Comparison and combination of two novel commercial detection methods
- 21 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1267-1270 Vol.2
- https://doi.org/10.1109/icme.2004.1394454
Abstract
Detection and removal of commercials plays an important role when searching for important broadcast news video material. Two novel approaches are proposed based on two distinctive characteristics of commercials, namely, repetitive use of commercials over time and distinctive color and audio features. Furthermore, proposed strategies for combining the results of the two methods yield even better performance. Experiments show over 90% recall and precision on a test set of 5 hours of ABC and CNN broadcast news dataKeywords
This publication has 4 references indexed in Scilit:
- Object Detection Using the Statistics of PartsInternational Journal of Computer Vision, 2004
- Story segmentation and detection of commercials in broadcast news videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Lessons learned from building a terabyte digital video libraryComputer, 1999
- On the detection and recognition of television commercialsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997