Going beyond completeness in information retrieval
DNIS'07 Proceedings of the 5th international conference on Databases in networked information systems
Going beyond completeness in information retrieval
International Journal of Computational Science and Engineering
| Hi-index | 0.00 |
Content-based video retrieval is one of the mostactive research issues in multimedia community. In thispaper, we propose a system for retrieving video data bymeans of mosaic images. Mosaicing is a technique ofjoining/merging frames of a shot into one blended image.The resulting mosaic image can convey three primitivefeatures in videos, that is, background, (moving) objects,and camera work such as pan, tilt and zoom. Thanks tothis capability, the user can retrieve video databases in apowerful way by specifying queries encompassing thecondition of those three types of video features.