Similarity retrieval of vector images considering human visual perception
| Project/Area Number |
26330130
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Multimedia database
|
|---|
| Research Institution | Niigata University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 画像検索 / 情報検索 / ベクタ画像 / 情報システム / 情報工学 / 類似画像検索 |
|---|
| Outline of Final Research Achievements |
The goal of this study is to develop a system for similarity retrieval of vector images. The achievements are as follows. (1) A method for contour completion of partly occluded objects was developed. In the method, local and global completion methods were combined to deal with various shape classes. (2) The algorithm of indirect matching, which is a fast algorithm for similarity retrieval of vector images, was improved. Besides, to examine the performance of the improved algorithm, experiments using a publicly available data set of shape images were conducted. From the experimental results, the improvement of retrieval accuracy was confirmed.
|
Report
(4 results)
Research Products
(21 results)
