Share Email Print

Proceedings Paper

Feature management for large video databases
Author(s): Farshid Arman; Arding Hsu; Ming-Yee Chiu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Large video databases, as well as many other applications involving video, such as multimedia, training, and `movie-on-demand' systems, require efficient steps to manipulate the enormous amount of data associated with full motion video. In this paper the incoming video is systematically and efficiently reduced via a frame selection procedure which takes advantage of the fact that the incoming video is encoded using one of several existing DCT- based standards. The procedure is performed in the frequency domain prior to video decoding. Further refinement in the frame selection step is achieved using a robust metric based upon the color histogram of the selected subset of decoded frames. The procedure is presented in detail and several examples are exhibited.

Paper Details

Date Published: 14 April 1993
PDF: 11 pages
Proc. SPIE 1908, Storage and Retrieval for Image and Video Databases, (14 April 1993); doi: 10.1117/12.143638
Show Author Affiliations
Farshid Arman, Siemens Corporate Research, Inc. (United States)
Arding Hsu, Siemens Corporate Research, Inc. (United States)
Ming-Yee Chiu, Siemens Corporate Research, Inc. (United States)

Published in SPIE Proceedings Vol. 1908:
Storage and Retrieval for Image and Video Databases
Carlton Wayne Niblack, Editor(s)

© SPIE. Terms of Use
Back to Top