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

Non-Volatile Taste Profile Dynamics Across Developmental Stages of <i>Agaricus bisporus</i> Fruiting Bodies.

Foods (Basel, Switzerland)·2026
Same author

Boosting the immune response and protective efficacy of inactivated PRV vaccine using cGAMP as a mucosal adjuvant.

BMC veterinary research·2026
Same author

Baicalein alleviates anxiety symptom in Parkinson's disease by targeting Sema3A-mediated parvalbumin interneuron dysfunction.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Inhibition of protein kinase CK2 remodels the tumor immune microenvironment and sensitizes lung cancer to PD-L1 blockade.

Experimental hematology & oncology·2026
Same author

Functional Characterization of <i>GA2ox3</i> in Rice Osmotic Stress Response and Identification of a Superior Allele for Breeding Applications.

Plants (Basel, Switzerland)·2026
Same author

Macrophage MERTK restrains GRAMD1A-driven mitochondrial oxysterol trafficking to limit colitis.

Redox biology·2026

Related Experiment Video

Updated: Aug 30, 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

2.9K

Image copy-move forgery detection and localization based on super-BPD segmentation and DCNN.

Qianwen Li1, Chengyou Wang2, Xiao Zhou1

  • 1School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, 264209, China.

Scientific Reports
|September 2, 2022
PubMed
Summary

This study introduces SD-Net, a novel method for copy-move forgery detection (CMFD) using deep convolutional neural networks (DCNN) and super boundary-to-pixel direction (super-BPD) segmentation. SD-Net enhances accuracy and robustness for detecting various image forgeries.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

615
Detection of Copy Number Alterations Using Single Cell Sequencing
09:45

Detection of Copy Number Alterations Using Single Cell Sequencing

Published on: February 17, 2017

11.7K

Related Experiment Videos

Last Updated: Aug 30, 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

2.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

615
Detection of Copy Number Alterations Using Single Cell Sequencing
09:45

Detection of Copy Number Alterations Using Single Cell Sequencing

Published on: February 17, 2017

11.7K

Area of Science:

  • Computer Vision
  • Digital Image Forensics
  • Machine Learning

Background:

  • Image forgery, particularly copy-move forgery, poses a significant threat to digital image security.
  • Existing copy-move forgery detection (CMFD) methods, especially those based on convolutional neural networks (CNN), often suffer from relatively low accuracy.
  • The subtle nature of copy-move forgeries makes their detection and localization a challenging task.

Purpose of the Study:

  • To propose a novel and accurate method for copy-move forgery detection and localization.
  • To address the limitations of existing CMFD techniques, particularly regarding accuracy and robustness.
  • To develop a system capable of effectively detecting and localizing various types of copy-move forgeries, including those with scaling and rotation.

Main Methods:

  • A deep convolutional neural network (DCNN) is employed for automatic feature extraction, replacing traditional hand-crafted features.
  • Super boundary-to-pixel direction (super-BPD) segmentation is utilized to enhance the correlation between similar image blocks, improving detection accuracy.
  • A feature pyramid is incorporated to bolster robustness against scaling attacks, and BPD information refines the localization of detected forgeries.

Main Results:

  • The proposed SD-Net demonstrates high accuracy in detecting and localizing multiple, rotated, and scaled copy-move forgeries, performing exceptionally well on large-scale scaling forgeries.
  • SD-Net exhibits superior localization accuracy compared to existing methods.
  • The method proves robust against various post-processing operations, including brightness changes, contrast adjustments, color reduction, blurring, JPEG compression, and noise addition.

Conclusions:

  • SD-Net offers a significant advancement in copy-move forgery detection and localization.
  • The integration of super-BPD segmentation and DCNN with feature pyramids provides enhanced accuracy and robustness.
  • The proposed method is a reliable tool for safeguarding image integrity against sophisticated forgery techniques.