| Project/Area Number |
26330204
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Chiba Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 画像処理 / 画像復元 / マセマティカルモフォフォジー / 雑音除去 / 正則化 / マセマティカルモフォロジー / 確率的勾配降下法 / 最適化 |
|---|
| Outline of Final Research Achievements |
In this study, we address the applications of set-theoretic image modeling to problems of the image recovery and reconstruction. We have applied the morphology, which provides a class of the set-theoretic image processing, to image recovery and reconstruction problems. We also extended the morphology to a novel class of nonlinear filtering. In the application of the image recovery, the regularization with a prior obtained from the set-theoretic image features is proposed. By using the morphological image priors, the image denoising that can preserve details of images is proposed. The image decomposition according to the sizes of local structures is also proposed by using the set-theoretic image features. In the extension of the morphology, the max and min functions of the morphology are extended to the class of convex and concave functions, respectively. We demonstrated that the novel nonlinear can outperform the morphological filter with relatively small computational costs.
|
