Detection of slide transition for topic indexing

Chong-Wah Ngo; Ting-Chuen Pong; Thomas S. Huang

doi:10.1109/ICME.2002.1035669

Detection of slide transition for topic indexing

Chong-Wah Ngo, Ting-Chuen Pong, Thomas S. Huang

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

28 Citations (Scopus)

Abstract

This paper presents an automatic and novel approach in detecting the transitions of slides for video sequences of technical lectures. Our approach adopts a foreground vs background segmentation algorithm to separate a presenter from the projected electronic slides. Once a background template is generated, text captions are detected and analyzed. The segmented caption regions as well as background templates together provide salient visual cues to decide whether a slide is flipped and replaced. The partitioning of videos according to slide changes not only structure the content of video according to topics, but also facilitate the synchronization of video, audio and electronic slides for effective indexing, browsing and retrieval.

Original language	English
Title of host publication	Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Publisher	IEEE
Pages	533-536
Volume	2
ISBN (Print)	780373049
DOIs	https://doi.org/10.1109/ICME.2002.1035669
Publication status	Published - 2002
Event	2002 IEEE International Conference on Multimedia and Expo (ICME 2002) - Swiss Federal Institute of Technology, Lausanne, Switzerland Duration: 26 Aug 2002 → 29 Aug 2002

Publication series

Name
Volume	2

Conference

Conference	2002 IEEE International Conference on Multimedia and Expo (ICME 2002)
Place	Switzerland
City	Lausanne
Period	26/08/02 → 29/08/02

Access Output

10.1109/ICME.2002.1035669

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{8752b3c4bae44658a04f64487960a254,

title = "Detection of slide transition for topic indexing",

abstract = "This paper presents an automatic and novel approach in detecting the transitions of slides for video sequences of technical lectures. Our approach adopts a foreground vs background segmentation algorithm to separate a presenter from the projected electronic slides. Once a background template is generated, text captions are detected and analyzed. The segmented caption regions as well as background templates together provide salient visual cues to decide whether a slide is flipped and replaced. The partitioning of videos according to slide changes not only structure the content of video according to topics, but also facilitate the synchronization of video, audio and electronic slides for effective indexing, browsing and retrieval.",

author = "Chong-Wah Ngo and Ting-Chuen Pong and Huang, {Thomas S.}",

year = "2002",

doi = "10.1109/ICME.2002.1035669",

language = "English",

isbn = "780373049",

volume = "2",

publisher = "IEEE",

pages = "533--536",

booktitle = "Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002",

address = "United States",

note = "2002 IEEE International Conference on Multimedia and Expo (ICME 2002) ; Conference date: 26-08-2002 Through 29-08-2002",

}

Detection of slide transition for topic indexing. / Ngo, Chong-Wah; Pong, Ting-Chuen; Huang, Thomas S.
Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. Vol. 2 IEEE, 2002. p. 533-536 1035669.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Detection of slide transition for topic indexing

AU - Ngo, Chong-Wah

AU - Pong, Ting-Chuen

AU - Huang, Thomas S.

PY - 2002

Y1 - 2002

N2 - This paper presents an automatic and novel approach in detecting the transitions of slides for video sequences of technical lectures. Our approach adopts a foreground vs background segmentation algorithm to separate a presenter from the projected electronic slides. Once a background template is generated, text captions are detected and analyzed. The segmented caption regions as well as background templates together provide salient visual cues to decide whether a slide is flipped and replaced. The partitioning of videos according to slide changes not only structure the content of video according to topics, but also facilitate the synchronization of video, audio and electronic slides for effective indexing, browsing and retrieval.

AB - This paper presents an automatic and novel approach in detecting the transitions of slides for video sequences of technical lectures. Our approach adopts a foreground vs background segmentation algorithm to separate a presenter from the projected electronic slides. Once a background template is generated, text captions are detected and analyzed. The segmented caption regions as well as background templates together provide salient visual cues to decide whether a slide is flipped and replaced. The partitioning of videos according to slide changes not only structure the content of video according to topics, but also facilitate the synchronization of video, audio and electronic slides for effective indexing, browsing and retrieval.

UR - http://www.scopus.com/inward/record.url?scp=84908209315&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84908209315&origin=recordpage

U2 - 10.1109/ICME.2002.1035669

DO - 10.1109/ICME.2002.1035669

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 780373049

VL - 2

SP - 533

EP - 536

BT - Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002

PB - IEEE

T2 - 2002 IEEE International Conference on Multimedia and Expo (ICME 2002)

Y2 - 26 August 2002 through 29 August 2002

ER -

Detection of slide transition for topic indexing

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this