dc.contributor.author | Subirana-Vilanova, J. Brian | en_US |
dc.date.accessioned | 2004-10-20T19:55:13Z | |
dc.date.available | 2004-10-20T19:55:13Z | |
dc.date.issued | 1995-04-01 | en_US |
dc.identifier.other | AITR-1442 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6792 | |
dc.description.abstract | We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/ incoming regions are more salient; and that perception begins by setting a reference frame (prior to early vision), and proceeds by processing convex structures. | en_US |
dc.format.extent | 239 p. | en_US |
dc.format.extent | 48192029 bytes | |
dc.format.extent | 2356367 bytes | |
dc.format.mimetype | application/postscript | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | AITR-1442 | en_US |
dc.subject | vision | en_US |
dc.title | Mid-Level Vision and Recognition of Non-Rigid Objects | en_US |