Deep Learning-based Face Recognition and the Robustness to Perspective Distortion

Damer, Naser; Wainakh, Yaza; Henniger, Olaf; Croll, Christian; Berthe, Benoit; Braun, Andreas; Kuijper, Arjan

doi:10.1109/icpr.2018.8545037

Cited by 12 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such attacks can be morphing attacks [5,6], presentation attacks (spoofing) [7], or different unconventional attacks [8]. Face recognition deployability is also affected by the biometric sample capture [9] and presentation [10], including face occlusions. Occluded face detection is a widely studied challenge in the domain of computer vision.…”

Section: Related Workmentioning

confidence: 99%

Extended evaluation of the effect of real and simulated masks on face recognition performance

et al. 2021

Self Cite

View full text Add to dashboard Cite

Face recognition is an essential technology in our daily lives as a contactless and convenient method of accurate identity verification. Processes such as secure login to electronic devices or identity verification at automatic border control gates are increasingly dependent on such technologies. The recent COVID‐19 pandemic has increased the focus on hygienic and contactless identity verification methods. The pandemic has led to the wide use of face masks, essential to keep the pandemic under control. The effect of mask‐wearing on face recognition in a collaborative environment is currently a sensitive yet understudied issue. Recent reports have tackled this by using face images with synthetic mask‐like face occlusions without exclusively assessing how representative they are of real face masks. These issues are addressed by presenting a specifically collected database containing three sessions, each with three different capture instructions, to simulate real use cases. The data are augmented to include previously used synthetic mask occlusions. Further studied is the effect of masked face probes on the behaviour of four face recognition systems—three academic and one commercial. This study evaluates both masked‐to‐non‐masked and masked‐to‐masked face comparisons. In addition, real masks in the database are compared with simulated masks to determine their comparative effects on face recognition performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Extended evaluation of the effect of real and simulated masks on face recognition performance

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 2 shows a simple example of the first step. After the merging, the new weight interval [−1, 2] is the convex hull of [−1, −1] and [1,2], and the other new weight interval [1,3] is similar. The new bias interval [−1, 1] is also the convex hull of the original bias intervals [1,1]…”

Section: Abstracting Dnn Into Innmentioning

confidence: 99%

“…In recent years, Deep Neural Networks (DNNs) have been achieving remarkable performance in many complex tasks and are increasingly deployed in safety-critical systems, such as autonomous vehicle [2], face recognition [3], airborne collision avoidance system [11]. However, it is well known that DNNs are vulnerable to slight perturbations, i.e., adding imperceptible perturbations to inputs may cause DNN to make mistakes [17,18,8,5].…”

Section: Introductionmentioning

confidence: 99%

Fine-Grained Neural Network Abstraction for Efficient Formal Verification

Wen¹

2021

Proceedings of the 33rd International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

The advance of deep learning makes it possible to empower safety-critical systems with intelligent capabilities. However, its intelligent component, i.e., deep neural network, is difficult to formally verify due to the large scale and intrinsic complexity of the verification problem. Abstraction has been proved to be an effective way of improving the scalability. A challenging problem in abstraction is that it is difficult to achieve a balance between the size reduced and output overestimation caused by abstraction. In this work, we propose an effective fine-grained approach to abstract neural networks. Our approach is fine-grained in that we identify four cases that should be abstracted independently under a certain neuron prioritization strategy. This allows us to merge more neurons in networks and meanwhile maintain a relatively low output overestimation. Experimental results show that our approach outperforms other existing abstraction approaches by significantly reducing the scale of target deep neural networks with small overestimation.

show abstract

“…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. It also carries other benefits; for example, perspective distortion affects the periocular region to a lower degree because the depth variation of the area is smaller than the that of the complete face [18]. Periocular recognition on smartphones and wearable devices has gained growing research attention, and with recent deep learning methods achieving superior accuracy and with applications in various domains have surfaced [19][20][21][22].…”

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

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

Deep Learning-based Face Recognition and the Robustness to Perspective Distortion

Cited by 12 publications

References 19 publications

Extended evaluation of the effect of real and simulated masks on face recognition performance

Extended evaluation of the effect of real and simulated masks on face recognition performance

Fine-Grained Neural Network Abstraction for Efficient Formal Verification

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

Contact Info

Product

Resources

About