PLCOM: Privacy-preserving outsourcing computation of Legendre circularly orthogonal moment over encrypted image data

Abstract

In the image outsourcing system, image privacy is still an increasing concern since the cloud service provider and image owners are not in the same trusted domain. The most straightforward method for guaranteeing image privacy is to leverage cryptographic tools, but traditional cryptographic tools make feature extraction algorithms useless. To this end, we propose a privacy-preserving feature extraction scheme for Legendre circularly orthogonal moment, which is a novel global feature descriptor and can be used for image analysis. We first develop a novel feature descriptor, which is one of the circularly orthogonal moments and termed as Legendre Circularly Orthogonal Moment (LCOM). Then, we present a mathematical framework for implementing Privacy-preserving Legendre Circularly Orthogonal Moment (PLCOM) by combining LCOM and somewhat homomorphic encryption, and implement the image reconstruction in the encrypted domain based on PLCOM. Besides, the detailed theoretical analysis of message space and expanding factor generated by the quantitative technology shows that LCOM and image reconstruction in the plaintext domain can be realized with the aid of PLCOM. Finally, experimental results verify that the PLCOM’s performance in terms of image reconstruction capability and image recognition accuracy is acceptable.