serves as a computationally efficient approximation of the exact geometric sensitivity of the latent embedding manifold. Extensive experiments across eight benchmarks and four FR models demonstrate that PreFIQs achieves competitive or superior performance compared to state-of-the-art FIQA methods, including establishing new state-of-the-art results on several benchmarks, without any training or supervision. These results validate parameter sparsification as a principled and practically efficient signal for face image utility, and demonstrate that quality is, in essence, what survives pruning. Code available at https://github.com/jankolf/PreFIQs. |
Babnik, Žiga; Boutros, Fadi; Damer, Naser; Jain, Deepak Kumar; Peer, Peter; Štruc, Vitomir FunFace: Feature Utility and Norm Estimation for Face Recognition Proceedings Article In: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, pp. 1–10, 2026. @inproceedings{FG2026_FunFace,
title = {FunFace: Feature Utility and Norm Estimation for Face Recognition},
author = {Žiga Babnik and Fadi Boutros and Naser Damer and Deepak Kumar Jain and Peter Peer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/04/qFR_paper.pdf},
year = {2026},
date = {2026-05-24},
urldate = {2026-05-24},
booktitle = {Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition},
pages = {1--10},
abstract = {Face Recognition (FR) is used in a variety of application domains, from entertainment and banking to security, and surveillance. Such applications rely on the FR model to be robust and perform well in a variety of settings. To achieve this, state-of-the-art FR models typically use expressive adaptive margin loss functions, which tie the feature norm to concepts related to sample quality, such as recognizability and perceptual image quality. Recently, through the development of Face Image Quality Assessment (FIQA) techniques, biometric utility has become the preferred measure of face-image quality and has been shown to be a better predictor of the usefulness of samples for face recognition compared to more human-centric aspects, such as resolution, blur, and lighting, tied to general image quality. While image quality expressed through feature norms exhibits a certain level of correlation with biometric utility, it does not fully encapsulate all aspects of utility. To address this point, we propose a new adaptive margin loss, FunFace (Face Recognition Through Utility and Norm Estimation), which incorporates biometric utility, estimated by the Certainty Ratio, into the adaptive margin, taking inspiration from AdaFace. We show that FunFace (when used to train a face recognition model) achieves competitive results to other state-of-the-art FR models on benchmarks containing high-quality samples, while surpassing them on low quality benchmarks.},
keywords = {face image processing, face image quality assessment, face image quality estimation, face images, face recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Face Recognition (FR) is used in a variety of application domains, from entertainment and banking to security, and surveillance. Such applications rely on the FR model to be robust and perform well in a variety of settings. To achieve this, state-of-the-art FR models typically use expressive adaptive margin loss functions, which tie the feature norm to concepts related to sample quality, such as recognizability and perceptual image quality. Recently, through the development of Face Image Quality Assessment (FIQA) techniques, biometric utility has become the preferred measure of face-image quality and has been shown to be a better predictor of the usefulness of samples for face recognition compared to more human-centric aspects, such as resolution, blur, and lighting, tied to general image quality. While image quality expressed through feature norms exhibits a certain level of correlation with biometric utility, it does not fully encapsulate all aspects of utility. To address this point, we propose a new adaptive margin loss, FunFace (Face Recognition Through Utility and Norm Estimation), which incorporates biometric utility, estimated by the Certainty Ratio, into the adaptive margin, taking inspiration from AdaFace. We show that FunFace (when used to train a face recognition model) achieves competitive results to other state-of-the-art FR models on benchmarks containing high-quality samples, while surpassing them on low quality benchmarks. |
2025
|
Babnik, Žiga; Štruc, Vitomir Delno nadzorovano ocenjevanje kakovosti obraznih slik Proceedings Article In: Proceedings of ERK 2025, 2025. @inproceedings{Babnik_ERK25,
title = {Delno nadzorovano ocenjevanje kakovosti obraznih slik},
author = {Žiga Babnik and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/11/ERK25.pdf},
year = {2025},
date = {2025-09-25},
booktitle = {Proceedings of ERK 2025},
abstract = {Important security and surveillance applications often depend on reliable predictions from the underlying face recognition (FR) models. Due to the nature of such applications FR models have to perform well in various unconstrained conditions. While state-of-the-art FR models achieve excellent results on large and varied closed set benchmarks, their performance depends heavily on the quality of the input face samples. Low-quality samples can cause critical false-match errors, lowering the trustworthiness of FR models, and furthermore lead to
