摘要
传统基于非对称直方图修改的图像可逆信息隐藏算法存在大量像素无效修改的问题。针对此问题,提出了一种基于多对非对称预测误差直方图修改的可逆信息隐藏方案。该方案结合了非对称直方图修改算法的优势和多直方图修改算法的特点,选择图像的平滑区域进行非对称直方图修改以嵌入信息。在达到发挥非对称直方图补偿还原效应的同时,能进一步减少像素的无效修改量,提高率失真性能。
There are many invalid modifications of pixels in traditional reversible image information hiding algorithms based on asymmetric histogram modification.To solve this problem,a reversible information hiding scheme based on multi-pair asymmetric prediction error histogram modification is proposed in this paper.This scheme combines the advantages of asymmetric histogram modification algorithm and the characteristics of multihistogram modification algorithm,and selects the smooth region of the image to modify the asymmetric histogram for embedding information.At the same time of achieving the compensation reduction effect of asymmetric histogram,it can further reduce the invalid pixel modification and improve the rate distortion performance.
作者
何玉芬
汤进
殷赵霞
HE Yufen;TANG Jin;YIN Zhaoxia(Lu’an Educational Science Research Institute,Lu’an 237000,Anhui,China;School of Computer Science and Technology,Anhui University,Hefei 230601,Anhui,China)
出处
《应用科学学报》
CAS
CSCD
北大核心
2022年第2期253-265,共13页
Journal of Applied Sciences
基金
国家重点研发计划-新一代人工智能重大项目(No.2018AAA0100400)
国家自然科学基金面上项目(No.61872003)资助
关键词
可逆信息隐藏
预测误差
非对称直方图
多直方图
直方图修改
reversible data hiding
prediction error
asymmetric histogram
multi-histogram
histogram modification