On the evolution of videotext description scheme and its validation experiments for MPEG-7

Authors:
Chitra Dorai;Ruud Bolle;Nevenka Dimitrova;Lalitha Agnihotri;Gang Wei
Affiliations:
IBM T.J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY;IBM T.J. Watson Research, Center, P.O. Box 704, Yorktown Heights, NY;Philips Research, 345 Scarborough Road, Briarcliff Manor, NY;Philips Research, 345 Scarborough Road, Briarcliff Manor, NY;Philips Research, 345 Scarborough Road, Briarcliff Manor, NY
Venue:
MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
Year:
2000

Citing 4
Cited 0

Automatic Caption Localization in Compressed Video

IEEE Transactions on Pattern Analysis and Machine Intelligence
Video OCR: indexing digital new libraries by recognition of superimposed captions

Multimedia Systems - Special section on video libraries
Text Detection for Video Analysis

CBAIVL '99 Proceedings of the IEEE Workshop on Content-Based Access of Image and Video Libraries
Automatic Text Extraction from Video for Content-Based Annotation and Retrieval

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Videotext refers to text superimposed on still images and video frames, and can be used in many MPEG-7 applications that deal with archival and delivery of images and video. It can be used to annotate and index large video and image collections, and enables text based search, automatic video logging, and video cataloging. This paper describes the joint work of IBM and Philips Research Laboratories on designing an MPEG-7 description scheme based on videotext. It describes the elements comprising the Videotext DS and discusses validation experiments performed to demonstrate the effectiveness of the DS in video browsing and classification tasks.