monetary or privacy issues. Face Image Quality Assessment (FIQA) techniques offer the FR model an estimate of the sample’s quality, allowing the system to reject samples of poor quality. Supervised state-of-the-art FIQA techniques rely on extensive training to accurately assess the sample quality. Alternatively, unsupervised techniques extract the quality directly from the input sample, achieving higher runtime complexity and worse performance. In this paper, we present a technique for quality
estimation, combining desired characteristics of both supervised and unsupervised methods. Our technique is able to quickly estimate the quality using a single forward pass of the sample through the model needed also for recognition, without any prior supervised training. Comprehensive experiments on a varied set of benchmark datasets and face recognition models show that our method outperforms all existing unsupervised techniques and performs similarly to current state-of-the-art supervised techniques, while achieving excellent runtime.},
keywords = {face analysis, face image quality assessment, face images, face recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Important security and surveillance applications often depend on reliable predictions from the underlying face recognition (FR) models. Due to the nature of such applications FR models have to perform well in various unconstrained conditions. While state-of-the-art FR models achieve excellent results on large and varied closed set benchmarks, their performance depends heavily on the quality of the input face samples. Low-quality samples can cause critical false-match errors, lowering the trustworthiness of FR models, and furthermore lead to
monetary or privacy issues. Face Image Quality Assessment (FIQA) techniques offer the FR model an estimate of the sample’s quality, allowing the system to reject samples of poor quality. Supervised state-of-the-art FIQA techniques rely on extensive training to accurately assess the sample quality. Alternatively, unsupervised techniques extract the quality directly from the input sample, achieving higher runtime complexity and worse performance. In this paper, we present a technique for quality
estimation, combining desired characteristics of both supervised and unsupervised methods. Our technique is able to quickly estimate the quality using a single forward pass of the sample through the model needed also for recognition, without any prior supervised training. Comprehensive experiments on a varied set of benchmark datasets and face recognition models show that our method outperforms all existing unsupervised techniques and performs similarly to current state-of-the-art supervised techniques, while achieving excellent runtime. |
Babnik, Žiga; Jain, Deepak Kumar; Peer, Peter; Štruc, Vitomir FROQ: Observing Face Recognition Models for Efficient Quality Assessment Proceedings Article In: Proceedings of the IEEE International Joint Conference On Biometrics (IJCB), pp. 1–10, IEEE 2025. @inproceedings{BabnikIJCB25,
title = {FROQ: Observing Face Recognition Models for Efficient Quality Assessment},
author = {Žiga Babnik and Deepak Kumar Jain and Peter Peer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/08/IJCB_25.pdf
https://arxiv.org/pdf/2509.17689?},
year = {2025},
date = {2025-09-08},
urldate = {2025-09-08},
booktitle = {Proceedings of the IEEE International Joint Conference On Biometrics (IJCB)},
pages = {1--10},
organization = {IEEE},
abstract = {Face Recognition (FR) plays a crucial role in many critical (high-stakes) applications, where errors in the recognition process can lead to serious consequences. Face Image Quality Assessment (FIQA) techniques enhance FR systems by providing quality estimates of face samples, enabling the systems to discard samples that are unsuitable for reliable recognition or lead to low-confidence recognition decisions. Most state-of-the-art FIQA techniques rely on extensive supervised training to achieve accurate quality estimation. In contrast, unsupervised techniques eliminate the need for additional training but tend to be slower and typically exhibit lower performance. In this paper, we introduce FROQ (Face Recognition Observer of Quality), a semi-supervised, training-free approach that leverages specific intermediate representations within a given FR model to estimate face-image quality, and combines the efficiency of supervised FIQA models with the training-free approach of unsupervised methods. A simple calibration step based on pseudo-quality labels allows FROQ to uncover specific representations, useful for quality assessment, in any modern FR model. To generate these pseudo-labels, we propose a novel unsupervised FIQA technique based on sample perturbations. Comprehensive experiments with four state-of-the-art FR models and eight benchmark datasets show that FROQ leads to highly competitive results compared to the state-of-the-art, achieving both strong performance and efficient runtime, without requiring explicit training. The code for FROQ is available from: https://github.com/LSIbabnikz/FROQ},
