PROJECT TITLE :

Towards Privacy-Preserving Content-Based Image Retrieval in Cloud Computing - 2018

ABSTRACT:

Content-based image retrieval (CBIR) applications are rapidly developed along with the increase in the amount, availability and importance of images in our existence. But, the wide deployment of CBIR scheme has been restricted by its the severe computation and storage requirement. In this Project, we have a tendency to propose a privacy-preserving content-based image retrieval scheme, which permits the info owner to outsource the image database and CBIR service to the cloud, without revealing the particular content of the database to the cloud server. Local options are utilized to represent the images, and earth mover's distance (EMD) is used to judge the similarity of images. The EMD computation is essentially a linear programming (LP) problem. The proposed theme transforms the EMD problem in such a means that the cloud server will solve it while not learning the sensitive data. In addition, local sensitive hash (LSH) is utilized to boost the search potency. The security analysis and experiments show the security and efficiency of the proposed scheme.