| Paper ID | SS-5.2 |
| Paper Title |
A SECURE SEARCHABLE IMAGE RETRIEVAL SCHEME WITH CORRECT RETRIEVAL IDENTITY |
| Authors |
Liejun Wang, Haitao Yu, Xinjiang University, China |
| Session | SS-5: Domain Adaptation for Multimedia Signal Processing |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Special Sessions: Domain Adaptation for Multimedia Signal Processing |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
As the image retrieval scheme continues to mature, many areas such as industrial and business have begun to apply more user-friendly techniques, namely image retrieval, instead of the text data retrieval technology. However, in some applications, the phenomenon of insufficient privacy protection for user images has been exposed. Aiming at the issue of user privacy, we proposed a Secure searchable image retrieval scheme with correct retrieval identity. We use the elliptic curve cryptography to realize the identification of entity identities in our scheme. Pre-filter tables can be constructed by local sensitive hash functions to build to optimize retrieval efficiency. The results of our experiments show that the statistical information of image data can be well protected and the entity identities in the system can be correctly identified. Due to the introduction of the pre-filtering table, the efficiency of image retrieval is higher than that of linear retrieval. |