keywords = {biometrics, face image quality assessment, face recognition, FIQA},
pubstate = {published},
tppubtype = {inproceedings}
}
Face Recognition (FR) plays a crucial role in many critical (high-stakes) applications, where errors in the recognition process can lead to serious consequences. Face Image Quality Assessment (FIQA) techniques enhance FR systems by providing quality estimates of face samples, enabling the systems to discard samples that are unsuitable for reliable recognition or lead to low-confidence recognition decisions. Most state-of-the-art FIQA techniques rely on extensive supervised training to achieve accurate quality estimation. In contrast, unsupervised techniques eliminate the need for additional training but tend to be slower and typically exhibit lower performance. In this paper, we introduce FROQ (Face Recognition Observer of Quality), a semi-supervised, training-free approach that leverages specific intermediate representations within a given FR model to estimate face-image quality, and combines the efficiency of supervised FIQA models with the training-free approach of unsupervised methods. A simple calibration step based on pseudo-quality labels allows FROQ to uncover specific representations, useful for quality assessment, in any modern FR model. To generate these pseudo-labels, we propose a novel unsupervised FIQA technique based on sample perturbations. Comprehensive experiments with four state-of-the-art FR models and eight benchmark datasets show that FROQ leads to highly competitive results compared to the state-of-the-art, achieving both strong performance and efficient runtime, without requiring explicit training. The code for FROQ is available from: https://github.com/LSIbabnikz/FROQ |
2024
|
Babnik, Žiga; Boutros, Fadi; Damer, Naser; Peer, Peter; Štruc, Vitomir AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation Proceedings Article In: Proceedings of the International Workshop on Biometrics and Forensics (IWBF), pp. 1-6, 2024. @inproceedings{Babnik_IWBF2024,
title = {AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation},
author = {Žiga Babnik and Fadi Boutros and Naser Damer and Peter Peer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/03/iwbf2024_fiq.pdf},
year = {2024},
date = {2024-04-10},
urldate = {2024-04-10},
booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},
pages = {1-6},
abstract = {Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD.},
keywords = {ai, CNN, deep learning, face, face image quality assessment, face image quality estimation, face images, face recognition, face verification},
pubstate = {published},
tppubtype = {inproceedings}
}
Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD. |
2023
|
Babnik, Žiga; Damer, Naser; Štruc, Vitomir Optimization-Based Improvement of Face Image Quality Assessment Techniques Proceedings Article In: Proceedings of the International Workshop on Biometrics and Forensics (IWBF), 2023. @inproceedings{iwbf2023babnik,
title = {Optimization-Based Improvement of Face Image Quality Assessment Techniques},
author = {Žiga Babnik and Naser Damer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/03/IWBF_23___paper-1.pdf},
year = {2023},
date = {2023-02-28},
booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},
abstract = {Contemporary face recognition~(FR) models achieve near-ideal recognition performance in constrained settings, yet do not fully translate the performance to unconstrained (real-world) scenarios. To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. While existing FIQA techniques are able to efficiently capture the differences between high and low quality images, they typically cannot fully distinguish between images of similar quality, leading to lower performance in many scenarios. To address this issue, we present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. The developed optimization procedure infuses additional information (computed with a selected FR model) into the initial quality scores generated with a given FIQA technique to produce better estimates of the ``actual'' image quality. We evaluate the proposed approach in comprehensive experiments with six state-of-the-art FIQA approaches (CR-FIQA, FaceQAN, SER-FIQ, PCNet, MagFace, SER-FIQ) on five commonly used benchmarks (LFW, CFP-FP, CPLFW, CALFW, XQLFW) using three targeted FR models (ArcFace, ElasticFace, CurricularFace) with highly encouraging results. },
