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

Method for steganography and reading of information in an image

An image-in-image technology, applied in the field of technical vision, can solve problems such as large noise, achieve the effect of high image quality, good information recovery robustness

Active Publication Date: 2020-04-17
珠海涵辰科技有限公司
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, a large amount of noise will be introduced during the entire transmission process from digital image to physical image, and then to digital image, which puts strict requirements on the robustness of the decoder.

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
  • Method for steganography and reading of information in an image
  • Method for steganography and reading of information in an image
  • Method for steganography and reading of information in an image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0054] Adopt the method of the present invention, construct such as Figure 4 The shown steganographic reading system, which is defined as DeStegaNet steganographic system, consists of 6 parts: encoder, decoder, saliency detector, encoded image detector, adversarial network, and noise simulation layer.

[0055] Encoder: given a RGB carrier image I with height H and width W and arbitrary binary data to be hidden M in ∈{0,1} L .First use the fully connected layer to process the hidden data and generate a vector with a fixed length of 7500. This vector is then upsampled and turned into a tensor of the same size as the cover image. This tensor and the carrier image are then combined into one input tensor I M ∈ R H×W×6 . Then a U-Net-style neural network structure is used to process the input tensor I M , outputting the encoded residual tensor I res ∈ R H...

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 belongs to the technical field of technical vision, and particularly relates to a method for steganography and reading of information in an image. According to the method, information ishidden in a non-salient region and a high-frequency region of an image to improve the human perception quality of a coded image; and meanwhile, the detector and the encoding / decoding system are trained together, so that the decoding system can automatically adapt to the positioning error of the detector to replace manual selection of the analog noise intensity, and finally, the balance between the robustness of the decoding system and the image quality is achieved.

Description

technical field [0001] The invention belongs to the technical field of visual technology, and in particular relates to a steganographic and reading method for information in an image. Background technique [0002] Steganography is an information hiding technology that hides private information in other public data carriers. Typically, these public data carriers contain images, video, audio, etc. Among them, information steganography in images has a long history of development and a wide range of application scenarios. Stealth communication is a classic application of steganography. It hides communication information in multimedia data such as digital images, while keeping the statistical characteristics and visual characteristics of the carrier data almost unchanged, so as to achieve the effect of deception. With the extensive development of the Internet, a large amount of multimedia data is generated on the network all the time. These public data provide a good cover for ...

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): G06T11/00G06K9/32H04N19/467H04N19/50
CPCG06T11/00H04N19/467H04N19/50G06V10/25
Inventor 杨诚
Owner 珠海涵辰科技有限公司
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