Supercharge Your Innovation With Domain-Expert AI Agents!

High-capacity image hiding method and system based on coding-decoding network

A decoding network and encoding network technology, which is applied in biological neural network models, image communication, electrical components, etc., can solve the problem of poor quality of secret image reconstruction with secret image quality, and achieve the effect of improving image quality and visual quality

Pending Publication Date: 2021-11-30
NANJING UNIV OF INFORMATION SCI & TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the prior art, the purpose of the present invention is to provide a large-capacity image-to-image method and system based on an encoding-decoding network, which is used to solve the problems existing in the existing steganographic models of the above-mentioned background technology. The quality of the secret image and the poor quality of the reconstructed secret image

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • High-capacity image hiding method and system based on coding-decoding network
  • High-capacity image hiding method and system based on coding-decoding network
  • High-capacity image hiding method and system based on coding-decoding network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] An embodiment of the present invention provides a large-capacity image-to-image method based on an encoding-decoding network, such as figure 1 As shown, it specifically includes the following steps:

[0069] S1, input a carrier image and two secret images to the dual-branch encoding network based on the Res2Net-Inception-SE module to generate a secret image;

[0070] In the specific implementation process, the carrier image is independently input to one branch of the encoding network, and the two secret images are input to the other branch of the encoding network after channel stacking operation.

[0071] In a specific implementation of the Fang Ming embodiment, such as figure 2 As shown, the dual-branch encoding network based on the Res2Net-Inception-SE module includes: the first convolution operation group Conv1_c of the carrier branch, the Res2Net-Inception-SE module R_c of the carrier branch, the second convolution operation group Conv2_c of the carrier branch, a...

Embodiment 2

[0123] Based on the same inventive concept as in Embodiment 1, an embodiment of the present invention provides a large-capacity image-to-image system based on an encoding-decoding network, including:

[0124] A generating unit for inputting a carrier image and two secret images into a dual-branch encoding network based on the Res2Net-Inception-SE module to obtain a secret image embedded with two secret images;

[0125] A reconstruction unit, configured to input the secret image into the W-Net network to obtain two reconstructed secret images;

[0126] The training unit is used to design a mixed loss function according to the quality of the dense image and the quality of the reconstructed secret image, and use it as the total loss function of the steganographic network, and optimize the steganographic network with the goal of minimizing the loss function. When the loss decreases And think that training ends when keeping stable; Described steganography network comprises the two-...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a high-capacity image hiding method and system based on a coding-decoding network, and belongs to the technical field of image processing, and the method comprises the steps: inputting a carrier image and two secret images into a double-branch coding network based on a Res2Net-Inception-SE module, obtaining a secret-containing image, inputting the secret-containing image into a W-Net decoding network, obtaining two reconstructed secret images, designing a mixed loss function according to the secret-containing image quality and the reconstructed secret image quality, taking the mixed loss function as a total loss function of the steganography network, optimizing the steganography network with the purpose of minimizing the loss function, and when the loss is reduced and kept stable, determining that training ends. compared with the existing algorithm, the method has the advantages of high hiding capacity and high concealment.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a large-capacity image-to-image storage method and system based on an encoding-decoding network. Background technique [0002] While the development of Internet technology has brought great convenience to people's lives, it has also created many information security problems, such as the leakage of personal privacy information and the illegal theft of commercial confidential data. Therefore, people pay more and more attention to the security issues in the process of data communication. [0003] Steganography is one of the main methods to ensure communication security. It embeds secret information into the carrier through a specific algorithm, and then the recipient of the secret information extracts the secret information through an extraction algorithm. Commonly used steganographic carriers include text, images, audio, video, etc. Among them, the image its...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04N1/32H04N1/44G06N3/04
CPCH04N1/32272H04N1/4446G06N3/045Y02T10/40
Inventor 胡欣珏付章杰
Owner NANJING UNIV OF INFORMATION SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com