| Project/Area Number |
09308010
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (A).
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | The University of Electro-Communications (1999-2000)
Osaka University (1997-1998) |
|---|
Principal Investigator |
FUKUSHIMA Kunihiko The University of Electro-Communications, Faculty of Electro-Communications, Professor, 電気通信学部, 教授 (90218909)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
菊池 眞之 (菊地 眞之) 大阪大学, 大学院・基礎工学研究科, 助手 (20291437)
庄野 逸 大阪大学, 大学院・基礎工学研究科, 助手 (50263231)
|
|---|
| Project Period (FY) |
1997 – 2000
|
| Project Status |
Completed (Fiscal Year 2000)
|
| Budget Amount *help |
¥15,600,000 (Direct Cost: ¥15,600,000)
Fiscal Year 2000: ¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 1999: ¥2,200,000 (Direct Cost: ¥2,200,000)
Fiscal Year 1998: ¥2,600,000 (Direct Cost: ¥2,600,000)
Fiscal Year 1997: ¥8,400,000 (Direct Cost: ¥8,400,000)
|
|---|
| Keywords | Visual system / Neural network model / Active vision / Pattern recognition / Neocognitron / Occluded patterns / Face recognition / Self-organization / 部分的遮蔽 / 手書き数字認識 / 複雑型細胞 / 位置不変性受容野 / 競合学習 / 視覚パターン認識 / 特徴抽出 / 能動的パターン認識 / 選択的注意 / 顔パターンの切り出し |
|---|
| Research Abstract |
Aiming to develop new design principles for visual information processing systems of the next generation, we have concentrated our research on the active and dynamic processes in the visual system of the biological brain. We used modeling approach to uncover the mechanism of the brain and to design advanced systems for visual pattern recognition. We have performed various researches in parallel and have obtained the following results.
1. Neural network model that can recognize faces from complex backgraound. It can focus attention to and segment facial components (eyes and mouth) from the recognized face.
2. Neural network model that can recognize partly occluded patterns correctly.
3. Neocognitron of a new version for recognizing handwritten digits in the real world. The neocognitron, which we have developed previously, is a pattern recognition system whose architecture has been suggested from the mammalian visual system. The recognition rate, which varies depending on the size of training set, was over 98% when we used 3000 characters for the training.
4. New learning rule by which cells with shift-invariant receptive fields are self-organized. With this learning rule, cells similar to simple and complex cells in the primary visual cortex are generated in a network.
5. Neural network model that can memorize and recall spatial maps. The model emulates a situation where a person memorizes and recalls spatial maps when he moves around in a two-dimensional space. The model memorizes fragmentary maps, but can retrieve an image covering a wide area seamlessly by a continuous chain process of recalling.
6. Stereo algorithm that extracts a depth cue from interocularly unpaired points.
|
