10 January 2003 Media segmentation using self-similarity decomposition
Author Affiliations +
Proceedings Volume 5021, Storage and Retrieval for Media Databases 2003; (2003); doi: 10.1117/12.476302
Event: Electronic Imaging 2003, 2003, Santa Clara, CA, United States
We present a framework for analyzing the structure of digital media streams. Though our methods work for video, text, and audio, we concentrate on detecting the structure of digital music files. In the first step, spectral data is used to construct a similarity matrix calculated from inter-frame spectral similarity.The digital audio can be robustly segmented by correlating a kernel along the diagonal of the similarity matrix. Once segmented, spectral statistics of each segment are computed. In the second step,segments are clustered based on the self-similarity of their statistics. This reveals the structure of the digital music in a set of segment boundaries and labels. Finally, the music is summarized by selecting clusters with repeated segments throughout the piece. The summaries can be customized for various applications based on the structure of the original music.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jonathan T. Foote, Matthew L. Cooper, "Media segmentation using self-similarity decomposition", Proc. SPIE 5021, Storage and Retrieval for Media Databases 2003, (10 January 2003); doi: 10.1117/12.476302; https://doi.org/10.1117/12.476302

Image segmentation



Data modeling

Distance measurement


Analytical research


Algorithm for the discovery of clusters in WBC data
Proceedings of SPIE (May 10 1996)
Using content models to build audio-video summaries
Proceedings of SPIE (December 17 1998)
Texture resynthesis using principle component analysis
Proceedings of SPIE (May 30 2002)
New approach for logo recognition
Proceedings of SPIE (March 31 2000)
PNRS: personalized news retrieval system
Proceedings of SPIE (August 24 1999)

Back to Top