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

Nonlinear filtering by threshold decomposition.

J H Lin1, N Ansari, J Li

  • 1Comput. Commun. Lab., Ind. Technol. Res. Inst., Hsinchu, Taiwan.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 13, 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

[Clinical practice of minimally invasive daytime hepatectomy based on enhanced recovery after surgery whole-process management scheme].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2025
Same author

Risk Factors of Cardiac Complications in Pregnant Women with Hypertrophic Cardiomyopathy.

Nigerian journal of clinical practice·2024
Same author

[Difference of urinary protein components and the correlation between urinary protein quantification and glomerular filtration rate in pregnant women with pre-eclampsia].

Zhonghua fu chan ke za zhi·2023
Same author

[Regional analysis of high risk factors of hypertensive disorders in pregnancy with organ or system impairment].

Zhonghua fu chan ke za zhi·2023
Same author

[EBF1 Promotes the Sensitivity of Cervical Cancer Cells to Cisplatin via Activating FBN1 Transcription].

Molekuliarnaia biologiia·2023
Same author

Rupture of a non sinus of Valsalva aneurysm during pregnancy: Case report and review of literatures.

Nigerian journal of clinical practice·2023
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

A novel threshold decomposition (TD) architecture enhances stack filters. TD filters are equivalent to L1-filters, and their intersection yields linear and order statistic (LOS) filters, outperforming others in noise suppression.

Area of Science:

  • Digital Signal Processing
  • Image Processing
  • Filter Design

Background:

  • Stack filters are a class of nonlinear filters with applications in image processing.
  • Existing filter designs may have limitations in noise suppression and computational complexity.

Purpose of the Study:

  • Introduce a new threshold decomposition (TD) architecture for implementing stack filters.
  • Generalize TD filters to a new class of nonlinear filters.
  • Define and analyze linear and order statistic (LOS) filters.
  • Compare the performance of TD, L1, LOS, and linear filters in noise suppression.

Main Methods:

  • Development of a new threshold decomposition architecture.
  • Mathematical generalization of threshold decomposition filters.

Related Experiment Videos

  • Analysis of the intersection of TD and L1 filter classes to define LOS filters.
  • Empirical performance evaluation of various filters against Gaussian and salt-and-pepper noise.

    • Main Results:

    • The new TD architecture effectively implements stack filters.
    • TD filters demonstrate equivalence to L1-filters under specific conditions.
    • LOS filters, derived from TD and L1 filters, offer a balance between performance and complexity.
    • TD filters show compatibility with L1, LOS, and linear filters for Gaussian noise suppression.
    • TD filters exhibit superior performance in suppressing salt-and-pepper noise compared to other tested filters.

    Conclusions:

    • The proposed threshold decomposition architecture provides a flexible framework for filter design.
    • Threshold decomposition filters offer significant advantages in noise reduction, particularly for salt-and-pepper noise.
    • Linear and order statistic filters present a practical compromise for applications requiring efficient noise suppression.