2002 Fiscal Year Final Research Report Summary
Development of IC Chip with human visual function for High-speed fish Recognition
| Project/Area Number |
12650908
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
海洋工学
|
|---|
| Research Institution | Nagasaki University |
|---|
Principal Investigator |
KUROKAWA Fujio Faculty of Engineering, Associate Professor, 工学部, 助教授 (20140808)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MATSUO Hirofumi Graduate School of Science and Technology, Professor, 生産科学研究科, 教授 (50101382)
|
|---|
| Project Period (FY) |
2000 – 2002
|
| Keywords | Image Processing / Visual Function / Cognitive Science / IC / Fish Recognition / Shape Feature Extraction / Color Feature Extraction / DSP |
|---|
| Research Abstract |
A new color image processing system with human visual function is constructed and applied to the pattern recognition of fish species, the shapes of which are very similar but the colors and/or patterns of which are different. This system has a function of variable partition of a picture. Therefore, the size, position, number of processing regions and control strategy such as SIMD, MIMD, etc. can be varied flexibly and dynamically for each processing task.
The high-speed feature extraction of fish is examined as an example of the application of the proposed system. In this application, the shape features of fish are extracted at first., and then the color features are extracted from several small regions of fish. As a result, it is clarified that the proposed system can be used in practice in order to classify fish species at a high speed.
As a result, it is clarified that the proposed algorithm and color image processing system are satisfactorily useful can be used in practice in order to classify fish species and that the recognition time less than 70ms per a fish is achieved.
|
