Translator Disclaimer
28 January 2008 Improving multimedia retrieval with a video OCR
Author Affiliations +
Abstract
We present a set of experiments with a video OCR system (VOCR) tailored for video information retrieval and establish its importance in multimedia search in general and for some specific queries in particular. The system, inspired by an existing work on text detection and recognition in images, has been developed using techniques involving detailed analysis of video frames producing candidate text regions. The text regions are then binarized and sent to a commercial OCR resulting in ASCII text, that is finally used to create search indexes. The system is evaluated using the TRECVID data. We compare the system's performance from an information retrieval perspective with another VOCR developed using multi-frame integration and empirically demonstrate that deep analysis on individual video frames result in better video retrieval. We also evaluate the effect of various textual sources on multimedia retrieval by combining the VOCR outputs with automatic speech recognition (ASR) transcripts. For general search queries, the VOCR system coupled with ASR sources outperforms the other system by a very large extent. For search queries that involve named entities, especially people names, the VOCR system even outperforms speech transcripts, demonstrating that source selection for particular query types is extremely essential.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dipanjan Das, Datong Chen, and Alexander G. Hauptmann "Improving multimedia retrieval with a video OCR", Proc. SPIE 6820, Multimedia Content Access: Algorithms and Systems II, 68200B (28 January 2008); doi: 10.1117/12.766931; https://doi.org/10.1117/12.766931
PROCEEDINGS
12 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Automatic text recognition in digital videos
Proceedings of SPIE (March 12 1996)
Content-based analysis of news video
Proceedings of SPIE (September 24 2001)
A new method for number recognition based on feature extract
Proceedings of SPIE (January 19 2006)
An improved algorithm for shot cut detection
Proceedings of SPIE (June 23 2005)
An interactive region merging method
Proceedings of SPIE (November 28 2011)

Back to Top