首页> 外文会议>International Conference on Artificial Intelligence and Security >A Robust Zero-Watermarking Algorithm for Medical Images Using Curvelet-Dct and RSA Pseudo-random Sequences
【24h】

A Robust Zero-Watermarking Algorithm for Medical Images Using Curvelet-Dct and RSA Pseudo-random Sequences

机译:基于Curvelet-Dct和RSA伪随机序列的医学图像鲁棒零水印算法

获取原文

摘要

With the popularization of digital medicine, the protection of patients' privacy has become extremely important in the medical field. Embedding watermarks into medical images is one of the effective ways to protect patients' privacy. However, the existing watermarking algorithms have poor robustness under geometric attacks. To solve this problem, aiming at the particularity of medical image, a robust zero-watermarking algorithm using Curvelet-Dct and RSA pseudo-random sequence is proposed in this paper. First, extract the visual feature vectors of medical images where the energy is most concentrated via perform DCT transformation on the Coarse layer of Curvelet transformation. Then, the pseudo-random sequence generated by the RSA algorithm is used to encrypt the watermark which improved the security of the patients' privacy. Combined with the concept of zero-watermark, the experimental results show that the proposed algorithm has good robustness in both conventional attacks and geometric attacks.
机译:随着数字医学的普及,保护患者隐私在医学领域已变得极为重要。在医疗图像中嵌入水印是保护患者隐私的有效方法之一。但是,现有的水印算法在几何攻击下鲁棒性较差。针对这一问题,针对医学图像的特殊性,提出了一种基于Curvelet-Dct和RSA伪随机序列的鲁棒零水印算法。首先,通过在Curvelet变换的粗糙层上执行DCT变换,提取能量最集中的医学图像的视觉特征向量。然后,使用RSA算法生成的伪随机序列对水印进行加密,提高了患者隐私的安全性。结合零水印的概念,实验结果表明,该算法在传统攻击和几何攻击方面均具有良好的鲁棒性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号