Development of a new image search system based on similarity measures and ranking
| Project/Area Number |
24500126
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | University of Miyazaki (2013-2014)
Osaka City University (2012) |
|---|
Principal Investigator |
THITHI Zin 宮崎大学, 工学部, 准教授 (30536959)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
HAMA Hiromitsu 大阪市立大学, 工学研究科, 名誉教授 (20047377)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2012: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 類似画像検索 / ユーザ満足度最大化 / 再帰的ランキング / クラスタリング / 画像類似測度 / マルコフ定常状態確率 / ビジョンキー / 類似度測度 / ユーザ満足度 / リランキング / 類似画像 / マルコフ定常確率 / マルコフ定常確率分布 |
|---|
| Outline of Final Research Achievements |
Aiming at maximizing user satisfaction, we have proposed a recursive ranking method for feeding back a high information relevant to a user's request to develop new generation image search engines. The validity of the proposed method has been confirmed through a number of experiments using a real image set. Search results are not fixed. It is devised to be able constantly to follow the change of user request, and we developed the controllable similarity measure by parameters. Thus, it is possible to control the degree of similarity and the order of presentation of the images, such functionality has not been intended in the conventional search engines. The results can be deployed in many applications.
|
Report
(4 results)
Research Products
(49 results)
