电信科学 ›› 2017, Vol. 33 ›› Issue (11): 102-111.doi: 10.11959/j.issn.1000-0801.2017254

• 研究与开发 • 上一篇    下一篇

基于SVD和SAE的医学图像多功能零水印算法

孙洁丽1,赵彦霞1,2,周增慧3,邢胜4   

  1. 1 河北经贸大学信息技术学院,河北 石家庄 050061
    2 河北大学管理学院,河北 保定 071002
    3 河北经贸大学教务处,河北 石家庄 050061
    4 沧州师范学院计算机科学与工程学院,河北 沧州 061001
  • 修回日期:2017-08-05 出版日期:2017-11-01 发布日期:2017-12-08
  • 作者简介:孙洁丽(1969-),女,博士,河北经贸大学教授,主要研究方向为信息处理、数据挖掘。|赵彦霞(1970-),女,河北大学管理学院博士生,河北经贸大学讲师,主要研究方向为数字水印、不确定知识管理与机器学习、信息处理。|周增慧(1975-),男,河北经贸大学工程师,主要研究方向为信息管理、数据挖掘。|邢胜(1982-),男,博士,沧州师范学院讲师,主要研究方向为不确定知识管理与机器学习。
  • 基金资助:
    国家自然科学基金资助项目(71371063);国家自然科学基金资助项目(61672205);河北省应用基础研究计划重点基础研究项目(16960314D);河北省人力资源社会保障科研合作课题(JRSHZ-2016-07038)

Multipurpose zero watermarking algorithm for medical image based on SVD and SAE

Jieli SUN1,Yanxia ZHAO1,2,Zenghui ZHOU3,Sheng XING4   

  1. 1 College of Information and Technology,Hebei University of Economics and Business,Shijiazhuang 050061,China
    2 College of Management,Hebei University,Baoding 071002,China
    3 Educational Administration Office,Hebei University of Economics and Business,Shijiazhuang 050061,China
    4 College of Computer Science and Engineering,Cangzhou Normal University,Cangzhou 061001,China
  • Revised:2017-08-05 Online:2017-11-01 Published:2017-12-08
  • Supported by:
    The National Natural Science Foundation of China(71371063);The National Natural Science Foundation of China(61672205);The Key Basic Research Project of Applied Basic Research Program of Hebei Province(16960314D);The Science and Technology Cooperation Project of Hebei Provincial Department of Human Resources and Social Security(JRSHZ-2016-07038)

摘要:

针对医学图像的版权保护和篡改定位问题,提出了一种多功能零水印算法。获取构造零顽健水印和半脆弱水印的信息矩阵,并分别与原始顽健和半脆弱水印进行异或运算,构造零顽健和零半脆弱水印图像。实验结果证明,提取的水印效果较好,算法能很好地抵抗常见攻击,特别是抵抗强度较大的攻击的效果较好。

关键词: 医学图像, 多功能零水印, 离散小波变换, 奇异值分解, 堆叠自编码器

Abstract:

A multipurpose zero watermarking algorithm was proposed according to the copyright protection and tamper location of medical image.The two information matrices were executed the XOR operation with the original robust watermarking image and the original semi-fragile watermarking image separately to generate zero robust watermarking image and zero semi-fragile watermarking image.The experimental results show that effects of extracted zero watermarking image are terrific,and the algorithm can resist the common attacks,particularly its resistance is effect ive for strong attacks.

Key words: medical image, multipurpose zero watermarking, discrete wavelet transform, stacked auto-encoder

中图分类号: 

No Suggested Reading articles found!