Human Face Processing with 1.5D Models

AbstractThe unprecedented efforts to minimize the effects of the COVID-19 pandemic introduce a new arena for human face recognition in which faces are partially occluded with masks. Here, we tested the extent to which face masks change the way faces are perceived. To this end, we evaluated face processing abilities for masked and unmasked faces in a large online sample of adult observers (n = 496) using an adapted version of the Cambridge Face Memory Test, a validated measure of face perception abilities in humans. As expected, a substantial decrease in performance was found for masked faces. Importantly, the inclusion of masks also led to a qualitative change in the way masked faces are perceived. In particular, holistic processing, the hallmark of face perception, was disrupted for faces with masks, as suggested by a reduced inversion effect. Similar changes were found whether masks were included during the study or the test phases of the experiment. Together, we provide novel evidence for quantitative and qualitative alterations in the processing of masked faces that could have significant effects on daily activities and social interactions.

Download Full-text

Neural tuning of human face processing

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1315621110 ◽

2013 ◽

Vol 110 (42) ◽

pp. 16702-16703

Author(s):

J. I. Borjon ◽

A. A. Ghazanfar

Keyword(s):

Face Processing ◽

Human Face

Download Full-text

Connectionists Methods for Human Face Processing

Face Recognition ◽

10.1007/978-3-642-72201-1_7 ◽

1998 ◽

pp. 124-156 ◽

Cited By ~ 2

Author(s):

Emmanuel Viennet ◽

Françoise Fogelman Soulié

Keyword(s):

Face Processing ◽

Human Face

Download Full-text

Face Recognition with Active Appearance Model (AAM)

Image Processing ◽

10.4018/978-1-4666-3994-2.ch057 ◽

2013 ◽

pp. 1124-1144 ◽

Cited By ~ 1

Author(s):

Patrycia Barros de Lima Klavdianos ◽

Lourdes Mattos Brasil ◽

Jairo Simão Santana Melo

Keyword(s):

Artificial Intelligence ◽

Computer Vision ◽

Face Recognition ◽

Face Processing ◽

Research Field ◽

Appearance Model ◽

Active Appearance Model ◽

Human Face ◽

Active Appearance ◽

Human Faces

Recognition of human faces has been a fascinating subject in research field for many years. It is considered a multidisciplinary field because it includes understanding different domains such as psychology, neuroscience, computer vision, artificial intelligence, mathematics, and many others. Human face perception is intriguing and draws our attention because we accomplish the task so well that we hope to one day witness a machine performing the same task in a similar or better way. This chapter aims to provide a systematic and practical approach regarding to one of the most current techniques applied on face recognition, known as AAM (Active Appearance Model). AAM method is addressed considering 2D face processing only. This chapter doesn’t cover the entire theme, but offers to the reader the necessary tools to construct a consistent and productive pathway toward this involving subject.

Download Full-text

Cortical networks for face perception in two-month-old infants

Proceedings of The Royal Society B Biological Sciences ◽

10.1098/rspb.2014.1468 ◽

2014 ◽

Vol 281 (1793) ◽

pp. 20141468 ◽

Cited By ~ 11

Author(s):

Tamami Nakano ◽

Kazuko Nakatani

Keyword(s):

Face Processing ◽

Behavioural Change ◽

Visual Pathway ◽

Recovery Phase ◽

Neural Mechanisms ◽

Human Face ◽

Functional Development ◽

Functional Pathways ◽

Preference Behaviour ◽

Functional Deterioration

Newborns have an innate system for preferentially looking at an upright human face. This face preference behaviour disappears at approximately one month of age and reappears a few months later. However, the neural mechanisms underlying this U-shaped behavioural change remain unclear. Here, we isolate the functional development of the cortical visual pathway for face processing using S-cone-isolating stimulation, which blinds the subcortical visual pathway. Using luminance stimuli, which are conveyed by both the subcortical and cortical visual pathways, the preference for upright faces was not observed in two-month-old infants, but it was observed in four- and six-month-old infants, confirming the recovery phase of the U-shaped development. By contrast, using S-cone stimuli, two-month-old infants already showed a preference for upright faces, as did four- and six-month-old infants, demonstrating that the cortical visual pathway for face processing is already functioning at the bottom of the U-shape at two months of age. The present results suggest that the transient functional deterioration stems from a conflict between the subcortical and cortical functional pathways, and that the recovery thereafter involves establishing a level of coordination between the two pathways.

