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

Non-destructive digital rights management method for fundus images based on hybrid architecture of fingerprint and zero watermark

A fundus image and watermark image technology, applied in the field of information security, can solve the problems of not fully meeting the digital copyright management of fundus images, high requirements for digital copyright management, and no copyright information, so as to achieve reliable copyright identification, accurate diagnosis, The effect of avoiding one-time problems

Inactive Publication Date: 2018-10-19
CENT SOUTH UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the extraction of digital fingerprints is the inherent characteristics of digital images, and there is no clear copyright information, such as publisher information, use right approval judgment information, etc., which may cause unnecessary copyright disputes
[0008] Since fundus images are mostly used in the medical industry, the requirements for digital rights management are relatively high. None of the existing digital rights management methods can fully meet the many requirements for digital rights management of fundus images.

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
  • Non-destructive digital rights management method for fundus images based on hybrid architecture of fingerprint and zero watermark
  • Non-destructive digital rights management method for fundus images based on hybrid architecture of fingerprint and zero watermark
  • Non-destructive digital rights management method for fundus images based on hybrid architecture of fingerprint and zero watermark

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0093] 150 fundus images are selected for various image attacks. The specific description of the image attack form is as follows:

[0094] Blur: Gaussian blur kernels of size 9×9 and 15×15 were applied to the fundus images, respectively.

[0095] Contrast adjustment: enhance and weaken the contrast of the fundus image respectively, the parameters are ±30% and ±50%.

[0096] Brightness adjustment: respectively enhance and reduce the brightness of the fundus image, the parameters are ±30% and ±50%.

[0097] Filtering: The average filter kernel and median filter kernel with sizes of 9×9 and 15×15 are applied to the fundus image respectively

[0098] Gaussian Noise: Adds 10% and 30% Gaussian noise to the image respectively.

[0099] Salt and Pepper Noise: Add salt and pepper noise to the image, and the noise densities are 0.03 and 0.05 respectively.

[0100] Resizing: Change the size settings of the image with a size factor of 0.5 and 0.2 respectively.

[0101] Rotate: Rotate...

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 non-destructive digital copyright management method for fundus images based on a hybrid structure of fingerprints and zero watermarks. The method first performs 2D-DCT transformation on the normalized fundus images, and extracts features by setting different weights for the transformed coefficients. Highly Discriminative and Robust Fundus Image Features as Fingerprints for Content-Based Retrieval. Then the zero-watermark copyright protection method based on the VSS visual cryptography algorithm establishes the mapping relationship between fingerprints and watermarks for copyright identification. Compared with existing methods, this method has the following advantages: the whole process of the method is non-destructive and meets the requirements of accurate diagnosis; the copyright protection of fundus images is durable, avoiding the one-time problem of digital watermark copyright identification; it is suitable for fundus images The digital rights management method has certain clinical significance for the auxiliary diagnosis of fundus-related diseases.

Description

technical field [0001] The invention belongs to the field of information security, and relates to a non-destructive digital rights management method for fundus images based on a mixed architecture of fingerprints and zero watermarks. Background technique [0002] Fundus images are images taken from different angles of the inner wall of the eyeball with a fundus camera, and are a standard objective diagnostic image. Various fundus diseases such as diabetic retinopathy, glaucoma, hypertension, age-related macular degeneration, etc. can be reflected in fundus images. Therefore, the processing and analysis of fundus images is of great significance to the early screening, diagnosis, treatment and auxiliary diagnosis and treatment of these diseases. As a part of medical digital content, fundus images, as well as their inherent clinical medical value and research value, indicate that fundus images should be effectively protected. However, according to the survey, there is current...

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 Patents(China)
IPC IPC(8): G06F21/10G16H30/20G06F17/30G06K9/62G06T1/00
CPCG06F16/583G06F21/10G06T1/0021G06F18/22
Inventor 邹北骥杜婧瑜刘熙尧
Owner CENT SOUTH UNIV
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