Secure Outsourcing Algorithm of BTC Feature Extraction in Cloud Computing

Abstract

Advances in cloud computing have aroused many researchers' interest in privacy-preserving feature extraction over outsourced multimedia data, especially private image data. Since block truncation coding (BTC) is known as a simple and efficient technology for image compression, this paper focuses on privacy-preserving feature extraction in BTC compressed domain. We propose a privacy-preserving computation of BTC feature extraction over massive encrypted images (also called PPBTC). First, all images are uploaded to the cloud after encryption. The privacy-preserving image encryption process consists of block permutation, pixel diffusion, and a bit-plane random shift. BTC features remain unchanged after encryption and the cloud server can directly extract BTC features from the encrypted images. Some analyses and experimental results demonstrate that the proposed privacy-preserving feature extraction scheme for BTC-compressed images is efficient and secure, and it can be applied to secure image computation applications in cloud computing.

Keywords

• Feature extraction
• privacy-preserving
• block truncation coding
• homomorphic encryption