Detecting of TV commercials in video databases

Michał Majewicz, Tomasz Gąciarz, Krzysztof Czajkowski

Abstract


TV commercials are present in almost each currently emitted telecast. Placing such content in video databases creates additional problems, most important of which is a larger file size and longer duration of their search. This paper shows methods of detecting and removing of undesirable TV commercials from video material by using classifiers based on Haar-like features. The proposed algorithm can adapt to a particular TV channel and achieves a high level of precision.

Keywords


video database; tv commercials detecting; extracting image features; video material analyzing; Haar-like features

Full Text:

PDF (Polski)

References


Rowe L. A., Boreczky J. S., Eads C. A.: Indexes for User Access to Large Video Databases. IS & / SPIE Symposium on Electronic Imaging Science and Technology, Conference, 1994.

Aas K., Eikvil L.: Indexes for User Access to Large Video Databases. 1997.

Brunelli R., Mich O., Modena C. M.: A Survey on the Automatic Indexing of Video Data. Journal of Visual Communication and Image Representation 10, Trento, Italy 1999.

Snoek C. G. M., Worring M.: Concept-Based Video Retrieval. Journal Foundations and Trends in Information Retrieval, Vol. 2, Issue 4, April 2008.

Thi-Lan L., Boucher A., Thonnat M., Bremond F.: A framework for surveillance video indexing and retrieval. Content-Based Multimedia Indexing, 2008.

Viola P., Jones M. J.: Rapid Object Detection using a Boosted Cascade of Simple Features. IEEE CVPR, 2001.

Papageorgiou C. P., Oren M., Poggio T.: A General Framework for Object Detection. International Conference on Computer Vision, 1998.

Gąciarz T.: Fast Adaptive Binarisation for Camera-based Document Images. Proceedings of International Conference on Artificial Intelligence, IIS Kraków 2009.

Gąciarz T., Czajkowski K.: Klasyfikacja zdjęć w multimedialnych bazach danych. Studia Informatica, Vol. 31, No. 2A (89), Wydawnictwo Politechniki Śląskiej, Gliwice 2010.

Nayak A., Stojmenović I.: Hanbook of Applied Algorithms - Solving Scientific, Engineering and Practical Problems. Wiley-Interscience, New Jersey 2008.

Schapire R. E.: The Boosting Approach To Machine Learning, An Overview. Lecture Notes In Statistics, Springer Verlag, New York 2002.

Freund Y., Schapire R. E.: A decision-theoretic generalization of on-line learning and an application to boosting. Computational Learning Theory: Eurocolt 95, Springer-Verlag, 1995, s. 23÷37.

Wang J., Duan L., Li Z., Liu J., Lu H., Jin J. S.: A robust method for TV logo tracking in video streams. Multimedia and Expo, IEEE International Conference, 2006.

Marlow S., Sadlier D. A., McGeough K., O’Connor N., Murphy N.: Audio and Video Processing for Automatic TV Advertisement Detection. ISSC 2001 - Irish Signals and Systems Conference, 25-27 June 2001, Maynooth, Ireland 2001.

Dimitrova N., Jeannin S., Nesvadba J., McGee T., Agnihotri L., Mekenkamp G.: Real time commercial detection using MPEG features. Visual Information Processing (EUVIP), 2010.

Li Y., Zhang D., Zhou X., Jin J. S.: A Confidence Based Recognition System for TV Commercial Extraction. Proc. Nineteenth Australasian Database Conference (ADC 2008), Wollongong, NSW, Australia 2008.

Stewart T.: Intel® Integrated Performance Primitves - How to Optimize Software Applications Using Intel® IPP. Intel Press, 2004.

Crow F.: Summed-area tables for texture mapping. Proceedings of SIGGRAPH, Vol. 18(3), 1984, s. 207÷212.

Lienhart R., Maydt J.: An extended set of Haar-like features for rapid object detection. Proceedings of the International Conference on Image Processing, 2002.

Wang J., Duan L. et al.: A robust method for TV logo tracking in video streams. IEEE International Conference on Multimedia and Expo, 2006.

Marlow S., Sadlier D. A., McGeough K., O’Connor N., Murphy N.: Audio and Video Processing for Automatic TV Advertisement Detection, ISSC 2001.

Dimitrova N., Jeannin S., et al.: Real time commercial detection using MPEG features. International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Annecy, France 2002, s. 1÷6.

Li Y., Zhang D., Zhou X., Jin J. S.: A Confidence Based Recognition System for TV Commercial Extraction. ADC, Vol. 75, Australian Computer Society, 2008.




DOI: http://dx.doi.org/10.21936/si2012_v33.n2B.175