2001 Fiscal Year Final Research Report Summary
Discovery of structure from color images by entropy minimization learning of neural networks
| 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)
|
|---|
| Project Period (FY) |
1998 – 2001
|
| Keywords | Neural network / Structure of image / Image classification / Image recognition / Rule extraction / Entropy minimization / Surface generation / 類似検索 |
|---|
| 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.
|