Download Full-text

P512: A magnetoencephalographic study on face processing with morphing human face into monkey face

Clinical Neurophysiology ◽

10.1016/s1388-2457(14)50610-4 ◽

2014 ◽

Vol 125 ◽

pp. S187

Author(s):

E. Yamada ◽

K. Ogata ◽

M. Tanaka ◽

S. Tobimatsu

Keyword(s):

Face Processing ◽

Human Face

Download Full-text

The Face-Space Typicality Paradox: Understanding the Face-Space Metaphor

The Quarterly Journal of Experimental Psychology Section A ◽

10.1080/713755768 ◽

1998 ◽

Vol 51 (3) ◽

pp. 475-483 ◽

Cited By ~ 27

Author(s):

A. Mike Burton ◽

John R. Vokey

Keyword(s):

Face Processing ◽

Dimensional Space ◽

Short Note ◽

High Dimensional ◽

Human Face ◽

Face Space ◽

The Face

Some recent accounts of human face processing use the idea of “face space”, considered to be a multi-dimensional space whose dimensions correspond to ways in which faces can vary. Within this space, “typicality” is sometimes taken to reflect the proximity of a face to its local neighbours. Intuitions about the distribution of faces within the space may suggest that the majority of faces will be “typical” in these terms. However, when typicality measures are taken, researchers very rarely find that faces cluster at the “typical” end of the scale. In this short note we attempt to resolve this paradox and point out that reasoning about high dimensional distributions requires that some specific assumptions are made explicit.

Download Full-text

Disentangling the Representation of Identity from Head View Along the Human Face Processing Pathway

Cerebral Cortex ◽

10.1093/cercor/bhw344 ◽

2016 ◽

Vol 27 (1) ◽

pp. 46-53 ◽

Cited By ~ 47

Author(s):

J Swaroop Guntupalli ◽

Kelsey G Wheeler ◽

M Ida Gobbini

Keyword(s):

Face Processing ◽

Human Face

Download Full-text

Face recognition algorithms as models of human face processing

Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580) ◽

10.1109/afgr.2000.840689 ◽

2002 ◽

Cited By ~ 7

Author(s):

A.J. O'Toole ◽

Yi Cheng ◽

P.J. Phillips ◽

B. Ross ◽

H.A. Wild

Keyword(s):

Face Recognition ◽

Face Processing ◽

Human Face ◽

Recognition Algorithms

Download Full-text

Not so fast: Limited validity of deep convolutional neural networks as in silico models for human naturalistic face processing

10.1101/2021.11.17.469009 ◽

2021 ◽

Author(s):

Guo Jiahui ◽

Ma Feilong ◽

Matteo Visconti di Oleggio Castello ◽

Samuel A Nastase ◽

James V Haxby ◽

...

Keyword(s):

Neural Networks ◽

Human Brain ◽

Convolutional Neural Networks ◽

Face Processing ◽

In Silico ◽

Processing System ◽

Human Face ◽

Deep Convolutional Neural Networks ◽

Neural Representations ◽

Fully Connected

Deep convolutional neural networks (DCNNs) trained for face identification can rival and even exceed human-level performance. The relationships between internal representations learned by DCNNs and those of the primate face processing system are not well understood, especially in naturalistic settings. We developed the largest naturalistic dynamic face stimulus set in human neuroimaging research (700+ naturalistic video clips of unfamiliar faces) and used representational similarity analysis to investigate how well the representations learned by high-performing DCNNs match human brain representations across the entire distributed face processing system. DCNN representational geometries were strikingly consistent across diverse architectures and captured meaningful variance among faces. Similarly, representational geometries throughout the human face network were highly consistent across subjects. Nonetheless, correlations between DCNN and neural representations were very weak overall—DCNNs captured 3% of variance in the neural representational geometries at best. Intermediate DCNN layers better matched visual and face-selective cortices than the final fully-connected layers. Behavioral ratings of face similarity were highly correlated with intermediate layers of DCNNs, but also failed to capture representational geometry in the human brain. Our results suggest that the correspondence between intermediate DCNN layers and neural representations of naturalistic human face processing is weak at best, and diverges even further in the later fully-connected layers. This poor correspondence can be attributed, at least in part, to the dynamic and cognitive information that plays an essential role in human face processing but is not modeled by DCNNs. These mismatches indicate that current DCNNs have limited validity as in silico models of dynamic, naturalistic face processing in humans.

Download Full-text