| Project/Area Number |
17500644
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | The University of Tokushima |
|---|
Principal Investigator |
SHISHIBORI Masami The University of Tokushima, Institute of Technology and Science, Graduate School, Associate Professor (50274262)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KITA Kenji The University of Tokushima, Center for Advanced Information Technology, Professor (10243734)
TSUGE Satoru The University of Tokushima, Institute of Technology and Science, Graduate School, Lecturer (00325250)
|
|---|
| Project Period (FY) |
2005 – 2007
|
| Project Status |
Completed (Fiscal Year 2007)
|
| Budget Amount *help |
¥3,550,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥150,000)
Fiscal Year 2007: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2006: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 2005: ¥1,700,000 (Direct Cost: ¥1,700,000)
|
|---|
| Keywords | Presentation document / Presentation Movie / e-learning / Video processing / Information retrieval / Full text search / 講義資料 / 講義映像 / 映像配信 |
|---|
| Research Abstract |
The purpose of this research is the development of the full text search system for presentation documents and movies. This system first retrieves the suitable page for the user's query from the huge presentation documents, and then this system serves both the contents of the page and the corresponding presentation movie scene with the voice.
1. The development of the processing module for presentation document and movie
This system can specify the correspondence of each presentation page and the cut scene of the presentation movie by the accuracy of 80%. We can found, however, that the accuracy becomes low when the presentation movie includes the animation slide.
2. The development of the linking module for movie scenes and language information
This system can extract word frequency and word position as the linguistic information from the presentation document, and link the linguistic information with time information of the corresponding cut wene.
3. The collection of presentation movies
We collected about 100 presentation documents and movies, which are almost graduation and master thesis presentations of our laboratory members.
4. The Management of the large-scale full text retrieval system for presentation documents and movies
The large-wale full text retrieval system for presentation documents and movies has been developed. About 100 presentation documents and movies have been registered into this system.
5. Publications of this research
The papers about this research have been already published as the following:
The number of journal is 6 papers(1 paper is in English, and 5 papers are in Japanese)
The number of international conference is 7 papers.
The number of domestic oonference is 25 papers.
|
