Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

High-Payload and Secure Data Hiding for Medical Images in IoMT-Based eHealth Systems.

Sensors (Basel, Switzerland)·2026

Same author

Relationship between the G Tolerance, Physical Performance, and Cardiac Force Index in Male Aircrew: A Prospective Observational Study.

Medicine and science in sports and exercise·2025

Same author

Steganography beyond space-time with chain of multimodal AI.

Scientific reports·2025

Same author

Dissecting the temporal genetic networks programming soybean embryo development from embryonic morphogenesis to post-germination.

Plant cell reports·2024

Same author

TALE-based organellar genome editing and gene expression in plants.

Plant cell reports·2024

Same author

Anti-Aliasing Attention U-net Model for Skin Lesion Segmentation.

Diagnostics (Basel, Switzerland)·2023

Search research articles

Related Experiment Video

Updated: Aug 9, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Anti-Screenshot Watermarking Algorithm for Archival Image Based on Deep Learning Model.

Wei Gu¹, Ching-Chun Chang², Yu Bai³

¹School of Computer Science and Technology, Anhui University, Hefei 230039, China.

Entropy (Basel, Switzerland)

|February 25, 2023

Summary

This summary is machine-generated.

This study introduces a novel deep learning model, ScreenNet, to improve anti-screenshot digital watermarking for archival images. The new method enhances image texture and robustness against ripping, significantly boosting watermark detection rates.

Keywords:

DLM Stegastamp anti-screenshot archival image image watermarking

More Related Videos

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Aug 9, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

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

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

Published on: December 15, 2023

Area of Science:

Computer Science
Digital Image Processing
Information Security

Background:

Archival images face increasing threats from ripping incidents, compromising their integrity.
Current anti-screenshot watermarking algorithms struggle with archival images due to their single texture, leading to low watermark detection rates.
Existing deep learning models for watermarking exhibit high bit error rates when applied to archival images.

Purpose of the Study:

To develop a robust anti-screenshot digital watermarking algorithm specifically for archival images.
To enhance the resilience of archival image watermarking against ripping and screenshot attacks.
To improve the detection rate and reduce the bit error rate of watermarks in compromised archival images.

Main Methods:

A novel deep learning model, ScreenNet, was developed for archival image watermarking.
Style transfer was employed in a preprocessing step to enrich image texture and background, mitigating screenshot interference.
A database of moiréd archival images was generated using moiréd networks to simulate ripping artifacts.
The ScreenNet model was improved and utilized for watermark encoding/decoding with the ripped archive database acting as a noise layer.

Main Results:

The proposed algorithm demonstrates significant robustness against anti-screenshot attacks.
The ScreenNet model effectively reduces the bit error rate of watermarks in archival images.
The algorithm successfully detects watermark information, enabling leak tracing of ripped archival images.

Conclusions:

The developed ScreenNet algorithm offers a robust solution for anti-screenshot watermarking of archival images.
The integration of style transfer and a moiréd image database enhances watermark detection and resilience.
This approach provides a viable method for protecting the integrity and traceability of archival image data.