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 Experiment Videos

Invariant visual object recognition: a model, with lighting invariance.

Edmund T Rolls1, Simon M Stringer

  • 1Oxford University, Centre for Computational Neuroscience, Department of Experimental Psychology, South Parks Road, Oxford OX1 3UD, England, United Kingdom. Edmund.Rolls@psy.ox.ac.uk

Journal of Physiology, Paris
|October 31, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Sex differences in activations to the sight of faces, scenes, body parts and tools in visual and non-visual cortical regions leading to the human hippocampus.

Biology of sex differences·2026
Same author

Visual Cortical Lateralization in Activations and Functional Connectivity to the Sight of Faces, Scenes, Body Parts, and Tools.

Human brain mapping·2026
Same author

Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model.

PLoS computational biology·2026
Same author

Hippocampal Revolutions.

Neuroscience and biobehavioral reviews·2025
Same author

Reward-specific satiety and reward-specific motivation: neural bases and significance.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Genetic risk-dependent brain markers of resilience to childhood Trauma.

Nature communications·2025
Same journal

Role of synchronized physiological and interpersonal rhythms in typical and atypical development.

Journal of physiology, Paris·2017
Same journal

Suicide attempts in children and adolescents: The place of clock genes and early rhythm dysfunction.

Journal of physiology, Paris·2017
Same journal

Editorial.

Journal of physiology, Paris·2017
Same journal

Dyssynchrony and perinatal psychopathology impact of child disease on parents-child interactions, the paradigm of Prader Willi syndrom.

Journal of physiology, Paris·2017
Same journal

Key considerations in designing a speech brain-computer interface.

Journal of physiology, Paris·2017
Same journal

Links between early child maltreatment, mental disorders, and cortisol secretion anomalies.

Journal of physiology, Paris·2017
See all related articles

This study presents a computational model for how the brain forms invariant object representations. It uses self-organizing learning based on visual input statistics to achieve invariance to translation, view, size, and lighting.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Computer Vision

Background:

  • The visual cortex processes complex visual information to form object representations.
  • Understanding how the brain achieves invariant object recognition is a key challenge.

Purpose of the Study:

  • To describe a neurophysiological and computational approach for forming invariant object representations.
  • To explain how self-organizing learning based on visual input statistics contributes to invariant object recognition.

Main Methods:

  • A feature hierarchy model utilizing self-organizing learning.
  • Incorporation of temporal continuity (associative synaptic learning with short-term memory) and spatial continuity (Continuous Transformation learning).
  • Extension of the model to include dorsal visual system functions, top-down feedback for attention control, and object selection in complex scenes.

Related Experiment Videos

Main Results:

  • The model successfully builds object representations invariant to translation, view, size, and lighting in the ventral visual stream.
  • Extensions account for invariant representations of global motion (looming, rotation, object-based movement) in the dorsal visual system.
  • The model explains attentional control via biased competition and the selection of single/multiple objects in complex scenes.

Conclusions:

  • Self-organizing learning based on visual input statistics is a viable mechanism for building invariant object representations.
  • The hierarchical model provides a unified framework for understanding object recognition, motion perception, and attention across visual streams.
  • The model offers insights into the computational principles underlying visual perception and object representation in the brain.