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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Frequency domain manipulation of multiple copy-move forgery in digital image forensics.

PloS one·2025
Same author

An optimized dynamic attribute-based searchable encryption scheme.

PloS one·2024
Same author

Machine learning based skin lesion segmentation method with novel borders and hair removal techniques.

PloS one·2022
Same author

Fault Tolerant DHT-Based Routing in MANET.

Sensors (Basel, Switzerland)·2022
Same author

Monitoring the Emotional Response to the COVID-19 Pandemic Using Sentiment Analysis: A Case Study in Mexico.

Computational intelligence and neuroscience·2022
Same author

An Efficient and Secure Revocation-Enabled Attribute-Based Access Control for eHealth in Smart Society.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Sep 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

An Efficient Defocus Blur Segmentation Scheme Based on Hybrid LTP and PCNN.

Sadia Basar1,2, Abdul Waheed3,4, Mushtaq Ali1

  • 1Department of Information Technology, Hazara University Mansehra, Mansehra 21120, Pakistan.

Sensors (Basel, Switzerland)
|April 12, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a new method for automatic defocus segmentation using Local Ternary Pattern (LTP) and Pulse Coupled Neural Network (PCNN) to accurately identify blurred regions in images. The novel approach enhances image analysis for applications like object recognition and scene enhancement.

Keywords:
EDASLTPPCNNdefocus blurin-focused regionout-of-focused region

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K

Related Experiment Videos

Last Updated: Sep 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Defocus and motion blur are primary causes of blurry regions in digital images, impacting image quality and information extraction.
  • Existing defocus segmentation algorithms often struggle with noise and are computationally expensive for generating local clarity metrics.
  • Automatic segmentation of blurred and sharp regions is crucial for applications such as scene enhancement and object detection in blurred images.

Purpose of the Study:

  • To propose a novel and robust defocus-blur segmentation scheme.
  • To address the limitations of existing methods in terms of noise handling and computational cost.
  • To improve the accuracy and efficiency of separating blurred and sharp image regions.

Main Methods:

  • A new scheme combining Local Ternary Pattern (LTP) and Pulse Coupled Neural Network (PCNN) for defocus-blur segmentation.
  • Utilizing a sharpness measure that fuses upper and lower patterns for enhanced region and edge detection.
  • Experimental validation against eight reference techniques using a dataset of 1000 semi-blurred images.

Main Results:

  • The proposed LTP-PCNN scheme demonstrated superior performance in segmenting blur regions compared to referenced algorithms.
  • Fusion of upper and lower patterns in the sharpness measure yielded more noticeable results in terms of region and edge delineation.
  • The scheme achieved improved efficiency and accuracy, validated by metrics including Precision, Recall, F1-Score, Accuracy, MCC, DSC, and Specificity.

Conclusions:

  • The developed LTP-PCNN scheme offers a robust and effective solution for automatic defocus-blur segmentation.
  • The method provides significant improvements over existing techniques, particularly in handling image blur and enhancing segmentation accuracy.
  • The flexible parameterization and promising results from the EDAS module analysis suggest broad applicability and reduced time complexity.