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

Adaptive learning method in self-organizing map for edge preserving vector quantization.

Y K Kim1, J B Ra

  • 1Dept. of Electr. Eng., Korea Adv. Inst. of Sci. and Technol., Taejon.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Search for Bs0 --> micro+ micro- and B0 --> micro+ micro- decays with 2 fb-1 of pp collisions.

Physical review letters·2008
Same author

Measurement of inclusive jet cross sections in Z/gamma*(-->e+e-) + jets production in pp[over ] collisions at square root s = 1.96 TeV.

Physical review letters·2008
Same author

Search for standard model Higgs bosons produced in association with W bosons.

Physical review letters·2008
Same author

Cross-section-constrained top-quark mass measurement from dilepton events at the Tevatron.

Physical review letters·2008
Same author

Direct measurement of the W Boson width in ppover collisions at square roots = 1.96 TeV.

Physical review letters·2008
Same author

Observation of orbitally excited B(s) mesons.

Physical review letters·2008
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study enhances Kohonen

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Kohonen's self-organizing map (SOM) algorithm is used for vector quantization in image coding.
  • Edge degradation is a common issue in SOM-based image compression.
  • Existing methods struggle to effectively mitigate this artifact.

Purpose of the Study:

  • To modify the Kohonen's self-organizing map algorithm.
  • To reduce edge degradation in vector quantized images.
  • To improve the quality of compressed images using SOM.

Main Methods:

  • Adaptive learning rates were introduced into the SOM algorithm.
  • Learning rates are determined based on image block activity.
  • The modified algorithm was applied to 4x4 vector quantization for image coding.

Related Experiment Videos

Main Results:

  • The proposed method effectively reduces edge degradation in coded images.
  • Simulation results demonstrate the feasibility of the adaptive learning rate approach.
  • Improved image quality was observed compared to standard SOM.

Conclusions:

  • The modified SOM algorithm with adaptive learning rates is a viable solution for reducing edge degradation.
  • This technique offers enhanced image quality in vector quantization.
  • Further research can explore its application in various image compression scenarios.