Abstract | ||
---|---|---|
The concept of an autonomous decentralized system can be applied to recognizing various complicated and skillful actions performed by humans. This concept is the basis for a proposed pattern recognition system, which can be regarded as an associative memory system modeled by a reaction- diffusion equation system. This paper will improve upon this pattern recognition system using the property of a dispersive wave instead of diffusion. This improvement has three advantages: acceleration of recognition, spread of similar regions, and human-like hysteresis in recognition. Computer simulation has shown that propagation of a dispersive wave is faster than that of diffusion, and that the dispersive wave system exhibits the above advantageous properties of recognition. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ISADS.1997.590606 | ISADS |
Keywords | Field | DocType |
dispersive wave,diffusion equation system,autonomous decentralized system,human-like hysteresis,dispersive wave system,recognition system,dispersive wave property,advantageous property,pattern recognition system,proposed pattern recognition system,computer simulation,associative memory system,associative memory,dispersion,diffusion,image recognition,pixel,pattern recognition,parallel processing,reaction diffusion equation,control systems,decentralized system,explosives,system modeling,wave propagation,stereo vision,hysteresis | Autonomous decentralized system,Content-addressable memory,Wave propagation,Stereopsis,Computer science,Real-time computing,Artificial intelligence,Control system,Computer vision,Topology,Pixel,Acceleration,Content-addressable storage | Conference |
ISBN | Citations | PageRank |
0-8186-7783-X | 0 | 0.34 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
H. Yuasa | 1 | 0 | 0.34 |
H. Maruyama | 2 | 0 | 0.34 |
S. Ito | 3 | 8 | 3.80 |
Masanori Ito | 4 | 69 | 15.48 |