| Project/Area Number |
08680403
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | KYUSHU UNIVERSITY |
|---|
Principal Investigator |
TSURUTA Naoyuki KYUSHU UNIV., GRADUATE SCHOOL OF INFORMATION SYSTEMS,RESEARCH ASSOCIATE, 大学院・システム情報科学研究科, 助手 (60227478)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KUSAKABE Shigeru KYUSHU UNIV., GRADUATE SCHOOL OF INFORMATION SYSTEMS,RESEARCH ASSOCIATE, 大学院・システム情報科学研究科, 助手 (70234416)
GYOUBA Jiro KYUSHU UNIV., LITERATURE ASSISTANT PROFESSOR, 文学部, 助教授 (50142899)
TANIGUCHI Rin-ichiro KYUSHU UNIV., GRADUATE SCHOOL OF INFORMATION SYSTEMS,PROFESSOR, 大学院・システム情報科学研究科, 教授 (20136550)
|
|---|
| Project Period (FY) |
1996 – 1997
|
| Project Status |
Completed (Fiscal Year 1997)
|
| Budget Amount *help |
¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 1997: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 1996: ¥1,600,000 (Direct Cost: ¥1,600,000)
|
|---|
| Keywords | Visual Search / Multi-layred Neural Networks / Multimedia / Auto Driving Car / Cooperative Distributed processing / Parallel Distributed Processing |
|---|
| Research Abstract |
Recently, many researches, which use a vision system to aid high level reasoning and planing of users or central systems, are started. The Visual search is a very important and basic function in those applications.
In this research, we constructed a visual search neural network model, which enable a high level and flexible visual search to the central system, and enlarged the applications of the visual search. The proposed model outputs high-level concepts such as shape, color and motion's direction of target objects. This model differs from conventional neural networks, in which information is propagated from input-layr to output-layr, because of bidirectional information propagation. According the mechanism, the model inhibits the unnecessary background information and processes necessary information selectively, when partial concepts of the target are put into it. Then, the model not only recognizes objects stably, but also provides flexible interface using high level concepts. Furthermore, in this
|
