Earticle

초록

영어

With the growing popularity of cloud computing, more and more data owners are willing to outsource their data to the cloud. However, private data should be encrypted before outsourcing for security requirements, which obsoletes data utilization like content-based image retrieval. In this paper, we propose a secure similarity image search scheme, which allows data owners to outsource their encrypted image database to the cloud server without revealing the real content of images. The proposed scheme supports both global and local feature based image retrieval under various distance metrics, such as earth mover's distance. Firstly, the data owner extracts either global features or local features from images to represent the images. Then, these features are used to generate a searchable index. Finally, both image database and searchable index are encrypted before outsourcing to the cloud server. When a query image coming, the data user extracts feature from the query image and generates the search trapdoor. The trapdoor is then sent to the cloud server and used to compare the similarity with the searchable index. Extensive experiments are conducted to show the efficiency and applicability of our proposed similarity image search system.

목차

Abstract
 1. Introduction
 2. System Overview and Preliminaries
  2.1. System Architecture
  2.2. Earth Mover’s Distance
 3. The Proposed Scheme
  3.1. Notations
  3.2. Global Feature based Scheme
  3.3. Local Feature based Scheme
  3.4. LP Transformation
  3.5. Construction Detail
  3.6. Global Feature vs. Local Feature
 4. Security Analysis
 5. Implementation and Performance
  5.1. Precision
  5.2. Efficiency
 6. Related Work
 7. Conclusion
 Acknowledgements
 References

키워드

저자

• Yi Zhu [ Jiangsu Engineering Center of Network Monitoring, School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, China ]
• Xingming Sun [ Jiangsu Engineering Center of Network Monitoring, School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, China ]
• Zhihua Xia [ Jiangsu Engineering Center of Network Monitoring, School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, China ]
• Naixue Xiong [ School of Computer Science, Colorado Technical University, USA ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Security and Its Applications

• 간기

  격월간

• pISSN

  1738-9976

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605