Presentation 2003/3/7
Slide Identification in the Lecture Movie by Using Matching of Characters and Images
Noriaki OZAWA, Hiroaki TAKEBE, Yutaka KATSUYAMA, Satoshi NAOI, Haruo YOKOTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Slide identification technique is very important for detecting the change of slides in lecture movie for creating e-Learning materials. Matching technique combined with the presentation file as answer information is very useful to identify slides in movie frames. Two methods for slide identification are proposed in this paper. One is a character based method, which uses the relationship of a character code and its coordinates. The other is an image based method, which uses normalized correlation and dynamic programming technique. Practical movies are used to evaluated the performance of the above two methods and their combination. Experimental results show that the proposed methods are very effective for slide identification in lecture movie.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) character recognition / image matching / movie recognition / e-Learning / educational materials / meta data
Paper # PRMU2002-245
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Slide Identification in the Lecture Movie by Using Matching of Characters and Images
Sub Title (in English)
Keyword(1) character recognition
Keyword(2) image matching
Keyword(3) movie recognition
Keyword(4) e-Learning
Keyword(5) educational materials
Keyword(6) meta data
1st Author's Name Noriaki OZAWA
1st Author's Affiliation Fujitsu Laboratory()
2nd Author's Name Hiroaki TAKEBE
2nd Author's Affiliation Fujitsu Laboratory
3rd Author's Name Yutaka KATSUYAMA
3rd Author's Affiliation Fujitsu Laboratory
4th Author's Name Satoshi NAOI
4th Author's Affiliation Fujitsu Laboratory:Global Scientific Information & Computing Center
5th Author's Name Haruo YOKOTA
5th Author's Affiliation Global Scientific Information & Computing Center
Date 2003/3/7
Paper # PRMU2002-245
Volume (vol) vol.102
Number (no) 708
Page pp.pp.-
#Pages 6
Date of Issue