Clarifying the emotion generation mechanism for the cross-media data retrieval system bringing emotion and its application
Project/Area Number |
18500163
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Sensitivity informatics/Soft computing
|
Research Institution | Kyoto Institute of Technology |
Principal Investigator |
HOUCHIN Teruhisa Kyoto Institute of Technology, Graduate Schoolof Seicnce and Technology, professor (00251984)
|
Co-Investigator(Kenkyū-buntansha) |
TANIZUKA Noboru Osaka Prefecture University, Graduate School of Science, Associate Professor (50079159)
|
Project Period (FY) |
2006 – 2007
|
Project Status |
Completed (Fiscal Year 2007)
|
Budget Amount *help |
¥4,010,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥510,000)
Fiscal Year 2007: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2006: ¥1,800,000 (Direct Cost: ¥1,800,000)
|
Keywords | Kansei Informatics / Experimental psychology / Brain / Information fundamentals / Information retrieval / 実験系心理学 |
Research Abstract |
It is experimentally clarified that how the harmony of the audiovisual material influences its impression, and how "semantic harmony" and "formal harmony" of the audiovisual material are related with "general harmony". In the experiment, four patterns of audiovisual materials are used. These are created by combining the semantically matched and mismatched sound clips and the temporally matched and mismatched video clips. This experiment clarifies that the impression of the sound is more dominant than that of the video overall in that of the audiovisual material, and the rating of general harmony must be high in order to get an audiovisual material of high scores of the impression words of "Natural", "Beautiful", and "Impressive" included in "Naturalness factor". In addition, the rating of general harmony of the audiovisual material could be estimated by using the rating of semantic harmony and that of formal harmony. A method of synchronizing a music clip and a video clip of the query result in the cross-media retrieval system is proposed for the purpose of improving the degree of their fitness. The proposed method changes the speed in playing a video clip. This method decides the synchronization points of a video clip based on the beats in a music clip. The speed in playing a video clip is decided according to the times of the synchronization points. The proposed synchronization method is experimentally evaluated. The evaluation result shows that the proposed method could improve the degree of fitness of a music clip and a video one. The predictability of the brain magnetism is discussed based on the analysis of the data at different consciousness states with nonlinear methods. External reading of the mental activity is concerned.
|
Report
(3 results)
Research Products
(21 results)