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, CBVR, is an active research topic. To make this feasible, development of a query language, which is simple (i.e., intuitive), yet powerful, is essential. In this paper, we propose a mosaic-based visual language for CBVR. Mosaicing is a well-known technique in computer vision and graphics for creating a comprehensive overview of a scene reproduced in a set of images. The language supports the specification of queries encompassing motion of objects and camera, as well as visual features, by arranging visual components on a mosaic image. The proposed language has then used to implement a graphical interface that allows users to specify and refine queries to a video database.