Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
COLOR IMAGE STEGANOGRAPHY METHOD BASED ON CONVOLUTIONAL NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2022/127374
Kind Code:
A1
Abstract:
A color image steganography method based on a convolutional neural network. The method comprises: making a data set that includes a carrier image and a secret image (S101); by taking the carrier image and the secret image as inputs, and a steganographic image and an extracted image as outputs, constructing an image steganography network model composed of a hiding network and an extraction network (S102); setting parameters of the image steganography network model, and training the image steganography network model (S103); and performing image steganography by using the trained image steganography network model (S104). In the color image steganography method based on the convolutional neural network, the embedding and extraction of a color image are realized by means of an image steganography network model composed of a hiding network and an extraction network, a generated steganographic image has a higher quality and security, and the steganography capacity is higher.

More Like This:
Inventors:
LI JINGBING (CN)
ZENG CHENG (CN)
LIU JING (CN)
CHEN YANWEI (CN)
Application Number:
PCT/CN2021/125640
Publication Date:
June 23, 2022
Filing Date:
October 22, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV HAINAN (CN)
International Classes:
G06T1/00
Foreign References:
CN112529758A2021-03-19
CN111292221A2020-06-16
CN109934761A2019-06-25
CN109587372A2019-04-05
Attorney, Agent or Firm:
UNITALEN ATTORNEYS AT LAW (CN)
Download PDF: