24 March 2014 A machine learning based lecture video segmentation and indexing algorithm
Author Affiliations +
Video segmentation and indexing are important steps in multi-media document understanding and information retrieval. This paper presents a novel machine learning based approach for automatic structuring and indexing of lecture videos. By indexing video content, we can support both topic indexing and semantic querying of multimedia documents. In this paper, our proposed approach extracts features from video images and then uses these features to construct a model to label video frames. Using this model, we are able to segment and indexing videos with accuracy of 95% on our test collection.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Di Ma, Di Ma, Bingqing Xie, Bingqing Xie, Gady Agam, Gady Agam, "A machine learning based lecture video segmentation and indexing algorithm", Proc. SPIE 9021, Document Recognition and Retrieval XXI, 90210V (24 March 2014); doi: 10.1117/12.2042602; https://doi.org/10.1117/12.2042602


Semantic event detection using MPEG-7
Proceedings of SPIE (January 09 2003)
Learning to annotate video databases
Proceedings of SPIE (December 18 2001)
Lecture video segmentation and indexing
Proceedings of SPIE (January 23 2012)

Back to Top