A study on accurate high-quality image reconstruction based on representation bases
| Project/Area Number |
22700088
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
OGAWA TAKAHIRO 北海道大学, 情報科学研究科, 助教 (20524028)
|
|---|
| Project Period (FY) |
2010-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2010: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 画像復元 / 画像再構成 / 画質評価 / 画像評価 |
|---|
| Research Abstract |
In this study, we realized algorithms for accurate high-quality image reconstruction based on representation bases obtained from training images in databases. Specifically, we realized 1) simultaneous removal of multiple degradation elements, 2) derivation of representation bases for obtaining high-quality images and 3) selection scheme of optimal bases suitable for reconstructing target contents. Consequently, our study improved the performance limitation existing in the field of image restoration such as error concealment, noise removal and super-resolution.
|
Report
(5 results)
Research Products
(54 results)
