Name
Abstract | ||
|---|---|---|
When we see an animation in which a small region of random texture moves on the background of random texture, we perceive that the small region is separated from the background as a moving object. We call this phenomenon figure-ground separation from motion. Playing it back relatively slowly, we perceive that the contour of the region becomes rounded. So, this contour can be regarded as a subjective contour. By the way, patterns generated by a reaction-diffusion equation also become rounded in process of time evolution. We consider that this equation is a suitable model for deformation of the subjective contour. Then, we generate the separation pattern by using this equation, confirm that the front of the pattern coincides with the subjective contour qualitatively, and claim that our model is useful. |
Year | Venue | Keywords |
|---|---|---|
1998 | ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3 | cognition and perception, visual computation |
Field | DocType | Citations |
Pattern recognition,Computer science,Figure–ground,Artificial intelligence,Artificial neural network | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Eizo Ueyama | 1 | 0 | 0.34 |
| Hideo Yuasa | 2 | 102 | 11.32 |
| Shigeyuki Hosoe | 3 | 226 | 48.79 |
| Masami Ito | 4 | 299 | 66.19 |