keywords = {distillation, face, face image quality assessment, face image quality estimation, face images, optimization, quality, transfer learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Contemporary face recognition~(FR) models achieve near-ideal recognition performance in constrained settings, yet do not fully translate the performance to unconstrained (real-world) scenarios. To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. While existing FIQA techniques are able to efficiently capture the differences between high and low quality images, they typically cannot fully distinguish between images of similar quality, leading to lower performance in many scenarios. To address this issue, we present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. The developed optimization procedure infuses additional information (computed with a selected FR model) into the initial quality scores generated with a given FIQA technique to produce better estimates of the ``actual'' image quality. We evaluate the proposed approach in comprehensive experiments with six state-of-the-art FIQA approaches (CR-FIQA, FaceQAN, SER-FIQ, PCNet, MagFace, SER-FIQ) on five commonly used benchmarks (LFW, CFP-FP, CPLFW, CALFW, XQLFW) using three targeted FR models (ArcFace, ElasticFace, CurricularFace) with highly encouraging results. |
Eyiokur, Fevziye Irem; Kantarci, Alperen; Erakin, Mustafa Ekrem; Damer, Naser; Ofli, Ferda; Imran, Muhammad; Križaj, Janez; Salah, Albert Ali; Waibel, Alexander; Štruc, Vitomir; Ekenel, Hazim K. A Survey on Computer Vision based Human Analysis in the COVID-19 Era Journal Article In: Image and Vision Computing, vol. 130, no. 104610, pp. 1-19, 2023. @article{IVC2023,
title = {A Survey on Computer Vision based Human Analysis in the COVID-19 Era},
author = {Fevziye Irem Eyiokur and Alperen Kantarci and Mustafa Ekrem Erakin and Naser Damer and Ferda Ofli and Muhammad Imran and Janez Križaj and Albert Ali Salah and Alexander Waibel and Vitomir Štruc and Hazim K. Ekenel },
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/01/FG4COVID19_PAPER_compressed.pdf
https://authors.elsevier.com/a/1gKOyxnVK7RBS},
doi = {https://doi.org/10.1016/j.imavis.2022.104610},
year = {2023},
date = {2023-01-01},
journal = {Image and Vision Computing},
volume = {130},
number = {104610},
pages = {1-19},
abstract = {The emergence of COVID-19 has had a global and profound impact, not only on society as a whole, but also on the lives of individuals. Various prevention measures were introduced around the world to limit the transmission of the disease, including
face masks, mandates for social distancing and regular disinfection in public spaces, and the use of screening applications. These developments also triggered the need for novel and improved computer vision techniques capable of (i) providing support to the prevention measures through an automated analysis of visual data, on the one hand, and (ii) facilitating normal operation of existing vision-based services, such as biometric authentication schemes, on the other. Especially important here, are computer vision techniques that focus on the analysis of people and faces in visual data and have been affected the most by the partial occlusions introduced by the mandates for facial masks.
Such computer vision based human analysis techniques include face and face-mask detection approaches, face recognition techniques, crowd counting solutions, age and expression estimation procedures, models for detecting face-hand interactions and many others, and have seen considerable attention over recent years. The goal of this survey is to provide an introduction to the problems induced by COVID-19 into such research and to present a comprehensive review of the work done in the computer vision based human analysis field. Particular attention is paid to the impact of facial masks on the performance of various methods and recent solutions to mitigate this problem. Additionally, a detailed review of existing datasets useful for the development and evaluation of methods for COVID-19 related applications is also provided. Finally, to help advance the field further, a discussion on the main open challenges and future research direction is given at the end of the survey. This work is intended to have a broad appeal and be useful not only for computer vision researchers but also the general public.},
keywords = {COVID-19, face, face alignment, face analysis, face image processing, face image quality assessment, face landmarking, face recognition, face verification, human analysis, masked face analysis},
pubstate = {published},
tppubtype = {article}
}
The emergence of COVID-19 has had a global and profound impact, not only on society as a whole, but also on the lives of individuals. Various prevention measures were introduced around the world to limit the transmission of the disease, including
face masks, mandates for social distancing and regular disinfection in public spaces, and the use of screening applications. These developments also triggered the need for novel and improved computer vision techniques capable of (i) providing support to the prevention measures through an automated analysis of visual data, on the one hand, and (ii) facilitating normal operation of existing vision-based services, such as biometric authentication schemes, on the other. Especially important here, are computer vision techniques that focus on the analysis of people and faces in visual data and have been affected the most by the partial occlusions introduced by the mandates for facial masks.
