Video content representation using optimal extraction of frames and scenes
- 1 January 1998
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 875-879
- https://doi.org/10.1109/icip.1998.723660
Abstract
In this paper, an efficient video content representation is proposed using optimal extraction of characteristic frames and scenes. This representation, apart from providing browsing capabilities to digital video databases, also allows more efficient content-based queries and indexing. For performing the frame/scene extraction, a feature vector formulation of the images is proposed based on color and motion segmentation. Then, the scene selection is accomplished by clustering similar scenes based on a distortion criterion. Frame selection is performed using an optimization method for locating a set of minimally correlated feature vectors.Keywords
This publication has 4 references indexed in Scilit:
- Content-based image retrieval with relevance feedback in MARSPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Eigen-image based video segmentation and indexingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Joint adaptive space and frequency basis selectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Blockmatching motion estimation algorithms-new resultsIEEE Transactions on Circuits and Systems, 1990