The application of new Monte Carlo methods to the problemof probabilistic image processing
| Project/Area Number |
21540396
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Mathematical physics/Fundamental condensed matter physics
|
|---|
| Research Institution | Tokyo Metropolitan University |
|---|
Principal Investigator |
OKABE Yutaka 首都大学東京, 大学院・理工学研究科, 教授 (60125515)
|
|---|
| Project Period (FY) |
2009 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2012: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2011: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2010: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2009: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | モンテカルロ法 / 画像処理 / 領域分割 / Mumford-Shah モデル / グラフカット法 / GPU / 並列計算 / クラスターフリップ / ＧＰＵ / Mumford-Shahモデル / レベルセット法 / XYモデル / KT転移 / 有限サイズスケーリング / 画像修復 / basin hopping |
|---|
| Research Abstract |
Complex spin models were studied by new Monte Carlo algorithms. The generalized XY model was shown to be of Kosterlitz-Thouless type regardless of the parameter. The Monte Carlo method was also applied to the problem of image segmentationproblems, and it was shown that this method is effective especially combined with the graph-cut method. Moreover, the graphic processing unit (GPU) was successfully applied to the high-speed calculation of Monte Carlo simulation.
|
Report
(5 results)
Research Products
(41 results)
