Fast dynamic image segmentation using discrete-time nonlinear dynamics of chaotic neuronal network model
| Project/Area Number |
20700209
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | The University of Tokushima |
|---|
Principal Investigator |
FUJIMOTO Kenichi The University of Tokushima, 大学院・ヘルスバイオサイエンス研究部, 助教 (20300626)
|
|---|
| Project Period (FY) |
2008 – 2009
|
| Project Status |
Completed (Fiscal Year 2009)
|
| Budget Amount *help |
¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2009: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2008: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 画像領域分割 / カオスニューラルネットワーク / 離散時間力学系 / 非振動応答 / 振動応答 / 分岐現象 / 不安定化制御系 / FPGA実装 / 動的画像領域分割 / 振動応答の引力圏 / カオス・ニューロン結合系 / 離散時間系 / 不安定化制御 / 非線形制御理論 |
|---|
| Research Abstract |
Image segmentation is an essential image processing technique in computed aided diagnosis support systems for medical images. We proposed a system called chaotic neuronal network for image segmentation and studied on the development of a fast image segmentation system using the intrinsic nonlinear properties of our chaotic neuronal network model. At first, we analyzed the nonlinear dynamics of our system and found appropriate values of the system parameters for image segmentation. Next, we de-monstrated that the system worked well. We also implemented it on a digital LSI.
|
Report
(3 results)
Research Products
(36 results)
