Face-selective regions show invariance to linear, but not to non-linear, changes in facial images

Heidi A Baseler,Andrew W Young,Rob Jenkins,A Mike Burton,Timothy J Andrews

doi:10.1016/j.neuropsychologia.2016.10.004

Heidi A Baseler, Andrew W Young + Show 3 more

Open Access

https://doi.org/10.1016/j.neuropsychologia.2016.10.004

Copy DOI

Journal: Neuropsychologia	Publication Date: Oct 10, 2016
Citations: 7	License type: cc-by

Affiliation: University of York

Abstract

Familiar face recognition is remarkably invariant across huge image differences, yet little is understood concerning how image-invariant recognition is achieved. To investigate the neural correlates of invariance, we localized the core face-responsive regions and then compared the pattern of fMR-adaptation to different stimulus transformations in each region to behavioural data demonstrating the impact of the same transformations on familiar face recognition. In Experiment 1, we compared linear transformations of size and aspect ratio to a non-linear transformation affecting only part of the face. We found that adaptation to facial identity in face-selective regions showed invariance to linear changes, but there was no invariance to non-linear changes. In Experiment 2, we measured the sensitivity to non-linear changes that fell within the normal range of variation across face images. We found no adaptation to facial identity for any of the non-linear changes in the image, including to faces that varied in different levels of caricature. These results show a compelling difference in the sensitivity to linear compared to non-linear image changes in face-selective regions of the human brain that is only partially consistent with their effect on behavioural judgements of identity. We conclude that while regions such as the FFA may well be involved in the recognition of face identity, they are more likely to contribute to some form of normalisation that underpins subsequent recognition than to form the neural substrate of recognition per se.

Highlights

A striking property of our ability to recognise familiar faces is that it remains relatively invariant across huge changes in the facial image
The aim of this study was to investigate the sensitivity of face-selective regions to linear and non-linear changes in face images
We found adaptation to identity in face-selective regions such as the occipital face area (OFA) and fusiform face area (FFA), which showed invariance to linear changes in the spatial configuration of the image

Summary

Introduction

A striking property of our ability to recognise familiar faces is that it remains relatively invariant across huge changes in the facial image. A useful way to probe the mechanisms underlying our imageinvariant responses to familiar faces is to look at transformations of the face image that permit or interfere with recognition Such transformations can be broadly grouped into those involving linear or non-linear changes. Changing the aspect ratio of a familiar face photograph by stretching or compressing it in the horizontal or vertical dimension has almost no measurable effect on our ability to recognise it (Hole et al, 2002; Sandford & Burton, 2014). The same is true for linear changes affecting both horizontal and vertical dimensions at once, as for a size change These linear changes in the image often occur with changes in viewing distance, so some degree of invariance to such changes is useful to everyday recognition. Invariance to changes in aspect ratio is found for changes that fall well outside the limits participants will have encountered (Hole et al, 2002; Sandford & Burton, 2014)

Objectives

Methods

Results

Conclusion