Privacy-Preserving Content-Based Image Retrieval Using Compressible Encrypted Images

Kenta Iida,Hitoshi Kiya

doi:10.1109/access.2020.3035563

Kenta Iida, Hitoshi Kiya

Open Access

https://doi.org/10.1109/access.2020.3035563

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 49	License type: CC BY 4.0

Affiliation: Tokyo Metropolitan University

Abstract

In this article, we propose a novel content-based image-retrieval (CBIR) scheme using compressible encrypted images called “encryption-then-compression (EtC) images.” The proposed scheme allows us not only to directly retrieve images from visually protected images but to also apply EtC images that can be compressed by using the JPEG standard for the first time. In addition, the sensitive management of secret keys is not required in our framework. The proposed retrieval scheme is carried out on the basis of weighted searching images with MPEG-7-powered localized descriptors (weighted SIMPLE descriptors) combining scalable color descriptor (SCD) or color and edge directivity descriptor (CEDD). Weighted SIMPLE descriptors are extended, and CEDD is also modified to avoid the influence of image encryption. In an experiment, the proposed scheme is demonstrated to have almost no degradation in retrieval performance compared with conventional content-based retrieval methods with plain images under the use of two datasets. In addition, the proposed scheme is shown to outperform conventional privacy-preserving CBIR schemes including state-of-the-art ones in terms of mean average precision (mAP) scores.

Highlights

With the rapid growth of cloud computing, outsourcing images to cloud storage services and sharing photos have greatly increased
We focus on a block scramblingbased image-encryption method that has been proposed for EtC systems [23]–[30], and encrypted images used in the systems are referred to as “EtC images.”
We focus on content-based image-retrieval (CBIR) because it is required that images be manually annotated with keywords and that extracted keywords be protected

Summary

INTRODUCTION

With the rapid growth of cloud computing, outsourcing images to cloud storage services and sharing photos have greatly increased. Privacy-preserving image-retrieval methods should satisfy three requirements: 1) protecting visual information on plain images, 2) having a high retrieval performance in the encrypted domain, and 3) being applicable to compressible encrypted images. In retrieval schemes using this type of encryption, it is required that the descriptors used for the retrieval be extracted from plain images, and encrypted for privacy-preserving by other forms of searchable encryption in general. K. Iida et al.: Privacy-Preserving Content-based Image Retrieval Using Compressible Encrypted Images methods extract descriptors from the content information of images, while images have to be manually annotated with keywords in TBIR methods.

ETC IMAGE

WEIGHTED SIMPLE DESCRIPTORS

THREAT MODEL

EXPERIMENT RESULTS FOR UKBENCH

Findings

CONCLUSION