Robust efficient distributed face image steganography method

A face image, distributed technology, applied in the field of image steganography and computer vision, can solve the problem of not being able to fit the task of face image steganography well, achieve real-time high-resolution image decoding, improve robustness and safety effect

Active Publication Date: 2021-08-31
湖南汇视威智能科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing deep learning-based image steganography models still have some problems in terms of security and practicability, and cannot be well suited to the task of face image steganography.

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
  • Robust efficient distributed face image steganography method
  • Robust efficient distributed face image steganography method
  • Robust efficient distributed face image steganography method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] 1. Dataset

[0062] For the secret image, the LFW data set is selected. LFW is a commonly used data set for face recognition at present. The face pictures provided are all from natural scenes in life, so the recognition difficulty will increase, especially due to multiple poses, lighting, and expressions. Due to factors such as age, occlusion, etc., even the photos of the same person are very different, so it is very consistent with the face image in the real scene. The LFW data set has a total of 13,233 face images, and each image has a corresponding name. There are 5,749 people in total, and most of them have only one picture, and the size of each picture is 250×250. But it will be scaled to 256×256 for training or testing. When training, select 10,000 of them as the training set and 3,232 as the test set, and there is no intersection between the training set and the test set pictures.

[0063] The carrier image is not suitable for using existing face images due to ...

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 robust efficient distributed face image steganography method, which comprises the following steps of: for a given secret face image, encoding the given secret face image and a plurality of carrier face images generated by a generative adversarial network into a plurality of secret-carrying images in a distributed manner by an encoder, and decoding the secret-carrying images into a plurality of secret images by a decoder, and adopting an adaptive synthesizer to synthesize the secret images into a final restored secret face image. The encoder and the decoder provided by the invention are excellent in performance, efficient in calculation and low in consumption of calculation resources. The distributed steganography method provided by the invention is higher in robustness and safer. And a standard of steganography performance of the first human face image is established. Therefore, the method has important application value in the fields of face image privacy protection and the like.

Description

technical field [0001] The invention belongs to the field of image steganography and computer vision, and protects the privacy of human face images by performing distributed image steganography on human face images. Background technique [0002] Image steganography is an important means of information hiding. It is a technology that can embed secret information in a carrier image to form a secret image, and can recover the secret information from the secret image. Face image steganography is to embed the face image as a secret image in the carrier image to achieve the purpose of privacy protection, and at the same time, it is necessary to ensure that the recovered face image is still unique and identifiable. [0003] The existing traditional steganography algorithm embeds the secret information into the space domain or transformation domain of the carrier image through the artificially designed feature extraction and embedding algorithm, which already has good security. But...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/60G06T9/00G06N3/04G06N3/08
CPCG06F21/60G06T9/002G06N3/08G06N3/045
Inventor 彭智亮顾善植蓝丹吴瑶王聪睿胡亚清谢良殷悦王明兴杨石梦
Owner 湖南汇视威智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap