Anti-printing shot image digital watermarking method based on image noise reduction

An image noise reduction and digital watermarking technology, applied in image watermarking, image data processing, image data processing, etc., can solve the problems of robustness, embedding capacity and visual effects at the same time, and achieve high fidelity and embedding capacity Effects that balance and enhance visual effects

Pending Publication Date: 2020-08-28
SUN YAT SEN UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the technical defects that the existing image digital watermarking method only considers watermark embedding, noise modeling and watermark extraction modules, and cannot simult

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
  • Anti-printing shot image digital watermarking method based on image noise reduction
  • Anti-printing shot image digital watermarking method based on image noise reduction
  • Anti-printing shot image digital watermarking method based on image noise reduction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Such as figure 1 As shown, the present invention provides a digital watermarking method for printing and photographing images based on image noise reduction. It mainly constructs a powerful image noise reducer before the watermark information decoder to counteract the problems experienced by the image during printing and shooting. Noise attacks reduce as much as possible the impact of the printing and shooting process on the embedding and extraction of watermark information. It mainly includes: the construction of the image noise reduction layer, the structure design of the watermark codec and the adversarial training process. Specifically include the following steps:

[0073] S1: Model the noise in the printing and shooting process to build a noise layer; perform confrontation training on the generative countermeasure network GANs according to the noise layer to build an image noise reduction layer;

[0074] S2: The original image and the noise image after the noise layer...

Embodiment 2

[0128] More specifically, the method provided by the present invention includes:

[0129] 1. Training of image noise reduction layer, see step 11)-12)

[0130] 11) Modeling the noise of the printing and shooting process, mainly including geometric distortion, motion blur, color transformation, additive noise and JPEG attack, etc., respectively using affine transformation, blur kernel convolution, channel interpolation, histogram scaling, Additive Gaussian noise and differentiable JPEG algorithm are simulated.

[0131] 12) Use a generative countermeasure network to denoise the noisy image, and the original image I input Input to the noise layer, get noisy image I noise And sent to the generator in the noise reduction layer, the output of the generator is the denoised image I denoise , The original image I input And denoised image I denoise Substitute into the optimization function formula 1, and use them as the input of the discriminator in the noise reduction layer, perform the ...

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 provides an anti-printing shot image digital watermarking method based on image noise reduction. A generative adversarial network is adopted to construct an image noise reduction layer capable of resisting possible noise attacks of an image in the printing and shooting process, simultaneous attacks of various kinds of noise can be resisted, a better noise reduction effect is achieved, and it is guaranteed that the image has high fidelity; an image noise reduction layer is added into the whole watermark embedding and extracting training framework; the image noise reduction layer achieves the function of resisting noise attacks, and ensures robustness to a certain extent, so that the watermark codec can focus on improving the visual effect after watermark embedding, the watermark detection accuracy and the embedding capacity, and the balance of three indexes of robustness, the visual effect and the embedding capacity is realized.

Description

Technical field [0001] The invention relates to the technical field of computer vision and image information hiding, and more specifically, to a digital watermarking method for anti-printing photographed images based on image noise reduction. Background technique [0002] In recent years, the rapid development of multimedia technology has made information dissemination more efficient and convenient. It has brought great convenience for users to access, obtain, print, or store multimedia data such as images, videos, and texts. At the same time, it has also reduced the media for counterfeiters. The threshold for information tampering, forgery and misappropriation. The image digital watermark method embeds specific identification information in the image without destroying the visual effect of the image, and is a commonly used method in copyright protection and authentication and anti-counterfeiting. [0003] The existing methods are divided into traditional image processing methods ...

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): G06T1/00G06T5/00G06N3/04G06N3/08
CPCG06T1/005G06T5/002G06N3/084G06N3/045
Inventor 林夏娜倪江群张木水
Owner SUN YAT SEN UNIV
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