Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors

The main question this work aims at answering is: can morphing attack detection (MAD) solutions be successfully developed based on synthetic data?. Towards that, this work introduces the first synthetic-based MAD development dataset, namely the Synthetic Morphing Attack Detection Development dataset (SMDD). This dataset is utilized successfully to train three MAD backbones where it proved to lead to high MAD performance, even on completely unknown attack types. Additionally, an essential aspect of this work is the detailed legal analyses of the challenges of using and sharing real biometric data, rendering our proposed SMDD dataset extremely essential. The SMDD dataset, consisting of 30,000 attack and 50,000 bona fide samples, is made publicly available for research purposes.

CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

The quality of face images significantly influences the performance of underlying face recognition algorithms. Face image quality assessment (FIQA) estimates the utility of the captured image in achieving reliable and accurate recognition performance. In this work, we propose a novel learning paradigm that learns internal network observations during the training process. Based on that, our proposed CR-FIQA uses this paradigm to estimate the face image quality of a sample by predicting its relative classifiability. This classifiability is measured based on the allocation of the training sample feature representation in angular space with respect to its class center and the nearest negative class center. We experimentally illustrate the correlation between the face image quality and the sample relative classifiability. As such property is only observable for the training dataset, we propose to learn this property from the training dataset and utilize it to predict the quality measure on unseen samples. This training is performed simultaneously while optimizing the class centers by an angular margin penalty-based softmax loss used for face recognition model training. Through extensive evaluation experiments on eight benchmarks and four face recognition models, we demonstrate the superiority of our proposed CR-FIQA over state-of-the-art (SOTA) FIQA algorithms.

Mask-invariant Face Recognition through Template-level Knowledge Distillation

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent wearing of masks. These masks affect the performance of previous face recognition systems, as they hide important identity information. In this paper, we propose a mask-invariant face recognition solution (MaskInv) that utilizes template-level knowledge distillation within a training paradigm that aims at producing embeddings of masked faces that are similar to those of non-masked faces of the same identities. In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss, ElasticFace, using masked and non-masked faces. In a step-wise ablation study on two real masked face databases and five mainstream databases with synthetic masks, we prove the rationalization of our MaskInv approach. Our proposed solution outperforms previous state-of-the-art (SOTA) academic solutions in the recent MFRC-21 challenge in both scenarios, masked vs masked and masked vs non-masked, and also outperforms the previous solution on the MFR2 dataset. Furthermore, we demonstrate that the proposed model can still perform well on unmasked faces with only a minor loss in verification performance. The code, the trained models, as well as the evaluation protocol on the synthetically masked data are publicly available: https://github.com/fdbtrs/Masked-Face-Recognition-KD.

Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models

It is challenging to derive explainability for unsupervised or statistical-based face image quality assessment (FIQA) methods. In this work, we propose a novel set of explainability tools to derive reasoning for different FIQA decisions and their face recognition (FR) performance implications. We avoid limiting the deployment of our tools to certain FIQA methods by basing our analyses on the behavior of FR models when processing samples with different FIQA decisions. This leads to explainability tools that can be applied for any FIQA method with any CNN-based FR solution using activation mapping to exhibit the network's activation derived from the face embedding. To avoid the low discrimination between the general spatial activation mapping of low and high-quality images in FR models, we build our explainability tools in a higher derivative space by analyzing the variation of the FR activation maps of image sets with different quality decisions. We demonstrate our tools and analyze the findings on four FIQA methods, by presenting inter and intra-FIQA method analyses. Our proposed tools and the analyses based on them point out, among other conclusions, that high-quality images typically cause consistent low activation on the areas outside of the central face region, while low-quality images, despite general low activation, have high variations of activation in such areas. Our explainability tools also extend to analyzing single images where we show that low-quality images tend to have an FR model spatial activation that strongly differs from what is expected from a high-quality image where this difference also tends to appear more in areas outside of the central face region and does correspond to issues like extreme poses and facial occlusions. The implementation of the proposed tools is accessible here [link].

QMagFace: Simple and Accurate Quality-Aware Face Recognition

Face recognition systems have to deal with large variabilities (such as different poses, illuminations, and expressions) that might lead to incorrect matching decisions. These variabilities can be measured in terms of face image quality which is defined over the utility of a sample for recognition. Previous works on face recognition either do not employ this valuable information or make use of non-inherently fit quality estimates. In this work, we propose a simple and effective face recognition solution (QMag-Face) that combines a quality-aware comparison score with a recognition model based on a magnitude-aware angular margin loss. The proposed approach includes model-specific face image qualities in the comparison process to enhance the recognition performance under unconstrained circumstances. Exploiting the linearity between the qualities and their comparison scores induced by the utilized loss, our quality-aware comparison function is simple and highly generalizable. The experiments conducted on several face recognition databases and benchmarks demonstrate that the introduced quality-awareness leads to consistent improvements in the recognition performance. Moreover, the proposed QMagFace approach performs especially well under challenging circumstances, such as cross-pose, cross-age, or cross-quality. Consequently, it leads to state-of-the-art performances on several face recognition benchmarks, such as 98.50% on AgeDB, 83.95% on XQLFQ, and 98.74% on CFP-FP. The code for QMagFace is publicly available

Partial Attack Supervision and Regional Weighted Inference for Masked Face Presentation Attack Detection