Such computer vision based human analysis techniques include face and face-mask detection approaches, face recognition techniques, crowd counting solutions, age and expression estimation procedures, models for detecting face-hand interactions and many others, and have seen considerable attention over recent years. The goal of this survey is to provide an introduction to the problems induced by COVID-19 into such research and to present a comprehensive review of the work done in the computer vision based human analysis field. Particular attention is paid to the impact of facial masks on the performance of various methods and recent solutions to mitigate this problem. Additionally, a detailed review of existing datasets useful for the development and evaluation of methods for COVID-19 related applications is also provided. Finally, to help advance the field further, a discussion on the main open challenges and future research direction is given at the end of the survey. This work is intended to have a broad appeal and be useful not only for computer vision researchers but also the general public. |
2022
|
Babnik, Žiga; Peer, Peter; Štruc, Vitomir FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration Proceedings Article In: IAPR International Conference on Pattern Recognition (ICPR), 2022. @inproceedings{ICPR2022,
title = {FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration},
author = {Žiga Babnik and Peter Peer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/ICPR_2022___paper-17.pdf},
year = {2022},
date = {2022-05-17},
urldate = {2022-05-17},
booktitle = {IAPR International Conference on Pattern Recognition (ICPR)},
abstract = {Recent state-of-the-art face recognition (FR) approaches have achieved impressive performance, yet unconstrained face recognition still represents an open problem. Face image quality assessment (FIQA) approaches aim to estimate the quality of the input samples that can help provide information on the confidence of the recognition decision and eventually lead to improved results in challenging scenarios. While much progress has been made in face image quality assessment in recent years, computing reliable quality scores for diverse facial images and FR models remains challenging. In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent. As such, the proposed approach is the first to link image quality to adversarial attacks. Comprehensive (cross-model as well as model-specific) experiments are conducted with four benchmark datasets, i.e., LFW, CFP–FP, XQLFW and IJB–C, four FR models, i.e., CosFace, ArcFace, CurricularFace and ElasticFace and in comparison to seven state-of-the-art FIQA methods to demonstrate the performance of FaceQAN. Experimental results show that FaceQAN achieves competitive results, while exhibiting several desirable characteristics. The source code for FaceQAN will be made publicly available.},
keywords = {adversarial examples, adversarial noise, biometrics, face image quality assessment, face recognition, FIQA, image quality assessment},
pubstate = {published},
tppubtype = {inproceedings}
}
Recent state-of-the-art face recognition (FR) approaches have achieved impressive performance, yet unconstrained face recognition still represents an open problem. Face image quality assessment (FIQA) approaches aim to estimate the quality of the input samples that can help provide information on the confidence of the recognition decision and eventually lead to improved results in challenging scenarios. While much progress has been made in face image quality assessment in recent years, computing reliable quality scores for diverse facial images and FR models remains challenging. In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent. As such, the proposed approach is the first to link image quality to adversarial attacks. Comprehensive (cross-model as well as model-specific) experiments are conducted with four benchmark datasets, i.e., LFW, CFP–FP, XQLFW and IJB–C, four FR models, i.e., CosFace, ArcFace, CurricularFace and ElasticFace and in comparison to seven state-of-the-art FIQA methods to demonstrate the performance of FaceQAN. Experimental results show that FaceQAN achieves competitive results, while exhibiting several desirable characteristics. The source code for FaceQAN will be made publicly available. |
Babnik, Žiga; Štruc, Vitomir Assessing Bias in Face Image Quality Assessment Proceedings Article In: EUSIPCO 2022, 2022. @inproceedings{EUSIPCO_2022,
title = {Assessing Bias in Face Image Quality Assessment},
author = {Žiga Babnik and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/EUSIPCO_2022___paper.pdf},
year = {2022},
date = {2022-05-16},
urldate = {2022-05-16},
booktitle = {EUSIPCO 2022},
abstract = {Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance by providing additional information about sample quality.
Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investigate the demographic biases associated with FIQA approaches, this paper presents a comprehensive study involving a variety of quality assessment methods (general-purpose image quality assessment, supervised face quality assessment, and unsupervised face quality assessment methods) and three diverse state-of-the-art FR models.
Our analysis on the Balanced Faces in the Wild (BFW) dataset shows that all techniques considered are affected more by variations in race than sex. While the general-purpose image quality assessment methods appear to be less biased with respect to the two demographic factors considered, the supervised and unsupervised face image quality assessment methods both show strong bias with a tendency to favor white individuals (of either sex). In addition, we found that methods that are less racially biased perform worse overall. This suggests that the observed bias in FIQA methods is to a significant extent related to the underlying face recognition system.},
keywords = {bias, bias analysis, biometrics, face image quality assessment, face recognition, FIQA, image quality assessment},
pubstate = {published},
tppubtype = {inproceedings}
}
Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance by providing additional information about sample quality.
Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investigate the demographic biases associated with FIQA approaches, this paper presents a comprehensive study involving a variety of quality assessment methods (general-purpose image quality assessment, supervised face quality assessment, and unsupervised face quality assessment methods) and three diverse state-of-the-art FR models.
Our analysis on the Balanced Faces in the Wild (BFW) dataset shows that all techniques considered are affected more by variations in race than sex. While the general-purpose image quality assessment methods appear to be less biased with respect to the two demographic factors considered, the supervised and unsupervised face image quality assessment methods both show strong bias with a tendency to favor white individuals (of either sex). In addition, we found that methods that are less racially biased perform worse overall. This suggests that the observed bias in FIQA methods is to a significant extent related to the underlying face recognition system. |