Ba Tu Truong
ABSTRACT
Using film grammar as the underpinning, we study the extraction of structures in video based on color using a wide configuration of clustering methods combined with existing and new similarity measures. We study the visualisation of these structures, which we call Scene-Cluster Temporal Charts and show how it can bring out the interweaving of different themes and settings in a film. We also extract color events that filmmakers use to draw/force a viewer's attention to a shot/scene. This is done by first extracting a set of colors used rarely in film, and then building a probabilistic model for color event detection. We demonstrate with experimental results from ten movies that our algorithms are effective in the extraction of both scene-cluster temporal charts and color events.
- C. Colombo, A. D. Bimbo, and P. Pala. Semantics in information retrieval. IEEE Multimedia, 6(3):38--53, 1999. Google Scholar
Digital Library
- C. Dorai and S. Venkatesh. Computational Media Aesthetics: Finding meaning beautiful. IEEE Multimedia, 8(4):10--12, October-December 2001. Google ScholarDigital Library
- B. S. Everitt. Cluster Analysis. Edward Arnold, 3rd edition, 1993.Google Scholar
- W. Johnson. Coming to term with color. Film Quaterly, 20(1):2--22, 1996.Google Scholar
- M. R. Napahde and T. S. Huang. A probablistics framework for semantic video indexing, filtering and retrieval. IEEE Transactions on Multimedia, 3(1):141--151, March 2001. Google ScholarDigital Library
- S. Neale. Cinema and Technology: Image, Sound and Color. MacMillan Education Ltd, 1985.Google Scholar
- B. T. Truong, C. Dorai, and S. Venkatesh. Automatic scene extraction in motion pictures. Technical Report 1/2001, School of Computing, Curtin University of Technology, Perth, Western Australia, 2001.Google Scholar
- H. Zettl. Sight Sound Motion: Applied Media Aesthetics. Wadsworth Publishing, 3rd edition, 1999.Google Scholar
Index Terms
- Application of computational media aesthetics methodology to extracting color semantics in film
Recommendations
Computational intelligence techniques for colour clustering
ICCC '11: Proceedings of the 2011 International Conference on Innovative Computing and Cloud ComputingColour clustering (or colour quantisation) is an elementary image processing process to reduce the number of distinct colours in an image. Colour quantised images contain a colour palette and it is the entries in this palette that determine the quality ...
Efficient edge-preserving algorithm for color contrast enhancement with application to color image segmentation
In this paper, a new and efficient edge-preserving algorithm is presented for color contrast enhancement in CIE Lu^'v^' color space. The proposed algorithm not only can enhance the color contrast as the previous algorithm does, but also has an edge-...
Computational Color Constancy
ICPR '00: Proceedings of the International Conference on Pattern Recognition - Volume 1The color response of a camera or of the human eye is confounded by illumination. The colors recorded under yellow and blue illuminants are respectively more yellowish and bluish than they ought to be. Removing color bias due to illumination is called ...
Comments