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

A new image representation algorithm inspired by image submodality models, redundancy reduction, and learning in

Nikhil Balakrishnan1, Karthik Hariharakrishnan, Dan Schonfeld

  • 1Department of Bioengineering, University of Illinois at Chicago, 851 S. Morgan Street, Room 218, (M/C 063), Chicago, IL 60607, USA. nikhilbalakrishnan@gmail.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 22, 2005
PubMed
Summary

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

A Deep Learning-Based Approach to Characterize Skull Physical Properties: A Phantom Study.

Journal of biophotonics·2024
Same author

Deep Learning Analyses of Brain MRI to Identify Sustained Attention Deficit in Treated Obstructive Sleep Apnea: A Pilot Study.

Sleep and vigilance·2022
Same author

Inferring excitation-inhibition dynamics using a maximum entropy model unifying brain structure and function.

Network neuroscience (Cambridge, Mass.)·2022
Same author

Autocatalytic-protection for an unknown locus CRISPR-Cas countermeasure for undesired mutagenic chain reactions.

Journal of theoretical biology·2021
Same author

Influence of personality on the psychosocial manifestations of postrefractive surgery patients during the COVID-19 pandemic.

Journal of cataract and refractive surgery·2020
Same author

Quantitative High-speed Assessment of Droplet and Aerosol From an Eye After Impact With an Air-puff Amid COVID-19 Scenario.

Journal of glaucoma·2020

This study introduces a novel algorithm for image representation, inspired by biology. It effectively captures image details like edges and color using a new method that achieves lower entropy than traditional techniques.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Image Processing

Background:

  • Current image representation methods often lack biological plausibility.
  • Efficiently representing natural images, including their complex features like edges and color, remains a challenge.

Purpose of the Study:

  • To develop a biologically motivated algorithm for natural image representation.
  • To improve the efficiency and quality of image representation compared to existing methods.
  • To model aspects of the human visual pathway.

Main Methods:

  • Utilizing successive projections into complementary subspaces for image decomposition.
  • Employing an Independent Component Analysis (ICA) basis for edge subspace representation.
  • Approximating residual image features using a Mixture of Probabilistic Principal Component Analyzers (MPPCA) model.

Related Experiment Videos

Main Results:

  • The proposed model effectively represents natural image attributes such as color and luminance.
  • Achieved lower entropy for chrominance and luminance components compared to DCT, ICA, and PCA at similar visual quality.
  • Demonstrated considerable simplification for image learning through sparse independent codes for edges.

Conclusions:

  • The new algorithm offers a biologically plausible and efficient approach to natural image representation.
  • The method outperforms traditional techniques like DCT, ICA, and PCA in terms of representational efficiency and visual quality.
  • The model's consistency with visual pathway paradigms suggests potential applications in understanding biological vision.