MFR 2021: Masked Face Recognition Competition

Boutros, Fadi; Damer, Naser; Kolf, Jan Niklas; Raja, Kiran B.; Kirchbuchner, Florian; Ramachandra, Raghavendra; Kuijper, Arjan; Fang, Pengcheng; Zhang, Chao; Wang, Fei; Montero, David; Aginako, Naiara; Sierra, Basilio; Nieto, Marcos; Erakin, Mustafa Ekrem; Demir, Uğur; Ekenel, Hazım Kemal; Kataoka, Asaki; Ichikawa, K; Kubo, Sachio; Zhang, Jie; He, Mingjie; Han, Dan; Shan, Shiguang; Grm, Klemen; Štruc, Vitomir; Seneviratne, Sachith; Kasthuriarachchi, Nuran; Rasnayaka, Sanka; Neto, Pedro C.; Sequeira, Ana F.; Pinto, João Ribeiro; Saffari, Mohsen; Cardoso, Jaime S.

doi:10.1109/ijcb52358.2021.9484337

Cited by 39 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of trainable parameters in ResNet-34 and ResNet-18 is 21.3 million (m) and 11.8 m, respectively. Additionally, ResNet proposed the use of a small filter size of (32,16,8) In this work, we deployed ResNet-34 and ResNet-18 as teacher networks and the compact ResNet-110 as a student, as well as a stand-alone baseline. In order to adopt these models for periocular verification, we modified the number of classes in the classification layer to match the number of identities in our training dataset.…”

Section: Baseline Modelsmentioning

confidence: 99%

“…These studies [9][10][11] concluded that the verification performance of face-recognition solutions significantly degraded when the subject was wearing a face mask, compared to the case where their face was unmasked. This was followed by several efforts to enhance masked face recognition [13][14][15], including competitions where some of the submitted solutions proposed the use of the periocular recognition [16,17]. Periocular biometrics have a distinct advantage over facial biometrics when the face is largely occluded or when capturing a full face is less convenient than capturing the periocular region (e.g., a selfie on a smartphone or masked face recognition [11], while maintaining the touchless nature of face capture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models

Damer

Raja

Kirchbuchner

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

This work addresses the challenge of building an accurate and generalizable periocular recognition model with a small number of learnable parameters. Deeper (larger) models are typically more capable of learning complex information. For this reason, knowledge distillation (kd) was previously proposed to carry this knowledge from a large model (teacher) into a small model (student). Conventional KD optimizes the student output to be similar to the teacher output (commonly classification output). In biometrics, comparison (verification) and storage operations are conducted on biometric templates, extracted from pre-classification layers. In this work, we propose a novel template-driven KD approach that optimizes the distillation process so that the student model learns to produce templates similar to those produced by the teacher model. We demonstrate our approach on intra- and cross-device periocular verification. Our results demonstrate the superiority of our proposed approach over a network trained without KD and networks trained with conventional (vanilla) KD. For example, the targeted small model achieved an equal error rate (EER) value of 22.2% on cross-device verification without KD. The same model achieved an EER of 21.9% with the conventional KD, and only 14.7% EER when using our proposed template-driven KD.

show abstract

Section: Baseline Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models

Damer

Raja

Kirchbuchner

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, in some cases facial masks are used intentionally to trick the FR systems. Hence, many research activities focus on algorithms to increase FR performance when dealing with masks that cover a large area of an individual's face [29], [30].…”

Section: Related Workmentioning

confidence: 99%

Fun Selfie Filters in Face Recognition: Impact Assessment and Removal

Botezatu¹,

Ibsen²,

Rathgeb³

et al. 2022

Preprint

View full text Add to dashboard Cite

This work investigates the impact of fun selfie filters, which are frequently used to modify selfies, on face recognition systems. Based on a qualitative assessment and classification of freely available mobile applications, ten relevant fun selfie filters are selected to create a database. To this end, the selected filters are automatically applied to face images of public face image databases. Different state-of-the-art methods are used to evaluate the influence of fun selfie filters on the performance of face detection using dlib, RetinaFace, and a COTS method, sample quality estimated by FaceQNet and MagFace, and recognition accuracy employing ArcFace and a COTS algorithm. The obtained results indicate that selfie filters negatively affect face recognition modules, especially if fun selfie filters cover a large region of the face, where the mouth, nose, and eyes are covered. To mitigate such unwanted effects, a GAN-based selfie filter removal algorithm is proposed which consists of a segmentation module, a perceptual network, and a generation module. In a cross-database experiment the application of the presented selfie filter removal technique has shown to significantly improve the biometric performance of the underlying face recognition systems.

show abstract

“…Based on the position of these facial landmarks, a polygon is synthesized, simulating a digital face mask of different shapes, heights, and colors. The generation of the simulated masks is according to the method described in the NIST report [27] and the detailed implementation can be found on the repo 3 . For each face image, the mask type C as described in [2], [27] with random color is used to generate the synthetic masks in this work.…”

Section: A Databasementioning

confidence: 99%

“…Studies have been proposed to address the face occlusion problem, but most of them only address the occlusion in the wild, e.g., by wearing sunglasses. Only very recently, some works specifi-cally addressed the enhancement of masked face recognition performance [3], [2], [26].…”

Section: Introductionmentioning

confidence: 99%

The Effect of Wearing a Face Mask on Face Image Quality

Fu¹,

Kirchbuchner²,

Damer³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

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-theart 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.

show abstract

MFR 2021: Masked Face Recognition Competition

Cited by 39 publications

References 22 publications

Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models

Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models

Fun Selfie Filters in Face Recognition: Impact Assessment and Removal

The Effect of Wearing a Face Mask on Face Image Quality

Contact Info

Product

Resources

About