A Novel Image Feature Extraction Framework Using Higher-Order Statistic Kernels
Project/Area Number |
22500198
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Sensitivity informatics/Soft computing
|
Research Institution | University of Tsukuba |
Principal Investigator |
|
Project Period (FY) |
2010 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2012: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2011: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2010: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
Keywords | ニューラルネットワーク / カーネル法 / 高次統計量 / パターン認識 / 信号処理 / 画像分類 |
Research Abstract |
This project focused on using the Higher-order moment functions as image features to be used for classification and retrieval, by way of Higher-order moment kernels which enables a drastic reduction of computation regardless of the order. The nature of the moment features which differs according to the order, and the conditions for applying the feature for real-world image classification have been investigated by mathematical analysis and image texture classification experiments.
|
Report
(4 results)
Research Products
(10 results)