Jove
Visualize
Contact Us

Related Experiment Video

Updated: Dec 23, 2025

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

931

Exposing Digital Image Forgeries by Detecting Contextual Abnormality Using Convolutional Neural Networks.

Haneol Jang1, Jong-Uk Hou2

  • 1Cyber Security Research Division, The Affiliated Institute of ETRI, Daejeon 34044, Korea.

Sensors (Basel, Switzerland)
|April 23, 2020
PubMed
Summary

Related Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

8.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
8.0K

You might also read

Related Articles

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

Sort by
Same author

JPEG-aware steganalysis: explicit frequency modeling with dequantized DCT for real-world JPEG images.

Scientific reports·2026
Same author

An exploratory study of headache pain intensity using facial expressions and APEX frames.

NPJ digital medicine·2026
Same author

Analyzing the effect of reasoning-based supervision on face anti-spoofing.

Scientific reports·2026
Same author

An artificial intelligence-based image recognition model using indocyanine green cholangiography to identify the hepatocystic triangle during minimally‑invasive cholecystectomy.

Wideochirurgia i inne techniki maloinwazyjne = Videosurgery and other miniinvasive techniques·2026
Same author

Assessment of the Prognostic Value of the ABC Score in Non-Variceal UGIB Showing Superiority to Traditional Scores, With Room for Improvement: A Retrospective Observational Study.

The Korean journal of helicobacter and upper gastrointestinal research·2025
Same author

Classifying Advanced Driver Assistance System (ADAS) Activation from Multimodal Driving Data: A Real-World Study.

Sensors (Basel, Switzerland)·2025
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

This study introduces a novel deep learning framework for digital image forensics. It detects image manipulation by analyzing contextual abnormalities, offering improved robustness against noise compared to traditional low-level feature methods.

Area of Science:

  • Computer Science
  • Digital Forensics
  • Artificial Intelligence

Background:

  • Traditional digital image forensics relies on low-level features (e.g., edges, texture).
  • These low-level features are vulnerable to common image processing techniques like JPEG compression and resizing, which introduce noise.
  • Existing methods struggle with noise, limiting their effectiveness in detecting image manipulation.

Purpose of the Study:

  • To propose a robust framework for detecting image manipulation using deep neural networks.
  • To overcome the limitations of traditional methods vulnerable to noise.
  • To leverage contextual information for more reliable image forgery detection.

Main Methods:

  • Utilizes deep neural networks, specifically a region-based convolutional neural network (R-CNN), for object detection.
Keywords:
R-CNNcontextual abnormalitydeep learningdigital image forensicslocalization

Related Experiment Videos

Last Updated: Dec 23, 2025

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

931
  • Identifies object classes and their locations within an image.
  • Evaluates contextual scores based on object combinations, spatial context, and object positions.

    • Main Results:

    • The proposed method effectively detects contextual abnormalities in images.
    • Demonstrates robustness against noise introduced by image processing techniques.
    • Successfully identifies image forgeries by analyzing semantic context rather than low-level features.

    Conclusions:

    • Deep neural networks offer a promising approach for robust digital image forensics.
    • Contextual abnormality detection provides a more resilient method for identifying image manipulation compared to traditional techniques.
    • The framework's ability to identify objects enables effective forgery detection even with noisy image data.