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

An algorithm for associating the features of two images.

G L Scott1, H C Longuet-Higgins

  • 1Department of Engineering Science, University of Oxford, U.K.

Proceedings. Biological Sciences
|April 22, 1991
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

Contradictions in theoretical chemistry.

Nature·2018
Same author

The structure of some electron-deficient molecules.

Journal of the Chemical Society·2010
Same author

A New Treatment of Fibrositis.

British medical journal·2010
Same author

Local Chemotherapy in Chronic Rheumatism.

British medical journal·2010
Same author

The electronic structure of conjugated systems; general theory.

Proceedings of the Royal Society of London. Series A, Mathematical and physical sciences·2010
Same author

Identification of the secreted macromolecular immunogens of Staphylococcus aureus by analysis of serum.

FEMS immunology and medical microbiology·2000
Same journal

Chronic limb loading results in remarkable load carriage economy in growing fowl.

Proceedings. Biological sciences·2026
Same journal

Motion-from-structure in face perception: expectations of natural face motion depend on face shape.

Proceedings. Biological sciences·2026
Same journal

Unification and generalization of models of zygote survival.

Proceedings. Biological sciences·2026
Same journal

Phenological type- and diameter-dependent effects of individual light availability and interannual climate variation on tree growth.

Proceedings. Biological sciences·2026
Same journal

Interaction range of common goods shapes Black Queen dynamics beyond the cheater-cooperator narrative.

Proceedings. Biological sciences·2026
Same journal

Stingray spine diversity reflects performance trade-offs linked to puncture and breakability.

Proceedings. Biological sciences·2026
See all related articles

This study introduces an algorithm for image correspondence, matching features between two images. It accurately maps features under various transformations, similar to human visual perception of motion.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Neuroscience

Background:

  • Establishing correspondences between features in related images is fundamental to computer vision.
  • Understanding how humans perceive motion and displacement between successive images offers insights for algorithmic development.

Purpose of the Study:

  • To develop and present a novel algorithm for determining feature correspondences between two related images.
  • To analyze the algorithm's behavior in relation to human perception of visual displacement and its robustness to image transformations.

Main Methods:

  • The algorithm operates on feature distances, maximizing the inner product of a 'pairing matrix' and a 'proximity matrix'.
  • The proximity matrix utilizes a Gaussian function (exp(-rij^2/2σ^2)), where rij is the feature distance and σ is a scale parameter.

Related Experiment Videos

Main Results:

  • The algorithm generates feature correspondences that align with perceived movements when viewing images sequentially.
  • Increasing the scale parameter (σ) in the algorithm mimics the effect of increased interstimulus interval on perceived displacements.
  • The algorithm successfully recovers feature mappings for image translation, expansion, and shear deformation, even with slight deviations in individual feature displacements.

Conclusions:

  • The proposed algorithm provides a robust method for establishing image correspondences, drawing parallels with human visual perception.
  • The scale parameter (σ) effectively controls the sensitivity of the correspondence matching, analogous to perceptual factors in human vision.
  • The algorithm's ability to handle common image transformations makes it suitable for applications involving image sequences.