| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Outline of Final Research Achievements |
Due to the rapid development of information society, viewing means is being changed from traditional television to online video viewing in recent years. However, text information describing the contents does not exist in the videos broadcasted on television or shot with video cameras. In order to realize video retrieval just using keywords, automatic annotation method is necessary that gives meta information representing the contents of video in a text format. In this research, we propose a novel annotation algorithm for video database with high precision, which can realize superior performance compared with conventional methods.
|
