Automatic recognition of film genres

Film genres in digital video can be detected automatically. In a three-step approach we analyze first the syntactic properties of digital films: color statistics, cut detection, camera motion, object motion and audio. In a second step we use these statistics to derive at a more abstract level film style attributes such as camera panning and zooming, speech and music. These are distinguishing properties for film genres, e.g. newscasts vs. sports vs. commercials. In the third and final step we map the detected style attributes to film genres. Algorithms for the three steps are presented in detail, and we report on initial experience with real videos. It is our goal to automatically classify the large body of existing video for easier access in digital video-on-demand databases.

[1]  Anindo Banerjea,et al.  Network support for multimedia: a discussion of the Tenet approach , 1994 .

[2]  Arding Hsu,et al.  Image processing on compressed data for large video databases , 1993, MULTIMEDIA '93.

[3]  Jian-Kang Wu,et al.  Identifying faces using multiple retrievals , 1994, IEEE MultiMedia.

[4]  G.R. Doddington,et al.  Speaker recognition—Identifying people by their voices , 1985, Proceedings of the IEEE.

[5]  Ralf Steinmetz,et al.  Experiences with the Heidelberg Multimedia Communication System: Multicast, Rate Enforcement and Performance , 1992, HPN.

[6]  Ramesh C. Jain,et al.  Architecture of a Multimedia Information System for Content-Based Retrieval , 1992, NOSSDAV.

[7]  Y. Yatsuzuka.  Highly Sensitive Speech Detector and High-Speed Voiceband Data Discriminator in DSI-ADPCM Systems , 1982, IEEE Trans. Commun..

[8]  Didier Dubois,et al.  Fuzzy sets and systems ' . Theory and applications , 2007 .

[9]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Ajit Singh,et al.  An estimation-theoretic framework for image-flow computation , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[11]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[12]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[13]  Forouzan Golshani,et al.  Rx for semantic video database retrieval , 1994, MULTIMEDIA '94.

[14]  David Wetherall,et al.  The VuSystem: a programming system for visual processing of digital video , 1994, MULTIMEDIA '94.

[15]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Paul T. Brady,et al.  A technique for investigating on-off patterns of speech , 1965 .

[17]  Yihong Gong,et al.  Automatic parsing of news video , 1994, 1994 Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[18]  Ketan Mayer-Patel,et al.  Performance of a software MPEG video decoder , 1993, MULTIMEDIA '93.

[19]  Brian Christopher Smith,et al.  Fast software processing of motion JPEG video , 1994, MULTIMEDIA '94.

[20]  Suliman Al-Hawamdeh,et al.  Image Information Retrieval Systems , 1993, Handbook of Pattern Recognition and Computer Vision.

[21]  Stephen W. Smoliar,et al.  Developing power tools for video indexing and retrieval , 1994, Electronic Imaging.