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

Image-based object recognition in man, monkey and machine

M J Tarr1, H H Bülthoff

  • 1Brown University, Department of Cognitive and Linguistic Sciences, Providence, RI 02912, USA.

Cognition
|September 15, 1998
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

Neural correlates of decision making on whole body yaw rotation: An fNIRS study.

Neuroscience letters·2017
Same author

Rotating objects to recognize them: A case study on the role of viewpoint dependency in the recognition of three-dimensional objects.

Psychonomic bulletin & review·2013
Same author

Integration of visual and inertial cues in the perception of angular self-motion.

Experimental brain research·2013
Same author

Neural correlates of oddball detection in self-motion heading: a high-density event-related potential study of vestibular integration.

Experimental brain research·2012
Same author

Does visual subordinate-level categorisation engage the functionally defined fusiform face area?

Cognitive neuropsychology·2010
Same author

In vitro modulation of macrophage functions by 1,1-dimethylhydrazine (UDMH): Possible mechanism for UDMH-induced immuno-enhancement.

Toxicology in vitro : an international journal published in association with BIBRA·2010
Same journal

People make graded judgments about the inconceivable.

Cognition·2026
Same journal

The self as an image: Appearance and belief in visual representations of one's own face.

Cognition·2026
Same journal

Corrigendum to 'Consonant, vowel, and tone cues in early wordform recognition: Evidence from Cantonese-learning infants' [Cognition 275 (2026) 106624].

Cognition·2026
Same journal

Identifying distinct sources of whole number interference in children's decimal comparison: the role of numerical magnitude and inhibitory control.

Cognition·2026
Same journal

Evidence for abstract spatial concept learning in young animals.

Cognition·2026
Same journal

Blurred lines or clear boundaries? Synchrony and social dominance shape domain-specific self-other processing.

Cognition·2026
See all related articles

Visual object recognition models face challenges with 3D objects from 2D retinal input. Image-based and structural-description models are compared, suggesting a hybrid approach offers the most promising solution for accurate recognition.

Area of Science:

  • Cognitive Science
  • Computer Vision
  • Neuroscience

Background:

  • Visual object recognition involves interpreting 3D objects from 2D retinal images.
  • Current models include image-based (local features) and structural-description (3D parts) approaches.

Purpose of the Study:

  • To compare the biological plausibility and computational aspects of image-based and structural-description models.
  • To determine the most effective model for visual object recognition.

Main Methods:

  • Review of human psychophysics, neurophysiology, and machine vision findings.
  • Analysis of behavioral results concerning model viability.
  • Evaluation of computational advantages and limitations.

Main Results:

Related Experiment Videos

  • Converging evidence supports image-based models using viewpoint-specific local features.
  • Structural-description models represent objects as configurations of 3D volumes or parts.
  • Image-based models show promise but have limitations.

Conclusions:

  • Image-based models have potential pitfalls that structural information can address.
  • A hybrid model integrating aspects of both image-based and structural-description theories is likely the most viable.
  • Future research should explore combined approaches for robust object recognition.