期刊
JOURNAL OF REAL-TIME IMAGE PROCESSING
卷 16, 期 3, 页码 765-773出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s11554-018-0826-4
关键词
Image encryption; Image compression; VAE; Generative model
类别
资金
- National Natural Science Foundation of China [U1204606, U1604156]
- Key Programs for Science and Technology Development of Henan Province [172102210335, 172102210045]
- Key Scientific Research Projects in Henan Universities [16A520058]
Efficient image encryption and compression not only well protect the security of image information, but also greatly reduce the bandwidth. This paper proposes an image encryption method based on variational auto-encoder generation model. Firstly, we use the random gradient method to train the variational auto-encoder generation model, and iteration times of the model is determined comprehensively by the training time, the loss function and the reconstruction image. The peak signal-to-noise ratio and mean square error are used to measure the compression effect of the model. Secondly, we utilize the two trained image data divisions to change the data of the generated model, and to generate an encryption image. Finally, this paper uses Spyder to simulate experiments and analyze the results. The experimental results show that the method is fast and easy to encrypt, the algorithm is simple and the distortion rate of the decrypt image is low, and it is strong practicality.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据