Knowledge extraction and understanding of images using Fuzzy inference neural network
| Project/Area Number |
12650394
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
情報通信工学
|
|---|
| Research Institution | Keio University |
|---|
Principal Investigator |
HAGIWARA Masafumi Keio University, Faculty of Science and Technology, Professor, 理工学部, 教授 (80198655)
|
|---|
| Project Period (FY) |
2000 – 2002
|
| Project Status |
Completed (Fiscal Year 2002)
|
| Budget Amount *help |
¥3,600,000 (Direct Cost: ¥3,600,000)
Fiscal Year 2002: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 2001: ¥600,000 (Direct Cost: ¥600,000)
Fiscal Year 2000: ¥1,700,000 (Direct Cost: ¥1,700,000)
|
|---|
| Keywords | Fuzzy / Neural network / Image recognition / 画像理解 / ファジイ |
|---|
| Research Abstract |
The following research results were obtained.
(1) Image recognition and understanding using fuzzy inference neural network
In this research, a new neural network system for image recognition and understanding is proposed. It consists of neural network which has high learning ability and fuzzy system which is good at treating rules. There are 3 processes in the system: segmentation, image recognition, and image interpretation. According to the computer experiments, 71.9% of pixels are correctly recognized and reasonable understanding results are obtained.
(2) Scenery image recognition considering relative position
When we recognize images, relative positions of objects play an important role. The recognition system considering the fact is proposed.
(3) Scenery image recognition based on hypothesis and testing
The recognition system can reflect Kansei information from the images and perform hypothesis and testing for better performance.
(4) Moving object recognition neural network based on visual system
A new neural network system inspired by biological visual system is proposed. It can recognize objects from the movement and the shape.
(5) Hierarchical-parallel neural network for 3-D object recognition
A new neural network composed of Neo-cognitron like structure and bi-directional information processing is proposed.
(6) Chaos analog associative memory.
Memory function is crucial for higher level image processing. This research is aimed for advanced recognition system for the next generation.
(7) Neural network associative memory for concepts of sentence
Our higher level intelligent processing such as thinking and inference are based on language. For the next step of image understanding, language processing by neural network is indispensable. In this research, we proposed such a kind of neural network.
|
Report
(4 results)
Research Products
(18 results)
