Open Access
ARTICLE
Image Feature Computation in Encrypted Domain Based on Mean Value
Xiangshu Ou1, Mingfang Jiang2,*, Shuai Li1, Yao Bai1
1 Department of Mathematics and Computational Science, Hunan First Normal University, Changsha, 410205, China
2 Department of Information Science and Engineering, Hunan First Normal University, Changsha, 410205, China
* Corresponding Author: Mingfang Jiang. Email:
Journal of Cyber Security 2020, 2(3), 123-130. https://doi.org/10.32604/jcs.2020.09703
Received 15 January 2020; Accepted 23 July 2020; Issue published 14 September 2020
Abstract
In smart environments, more and more teaching data sources are
uploaded to remote cloud centers which promote the development of the smart
campus. The outsourcing of massive teaching data can reduce storage burden and
computational cost, but causes some privacy concerns because those teaching
data (especially personal image data) may contain personal private information.
In this paper, a privacy-preserving image feature extraction algorithm is
proposed by using mean value features. Clients use block scrambling and chaotic
map to encrypt original images before uploading to the remote servers. Cloud
servers can directly extract image mean value features from encrypted images.
Experiments show the effectiveness and security of our algorithm. It can achieve
information search over the encrypted images on the smart campus.
Keywords
Cite This Article
X. Ou, M. Jiang, S. Li and Y. Bai, "Image feature computation in encrypted domain based on mean value,"
Journal of Cyber Security, vol. 2, no.3, pp. 123–130, 2020.