Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image robust steganography method with reference generation

An image and original image technology, applied in the field of deep learning, to achieve the effect of high secret information embedding and high steganographic image quality

Pending Publication Date: 2020-12-25
ENG UNIV OF THE CHINESE PEOPLES ARMED POLICE FORCE
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are obvious gray patches in the image generated by the StegaStamp model, and as the amount of message embedding increases, the gray patches become more obvious

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
  • Image robust steganography method with reference generation
  • Image robust steganography method with reference generation
  • Image robust steganography method with reference generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0040] refer to figure 1 , a robust image steganography method with reference generation, including:

[0041] S1: Concealment of secret information

[0042] S11: Use the Residual-encoder model with a residual structure as the encoder, and use the original image and secret information as the input of the encoder, and the steganographic image as the output; wherein, the encoder uses perceptual loss constraints to generate image content, The calculation formula of perceptual loss is shown in formula (1):

[0043] (1)

[0044]in, represent the original image and the steganographic image, respe...

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 an image robust steganography method with reference generation, and relates to the technical field of deep learning. The method comprises the steps: taking an existing neural network model as an encoder, taking an original image and secret information as the input of the encoder, and taking a steganography image as the output; using an existing neural network model as a discriminator, using a steganography image as the input of the discriminator, and taking the difference between the mean values of an original image and the steganography image as the loss to judge the authenticity of the steganography image; and extracting and outputting secret information by taking an existing neural network model as a decoder and taking the steganography image added with the interference as input. Compared with other existing image robust steganography methods, the method has the advantages that the secret information extraction accuracy can be improved to 98.55%, and the secret information extraction rate can also reach 90% or above under the condition that interference is added.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to an image robust steganography method with reference generation. Background technique [0002] Traditional image steganography algorithms can be divided into two categories: spatial domain steganography algorithms and frequency domain steganography algorithms. The spatial domain steganography algorithm embeds secret information by modifying image pixels, such as LSB replacement and matching algorithm; the frequency domain steganographic algorithm embeds secret information by modifying some specified frequency domain coefficients in the main signal, such as discrete cosine transform (DCT) algorithm, discrete Fourier transform (DFT) algorithm, discrete wavelet transform (DWT) algorithm, etc. However, these traditional steganography algorithms lack robustness, and when transmitted in lossy channels such as social networks and wireless communications, slight interference will l...

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): G06T1/00G06N3/04G06N3/08
CPCG06T1/005G06N3/08G06N3/048G06N3/045Y02T10/40
Inventor 张敏情李宗翰刘佳
Owner ENG UNIV OF THE CHINESE PEOPLES ARMED POLICE FORCE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com