Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms

Phillips, P. Jonathon; Yates, Amy N.; Hu, Ying; Hahn, Carina A.; Noyes, Eilidh; Jackson, Kelsey; Cavazos, Jacqueline G.; Jeckeln, Géraldine; Ranjan, Rajeev; Sankaranarayanan, Swami; Chen, Jun-Cheng; Castillo, Carlos D.; Chellappa, Rama; White, David; O’Toole, Alice J.

doi:10.1073/pnas.1721355115

Cited by 351 publications

(385 citation statements)

References 25 publications

Supporting

Mentioning

359

Contrasting

Order By: Relevance

“…Such hierarchical neural networks process information sequentiallythrough a feedforward cascade of filtering, rectification and normalization operations. The accuracy of these architectures is now approachingsometimes exceedingthat of human observers on key visual recognition tasks including object [1] and face recognition [2]. These advances suggest that purely feedforward mechanisms suffice to accomplish remarkable results in object categorization, in line with previous experimental studies on humans [3] and animals [4].…”

Section: Introductionsupporting

confidence: 70%

Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

Alamia

Luo

Ricci

et al. 2019

Preprint

View full text Add to dashboard Cite

The development of deep convolutional networks (DCNs) has recently led to great successes in computer vision and have become de facto computational models of vision. However, a growing body of work suggests that they exhibit critical limitations beyond image categorization. Here, we study a fundamental limitation of DCNs for judging whether two items are the same or different (SD) compared to a baseline assessment of their spatial relationship (SR). We test the prediction that SD tasks recruit additional cortical mechanisms which underlie critical aspects of visual cognition that are not explained by current computational models. We thus recorded EEG signals from 14 participants engaged in the same tasks as the computational models. Importantly, the two tasks were matched in terms of difficulty by an adaptive psychometric procedure: yet, on top of a modulation of evoked potentials, our results revealed higher activity in the low beta (13-20Hz) band in the SD compared to the SR conditions, which we surmise as reflecting the crucial involvement of recurrent mechanisms sustaining working memory and attention.Despite the impressive progress of deep convolutional networks (DCNs) in object recognition, recent studies demonstrated that state-of-the-art vision algorithms encounter severe limitations when performing certain visual reasoning tasks: for instance, convolutional networks can easily solve problems involving spatial relations, but fail in identifying whether two items are identical or different (same-different task). This conclusion led us to test the hypothesis that different computational mechanisms are needed to successfully perform these tasks also in the visual system. First, we confirmed in our simulations that DCNs can successfully perform spatial relationship tasks but struggle with same-different ones. Then, we tested 14 participants on the same experimental design while recording their EEG signals.Remarkably, our results revealed a significant difference between the tasks in the occipital brain regions both in evoked potentials and in the oscillatory dynamics. Specifically, an increase of activity was found when performing the SD over the SR condition. We interpret these results as reflecting the fundamental involvement of recurrent mechanisms implementing cognitive functions such as working memory and attention.

show abstract

Section: Introductionsupporting

confidence: 70%

Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

Alamia

Luo

Ricci

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Recent developments in machine face recognition, enable us to test this hypothesis, with deep convolutional neural networks (DCNNs). In particular, face and object-trained DCNNs have recently reached and even surpassed human face and object recognition abilities (4,5). This human-level performance together with their brain-inspired hierarchical structure, make them good candidates to model the human brain (6).…”

Section: Discussionmentioning

confidence: 99%

Face recognition depends on specialized mechanisms tuned to view-invariant facial features: Insights from deep neural networks optimized for face or object recognition

Abudarham

Yovel

2020

Preprint

View full text Add to dashboard Cite

SummaryFaces are processed by specialized neural mechanisms in high-level visual cortex. How does this divergence to a face-specific and an object-general system contribute to face recognition? Recent advances in machine face recognition together with our understanding of how humans recognize faces enable us to address this fundamental question. We hypothesized that face recognition depends on a face-selective system that is tuned to view-invariant facial features, which cannot be accomplished by an object-general system. To test this hypothesis, we used deep convolutional neural networks (DCNNs) that were optimized for face or object recognition. Consistent with the hierarchical architecture of the visual system, results show that a human-like, view-invariant face representation emerges only at higher layers of a face-trained but not the object-trained neural network. Thus, by combining human psychophysics and computational modelling of the visual system, we revealed how the functional organization of the visual cortex may contribute to recognition.

show abstract

“…Recently, there has been a lot of interest in image processing techniques and they have been widely used in many different fields. Face recognition and license plate detection are two of the widest areas of research in the application of CNN [27, 28]. Medical image pattern recognition is another attractive field of research for image processing and machine-based prediction neural networks [29].…”

Section: Discussionmentioning

confidence: 99%

The First Implication of Image Processing Techniques on Influenza A Virus Sub-Typing Based on HA/NA Protein Sequences, using Convolutional Deep Neural Network

Ahsan¹,

Ebrahimi²

2018

Preprint

View full text Add to dashboard Cite

Increase in influenza A virus host range throughout its evolution has given rise to major concerns worldwide. Although the increasing host range mechanism of the virus is largely unknown; persistent genetic mutations have been blamed as a key factor in the re-organization of the host response and the host range. To uncover the underlying core bases of the two important antigenic proteins of influenza virus (HA and NA), functional data mining and image processing analysis of over 8000 protein sequences of different HA and NA subtypes were performed. Each amino acid sequence in HA or NA proteins sat as a feature or variable and two polynomial datasets were created and subjected into conventional prediction models.

show abstract

Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms

Cited by 351 publications

References 25 publications

Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

Face recognition depends on specialized mechanisms tuned to view-invariant facial features: Insights from deep neural networks optimized for face or object recognition

The First Implication of Image Processing Techniques on Influenza A Virus Sub-Typing Based on HA/NA Protein Sequences, using Convolutional Deep Neural Network

Contact Info

Product

Resources

About