Hierarchical privacy preservation for personalized image retrieval

  • Authors:

  • Li Zhuo;Mengmeng Diao;Jing Zhang;Zhenwei Li

  • Affiliations:

  • Beijing University of Technology, Beijing, P.R. China;Beijing University of Technology, Beijing, P.R. China;Beijing University of Technology, Beijing, P.R. China;Beijing University of Technology, Beijing, P.R. China

  • Venue:
  • Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the rapid development of multimedia and Internet technologies, the number of digital images is growing with an amazing speed. Nowadays, more and more researchers pay attention to the personalized image retrieval which has become a hot research topic. However, personalized retrieval must collect user's personal information to provide the retrieval results for different users, and thus this approach inevitably touches the sensitive nerve of user's privacy. This paper will focus on the privacy problem of the personalized image retrieval to study a user's privacy preservation scheme with hierarchical structure. First, user profile is obtained by using user interest model of personalized image retrieval. Then, a hierarchical structure profile is constructed by using the user's profile. Finally, the privacy preservation is imposed into personalized image retrieval. Experimental results show proposed method can preserve the user's personal privacy by selecting the different levels of privacy preservation, as well as meet the needs of users' personalize retrieval.