Wearing a mask has proven to be one of the most effective ways to prevent the transmission of SARS-CoV-2 coronavirus. However, wearing a mask poses challenges for different face recognition tasks and raises concerns about the performance of masked face presentation detection (PAD). The main issues facing the mask face PAD are the wrongly classified bona fide masked faces and the wrongly classified partial attacks (covered by real masks). This work addresses these issues by proposing a method that considers partial attack labels to supervise the PAD model training, as well as regional weighted inference to further improve the PAD performance by varying the focus on different facial areas. Our proposed method is not directly linked to specific network architecture and thus can be directly incorporated into any common or custom-designed network. In our work, two neural networks (DeepPixBis and MixFaceNet) are selected as backbones. The experiments are demonstrated on the collaborative real mask attack (CRMA) database. Our proposed method outperforms established PAD methods in the CRMA database by reducing the mentioned shortcomings when facing masked faces. Moreover, we present a detailed step-wise ablation study pointing out the individual and joint benefits of the proposed concepts on the overall PAD performance.

Pixel-Level Face Image Quality Assessment for Explainable Face Recognition

An essential factor to achieve high performance in face recognition systems is the quality of its samples. Since these systems are involved in various daily life there is a strong need of making face recognition processes understandable for humans. In this work, we introduce the concept of pixel-level face image quality that determines the utility of pixels in a face image for recognition. Given an arbitrary face recognition network, in this work, we propose a training-free approach to assess the pixel-level qualities of a face image. To achieve this, a model-specific quality value of the input image is estimated and used to build a sample-specific quality regression model. Based on this model, quality-based gradients are back-propagated and converted into pixel-level quality estimates. In the experiments, we qualitatively and quantitatively investigated the meaningfulness of the pixel-level qualities based on real and artificial disturbances and by comparing the explanation maps on ICAO-incompliant faces. In all scenarios, the results demonstrate that the proposed solution produces meaningful pixel-level qualities. The code is publicly available.

The Effect of Wearing a Face Mask on Face Image Quality

Due to the COVID-19 situation, face masks have become a main part of our daily life. Wearing mouth-and-nose protection has been made a mandate in many public places, to prevent the spread of the COVID-19 virus. However, face masks affect the performance of face recognition, since a large area of the face is covered. The effect of wearing a face mask on the different components of the face recognition system in a collaborative environment is a problem that is still to be fully studied. This work studies, for the first time, the effect of wearing a face mask on face image quality by utilising state-of-the-art face image quality assessment methods of different natures. This aims at providing better understanding on the effect of face masks on the operation of face recognition as a whole system. In addition, we further studied the effect of simulated masks on face image utility in comparison to real face masks. We discuss the correlation between the mask effect on face image quality and that on the face verification performance by automatic systems and human experts, indicating a consistent trend between both factors. The evaluation is conducted on the database containing (1) no-masked faces, (2) real face masks, and (3) simulated face masks, by synthetically generating digital facial masks on no-masked faces. Finally, a visual interpretation of the face areas contributing to the quality score of a selected set of quality assessment methods is provided to give a deeper insight into the difference of network decisions in masked and non-masked faces, among other variations.

FocusFace: Multi-task Contrastive Learning for Masked Face Recognition

SARS-CoV-2 has presented direct and indirect challenges to the scientific community. One of the most prominent indirect challenges advents from the mandatory use of face masks in a large number of countries. Face recognition methods struggle to perform identity verification with similar accuracy on masked and unmasked individuals. It has been shown that the performance of these methods drops considerably in the presence of face masks, especially if the reference image is unmasked. We propose FocusFace, a multi-task architecture that uses contrastive learning to be able to accurately perform masked face recognition. The proposed architecture is designed to be trained from scratch or to work on top of state-of-the-art face recognition methods without sacrificing the capabilities of a existing models in conventional face recognition tasks. We also explore different approaches to design the contrastive learning module. Results are presented in terms of masked-masked (M-M) and unmasked-masked (U-M) face verification performance. For both settings, the results are on par with published methods, but for M-M specifically, the proposed method was able to outperform all the solutions that it was compared to. We further show that when using our method on top of already existing methods the training computational costs decrease significantly while retaining similar performances. The implementation and the trained models are available at GitHub.

A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics

Quality scores provide a measure to evaluate the utility of biometric samples for biometric recognition. Biometric recognition systems require high-quality samples to achieve optimal performance. This paper focuses on face images and the measurement of face image utility with general and face-specific image quality metrics. While face-specific metrics rely on features of aligned face images, general image quality metrics can be used on the global image and relate to human perceptions. In this paper, we analyze the gap between the general image quality metrics and the face image quality metrics. Our contribution lies in a thorough examination of how different the image quality assessment algorithms relate to the utility for the face recognition task. The results of image quality assessment algorithms are further compared with those of dedicated face image quality assessment algorithms. In total, 25 different quality metrics are evaluated on three face image databases, BioSecure, LFW, and VGGFace2 using three open-source face recognition solutions, SphereFace, ArcFace, and FaceNet. Our results reveal a clear correlation between learned image metrics to face image utility even without being specifically trained as a face utility measure. Individual handcrafted features lack general stability and perform significantly worse than general face-specific quality metrics. We additionally provide a visual insight into the image areas contributing to the quality score of a selected set of quality assessment methods.