Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

5.1K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
5.1K
Prosopagnosia01:24

Prosopagnosia

142
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
142
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

599
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
599

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The use of AI in psychology: A historical perspective.

British journal of psychology (London, England : 1953)·2026
Same author

Constructing a cross-race face identity triad test.

Behavior research methods·2025
Same author

Perceptual Expertise of Forensic Examiners and Reviewers on Tests of Cross-Race and Disguised Face Identification and Face Memory.

Applied cognitive psychology·2024
Same author

The Influence of the Other-Race Effect on Susceptibility to Face Morphing Attacks.

ACM transactions on applied perception·2024
Same author

Twin Identification over Viewpoint Change: A Deep Convolutional Neural Network Surpasses Humans.

ACM transactions on applied perception·2024
Same author

Identity recognition from faces and bodies in schizophrenia spectrum disorders.

Schizophrenia research. Cognition·2024

Related Experiment Video

Updated: Jun 8, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

473

Deep convolutional neural networks are sensitive to face configuration.

Virginia E Strehle1,2,3, Natalie K Bendiksen1,4,5, Alice J O'Toole1,6,7

  • 1School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, Texas, USA.

Journal of Vision
|November 5, 2024
PubMed
Summary
This summary is machine-generated.

Deep convolutional neural networks (DCNNs) show sensitivity to facial configuration changes, similar to human face recognition. These models prioritize configural information over feature details for identifying faces.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

394

Related Experiment Videos

Last Updated: Jun 8, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

473
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

394

Area of Science:

  • Computer Vision
  • Cognitive Neuroscience
  • Artificial Intelligence

Background:

  • Deep convolutional neural networks (DCNNs) achieve high accuracy in face recognition tasks.
  • Human face recognition relies heavily on sensitivity to facial configuration.
  • It remains unclear if DCNNs develop human-like representations of faces.

Purpose of the Study:

  • To investigate whether DCNNs trained for face identification perceive alterations in facial features and configuration.
  • To compare the sensitivity of DCNN representations to configural versus feature changes.
  • To determine if DCNNs' configural sensitivity arises from image properties or network processing.

Main Methods:

  • Altering facial configuration by changing inter-eye or nose-mouth distances.
  • Altering facial features by swapping eyes or mouths between different faces.
  • Processing altered faces through two DCNN models (Ranjan et al., 2018; Szegedy et al., 2017) and comparing representation similarity.

Main Results:

  • Both DCNNs demonstrated sensitivity to both configural and feature alterations.
  • Configural changes had a greater impact on DCNN representations than feature changes.
  • Sensitivity to configuration increased from pixel-level to DCNN encoding, while feature sensitivity remained unchanged.

Conclusions:

  • DCNNs are sensitive to facial configuration, mirroring human perception.
  • The enhanced sensitivity to configuration in DCNNs is a result of the network's processing, not just image properties.
  • Configural information is crucial for DCNNs discriminating similar faces, likely due to training objectives.