Unlock instant, AI-driven research and patent intelligence for your innovation.

ResNet-DCT-based medical image robust zero-watermark algorithm

A medical image and zero watermark technology, applied in the field of medical image robust zero watermark algorithm, multimedia data protection, and medical image robust watermark

Pending Publication Date: 2022-04-19
HAINAN UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In short, the method of embedding a digital watermark that is resistant to geometric attacks such as rotation, scaling, translation, and shearing in ResNet-DCT-based medical images is still blank, and there is no public report

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
  • ResNet-DCT-based medical image robust zero-watermark algorithm
  • ResNet-DCT-based medical image robust zero-watermark algorithm
  • ResNet-DCT-based medical image robust zero-watermark algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0109] Below in conjunction with accompanying drawing, the present invention will be further described, and the object of experimental test is the medical image of 512 * 512 (size is set as 224 * 224 during actual input), see image 3 , represented by I(i,j), where 1≤i, j≤512. Select a meaningful binary image as the original watermark, recorded as: W={w(i,j)|w(i,j)=0,1; 1≤i≤M1,1≤j≤M2}, see Figure 4 , where the size of the watermark is 64×64. First, the original image is processed with the ResNet50 neural network to obtain the fc coefficient matrix (fc1000), and then the global DCT transformation is performed on the coefficient matrix. Considering the robustness and the capacity of one-time embedding watermark, we take 64 coefficients, that is, a 1×64 module. Set the initial value of the chaos coefficient to 0.2, the growth parameter to 4, and the number of iterations to 32. Then perform chaotic encryption on the original watermark, and the encrypted watermark can be seen i...

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 relates to a ResNet-DCT-based medical image robust zero-watermark algorithm, discloses a method for realizing the ResNet-DCT-based medical image robust zero-watermark algorithm, and belongs to the field of multimedia signal processing. The method comprises the following steps of: firstly, scrambling and encrypting a watermark in a frequency domain by utilizing the property of a Logistic Map; then, ResNet-DCT is carried out on the medical image to extract a feature vector to embed the watermark, the feature vector is associated with the binary watermark to obtain a binary logic sequence, and the binary logic sequence is stored in a third party; resNet-DCT is carried out on a medical image to be detected to extract a feature vector of the medical image, and the feature vector is associated with a binary sequence stored in a third party to carry out watermark extraction. The method is a medical image digital watermarking technology based on ResNet-DCT, has good robustness, is particularly prominent for geometric attacks such as rotation, translation and shearing, and is a zero-watermarking technology because the embedding of the watermark does not change the content of original encrypted volume data.

Description

technical field [0001] The present invention relates to a medical image robust watermarking technology based on ResNet-DCT transformation, chaotic mapping and image feature vectors, specifically a ResNet-DCT-based medical image robust zero-watermarking algorithm, which is a multimedia data protection method, It belongs to the field of multimedia signal processing. [0002] technical background [0003] With the development of science and technology, today's society is in the information age, traditional medical methods can no longer meet the needs of today, and gradually shift to the direction of telemedicine. This process cannot avoid a large number of medical images to be transmitted and shared through the network; in order to solve the problems that medical images may be tampered with and stolen during the transmission and sharing process, it is necessary to protect the original medical images; at present, zero watermarking technology and The combination of perceptual has...

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): G06T1/00G06N3/04G06N3/08G06F21/62
CPCG06T1/0064G06T1/0057G06N3/08G06F21/6245G06T2201/0065G06T2201/0051G06T2201/0052G06N3/045
Inventor 李京兵盛明帅陈延伟涂蓉邵春艳
Owner HAINAN UNIVERSITY