基于显著性目标检测的选择性混沌图像加密  

Selective Chaotic Image Encryption Based on Salient Object Detection

作　　者：宦立鑫 HUAN Lixin(School of Computer Science and Engineering,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001

出　　处：《现代信息科技》2022年第9期84-88,91,共6页Modern Information Technology

摘　　要：针对当前大多数图像加密算法都是对整体图像进行加密,文章提出了一种选择性混沌图像加密算法,该算法只对图像的重要区域进行加密。首先使用显著性目标检测算法对明文图像进行预处理,识别出明文图像的重要区域;之后再用混沌图像加密算法对图像的重要区域进行加密。该算法根据明文图像的像素值生成加密密钥,能够有效地抵抗选择明文攻击。实验结果表明,该算法能够实现对图像重要区域的有效保护。与对整体图像加密相比,该文加密算法大大提升了图像加密的效率。In view of the fact that most current image encryption algorithms encrypt the whole image, this paper proposes a selective chaotic image encryption algorithm, which only encrypts the important areas of the image. Firstly, the salient object detection algorithm is used to preprocess the plaintext image and identify the important regions of the plaintext image, and then the chaotic image encryption algorithm is used to encrypt the important areas of the image. The algorithm generates the secret key according to the pixel value of the plaintext image, which can effectively resist the chosen-plaintext attack. Experimental results show that the algorithm can effectively protect the important areas of the image. Compared with the whole image encryption, the encryption algorithm proposed in this paper greatly improves the efficiency of image encryption.

关 键 词：混沌 图像加密 显著性目标检测 选择明文攻击 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]