Secure and efficient image retrieval based on global features

Abstract

Abstract A few years ago, an image retrieval needs have been increased enormously. Therefore, a need for an efficiency and accurate image retrieval scheme has become desired accordingly. In fact, the images require high storage space; for this reason, cloud computing considers the best selective to outsource images. Many outsourcing images to the cloud server such as medical, police investigation, and personal images that require to encrypt before being outsourced to the cloud servers. However, in this paper a robust scheme has been presented which provides Content Based Image Retrieval (CBIR) over the encrypted images without declassing the important information to the cloud server side. Additionally, the information is exchanging in the strong secure manner among entities. The proposed scheme consists of two phases: setup phase and retrieve phase. The first phase based on build secure dictionary based on global features (intensity of histogram) and images decryption while the second phase utilizes secure query to retrieve the queried image. This scheme is a robust to measure the Euclidean Distance similarity between two queries without decryption. The security and efficiency of the proposed scheme are proofed by security analysis and experiments.