Project/Area Number |
10480076
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Kyushu University |
Principal Investigator |
NIJIMA Koichi Kyushu University, Graduate School of Information Science and Electrical Engineering, Professor, 大学院・システム情報科学研究院, 教授 (30047881)
|
Co-Investigator(Kenkyū-buntansha) |
TAKANO Shigiru Kyushu University, Graduate School of Information Science and Electrical Engineering, Assistant Professor, 大学院・システム情報科学研究院, 助手 (70336064)
TAKAHASHI Norikazu Kyushu University, Graduate School of Information Science and Electrical Engineering, Associate Professor, 大学院・システム情報科学研究院, 助教授 (60284551)
OKADA Yoshihiro Kyushu University, Graduate School of Information Science and Electrical, Engineering Associate Professor, 大学院・システム情報科学研究院, 助教授 (70250488)
葛目 幸一 弓削商船高等学校, 情報工学科, 助教授 (80225151)
皆本 晃弥 九州大学, 大学院・システム情報科学研究科, 助手 (00294900)
ツォイクマン トーマス 九州大学, 大学院・システム情報科学研究科, 教授 (60264016)
|
Project Period (FY) |
1998 – 2001
|
Project Status |
Completed (Fiscal Year 2001)
|
Budget Amount *help |
¥10,300,000 (Direct Cost: ¥10,300,000)
Fiscal Year 2001: ¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 2000: ¥2,500,000 (Direct Cost: ¥2,500,000)
Fiscal Year 1999: ¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 1998: ¥3,000,000 (Direct Cost: ¥3,000,000)
|
Keywords | Neural network / Structure of image / Image classification / Image recognition / Rule extraction / Entropy minimization / Surface generation / 類似検索 / 訓練パターン / 認識領域 / 枝刈り / 曲面生成 / マージ法 / 位相 / 境界処理 / 教師付きエントロピー最大化法 / 自己組織型エントロピー最大化法 / データマイニング / 隠蔽画像 / ウェーブレット変換 / 画像作成システム / ウェーブレット / 学習理論 / 安定性理論 / 動画像認識 / 画像処理 / 非対称相互結合型 / 引き込み領域 |
Research Abstract |
Neural networks play an important role in this research. In order to discover the structure that characterizes images, we need to study learning methods for neural networks and to analyze the behavior of the learned neural network. It is required to study the classification and recognition ability of the neural network. We must find rules from the learned neural network. Simplification of 3D images for inputting in the neural network is also an important research subject. To resolve such problems, we studied various learning methods as well as the entropy minimization learning technique for neural networks and the behavior of cellular neural networks. And we applied the obtained results to image classification and rule extraction. We proposed a method for finding a hidden image from two similar images by combining the entropy minimization learning technique of the neural network with a wavelet theory, which is a main theme of this research. For discovering the structure of 3D models using a neural network, we studied simple surface generation algorithms for obtaining vertices which are input data of the neural network.
|