| dc.contributor.author |
Jacobs, David W. |
en_US |
| dc.date.accessioned |
2004-10-04T14:24:11Z |
|
| dc.date.available |
2004-10-04T14:24:11Z |
|
| dc.date.issued |
1992-02-01 |
en_US |
| dc.identifier.other |
AIM-1353 |
en_US |
| dc.identifier.uri |
http://hdl.handle.net/1721.1/5960 |
|
| dc.description.abstract |
We show that we can optimally represent the set of 2D images produced by the point features of a rigid 3D model as two lines in two high-dimensional spaces. We then decribe a working recognition system in which we represent these spaces discretely in a hash table. We can access this table at run time to find all the groups of model features that could match a group of image features, accounting for the effects of sensing error. We also use this representation of a model's images to demonstrate significant new limitations of two other approaches to recognition: invariants, and non- accidental properties. |
en_US |
| dc.description.provenance |
Made available in DSpace on 2004-10-04T14:24:11Z (GMT). No. of bitstreams: 2
AIM-1353.ps: 2278295 bytes, checksum: 1156720104e95e3b1d200ca01f031b0e (MD5)
AIM-1353.pdf: 1790124 bytes, checksum: 15be5c61897f00a9f48e8b81747678f7 (MD5)
Previous issue date: 1992-02-01 |
en |
| dc.format.extent |
23 p. |
en_US |
| dc.format.extent |
2278295 bytes |
|
| dc.format.extent |
1790124 bytes |
|
| dc.format.mimetype |
application/postscript |
|
| dc.format.mimetype |
application/pdf |
|
| dc.language.iso |
en_US |
|
| dc.relation.ispartofseries |
AIM-1353 |
en_US |
| dc.subject |
object recognition |
en_US |
| dc.subject |
indexing |
en_US |
| dc.subject |
invariants |
en_US |
| dc.subject |
non-accidentalsproperties |
en_US |
| dc.subject |
hashing |
en_US |
| dc.subject |
space efficiency |
en_US |
| dc.title |
Space Efficient 3D Model Indexing |
en_US |
