Image storage and retrieval incur high storage and computation complexities and cloud computing offers an attractive choice for the image storage outsourcing and the on-demand access. Since the outsourced images often include sensitive information, privacy-preserving image outsourcing scheme becomes the biggest research hot spot. In this paper, we proposed a lightweight-client and privacy-preserving content-based image retrieval (CBIR) scheme, which has the following advantages: (1) to improve search accuracy, color and texture feature are integrated to construct index; (2) to reduce the client (owner and user) burden, computationally intensive tasks, texture feature extraction and index construction, are securely outsourced to cloud server; (3) to enhance search efficiency, a two-layer index structure is also adopted. The security analysis and the experiments show the security and efficiency of the proposed scheme.

Date Published: 6 May 2019
PDF: 9 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 1106922 (6 May 2019); doi: 10.1117/12.2524165

Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)