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

Weighted centroid neural network for edge preserving image compression.

D C Park1, Y J Woo

  • 1Department of Information and Control Engineering, Myong Ji University, Korea.

IEEE Transactions on Neural Networks
|February 6, 2008
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

Proteomic associations with forced expiratory volume - a Mendelian randomisation study.

medRxiv : the preprint server for health sciences·2023
Same author

Author Correction: 3D-printed vascular networks direct therapeutic angiogenesis in ischaemia.

Nature biomedical engineering·2020
Same author

Successful Heart-Lung Transplant for a Patient on Continuous-Flow Left Ventricular Assist Device Support Complicated With Amiodarone-Induced Pulmonary Fibrosis.

Transplantation proceedings·2019
Same author

Successful Outcome Following Orthotopic Heart Transplantation With a Donor Half Way Across The Country.

Transplantation proceedings·2018
Same author

Ectopic pregnancy occurring in the remnant tube of a previous adnexectomy: a case report.

Clinical and experimental obstetrics & gynecology·2018
Same author

3D-printed vascular networks direct therapeutic angiogenesis in ischaemia.

Nature biomedical engineering·2018
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

A novel weighted centroid neural network (WCNN) enhances image compression by preserving edges. This unsupervised competitive neural network effectively allocates resources, improving reconstructed image quality compared to traditional methods.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Processing

Background:

  • Traditional image compression methods often struggle with preserving fine details, particularly edges.
  • Vector Quantization (VQ) algorithms, while effective for compression, can lead to loss of image fidelity in textured or edge-rich regions.
  • Existing neural network approaches for image compression have limitations in edge preservation.

Purpose of the Study:

  • To propose a novel edge-preserving image compression algorithm.
  • To introduce the weighted centroid neural network (WCNN) for enhanced image compression.
  • To improve the allocation of code vectors in vector quantization based on image block characteristics.

Main Methods:

  • Development of an unsupervised competitive neural network, the weighted centroid neural network (WCNN).

Related Experiment Videos

  • Integration of the Mean/Residual Vector Quantization (M/RVQ) scheme as the algorithmic framework.
  • Utilizing edge strength of image blocks to dynamically allocate code vectors within the WCNN.

    • Main Results:

    • The WCNN effectively allocates more code vectors to edge regions and fewer to non-edge/shade regions.
    • Demonstrated improved edge characteristics in reconstructed images compared to conventional VQ-based neural networks.
    • Outperformed standard algorithms like Self-Organizing Map (SOM) and adaptive SOM in edge preservation.

    Conclusions:

    • The proposed WCNN offers a superior approach for edge-preserving image compression.
    • The method enhances the quality of reconstructed images, particularly in areas with significant detail.
    • WCNN provides a more efficient and effective strategy for vector code allocation in image compression.