Facial Expressions as a Vulnerability in Face Recognition

Peña, Alejandro; Serna, Ignacio; Morales, Aythami; Fiérrez, Julián; Lapedriza, Àgata

doi:10.1109/icip42928.2021.9506444

Cited by 19 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 and Figure 7 illustrate the results of recently reported face detection models with our designed method. We compare our method against 8 recent deep learning approaches: LDCF+ [27], multitask cascade-CNN [6], ScaleFace [28], CMS-RCNN [8], MSCNN [29], HR [19], Zhu [30], and FAN [29]. We discover that our proposed method performs compelling performance with the SOTA methods on easy set (96.3%) and medium difficulty set (95.1%), respectively.…”

Section: Results On Widermentioning

confidence: 93%

An Efficient Multiscale Pyramid Attention Network for Face Detection in Surveillance Images

Liu¹,

Cai²,

Li³

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Although a large number of works have been done to explore efficient face detection in various scenes, practical face detection in unconstrained condition of varying lighting, pose, scale, and occlusion remains a challenging task. The primary limitation of existing solutions is that they are vulnerable to influence from the wild environment. Practical features extraction plays a crucial part in the face detection of low-quality images. Based on the EfficientNet, this paper builds a novel pyramid attention network to integrate multilevel features with rich context messages. Firstly, a context model is exploited to increase the receptive fields at the beginning of the network. Secondly, stacked pyramid feature attention modules and feature fusion simultaneously selectively integrate the contextual information and enable spatial details, thus enhancing the capacity to detect faces on hard images. In addition, hard samples augmentation of the training sets is conducted, which is beneficial for improving the accuracy. A thorough study on ablation verifies the effect of the proposed strategies. Moreover, extensive experiments on Wider Face and FDDB datasets, remarkably pushing the accuracy both of 96.3% (2%↑), demonstrate the performance of the proposed deep face detector which is superior and outperforms most of the preexisting methods. The method presented in this paper can perform the task of face detection in surveillance images well.

show abstract

Section: Results On Widermentioning

confidence: 93%

An Efficient Multiscale Pyramid Attention Network for Face Detection in Surveillance Images

Liu¹,

Cai²,

Li³

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…The ResNet50 model was originally proposed for general image recognition tasks and later it was retrained with the VGGFace2 database [49] for face recognition. This architecture has been extensively used as a starting point in the Facial expressions analysis [57][58][59] and Action Units recognition in competitions like Affective Behavior Analysis in-thewild (ABAW) in FG 2020 [60], ICCV 2021 [61], and CVPR 2022 [62]. The architecture is used as feature extractor by removing the final decision layer.…”

Section: Plos Onementioning

confidence: 99%

Exploring facial expressions and action unit domains for Parkinson detection

et al. 2023

View full text Add to dashboard Cite

Background and objective Patients suffering from Parkinson’s disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection. Methods Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects. Results Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at https://github.com/luisf-gomez/Explorer-FE-AU-in-PD. Conclusions Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.

show abstract

“…• Need for robustness: Face recognition systems need to become more robust against partial occlusions (from accessories or hair) [72], [42], facial expressions (beyond neutral and smiling faces) [50], and temporary attributes that might change the daily appearance of a face [64], [71]. This can greatly enhance the applicability in more real-life scenarios.…”

Section: Performance Analysismentioning

confidence: 99%

“…Biases can be identified as learning weakness to be exploited by users with malicious intentions (i.e. vulnerability attacks [50]). To be precise, we analyse the differential outcome as defined by Howard et al [33] of two popular face recognition models (FaceNet [55] and ArcFace [17]) with regard to 47 attributes.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Terhörst¹,

Kolf²,

Huber³

et al. 2021

Preprint

View full text Add to dashboard Cite

Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics. Therefore, in this work, we analyse FR bias over a wide range of attributes. We investigate the influence of 47 attributes on the verification performance of two popular FR models. The experiments were performed on the publicly available MAADFace attribute database with over 120M high-quality attribute annotations. To prevent misleading statements about biased performances, we introduced control group based validity values to decide if unbalanced test data causes the performance differences. The results demonstrate that also many non-demographic attributes strongly affect the recognition performance, such as accessories, hair-styles and colors, face shapes, or facial anomalies. The observations of this work show the strong need for further advances in making FR system more robust, explainable, and fair. Moreover, our findings might help to a better understanding of how FR networks work, to enhance the robustness of these networks, and to develop more generalized bias-mitigating face recognition solutions.

show abstract

Facial Expressions as a Vulnerability in Face Recognition

Cited by 19 publications

References 32 publications

An Efficient Multiscale Pyramid Attention Network for Face Detection in Surveillance Images

An Efficient Multiscale Pyramid Attention Network for Face Detection in Surveillance Images

Exploring facial expressions and action unit domains for Parkinson detection

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Contact Info

Product

Resources

About