| dc.contributor.author |
Jacobs, David W. |
en_US |
| dc.date.accessioned |
2004-10-20T19:55:20Z |
|
| dc.date.available |
2004-10-20T19:55:20Z |
|
| dc.date.issued |
1993-04-01 |
en_US |
| dc.identifier.other |
AITR-1416 |
en_US |
| dc.identifier.uri |
http://hdl.handle.net/1721.1/6796 |
|
| dc.description.abstract |
We discuss a strategy for visual recognition by forming groups of salient image features, and then using these groups to index into a data base to find all of the matching groups of model features. We discuss the most space efficient possible method of representing 3-D models for indexing from 2-D data, and show how to account for sensing error when indexing. We also present a convex grouping method that is robust and efficient, both theoretically and in practice. Finally, we combine these modules into a complete recognition system, and test its performance on many real images. |
en_US |
| dc.description.provenance |
Made available in DSpace on 2004-10-20T19:55:20Z (GMT). No. of bitstreams: 2
AITR-1416.ps.Z: 3519825 bytes, checksum: d331ce325ad0d4c26369773839b371ec (MD5)
AITR-1416.pdf: 7005877 bytes, checksum: af35db36c00b68659cec4b764a98e2d6 (MD5)
Previous issue date: 1993-04-01 |
en |
| dc.format.extent |
269 p. |
en_US |
| dc.format.extent |
3519825 bytes |
|
| dc.format.extent |
7005877 bytes |
|
| dc.format.mimetype |
application/octet-stream |
|
| dc.format.mimetype |
application/pdf |
|
| dc.language.iso |
en_US |
|
| dc.relation.ispartofseries |
AITR-1416 |
en_US |
| dc.subject |
grouping |
en_US |
| dc.subject |
indexing |
en_US |
| dc.subject |
recognition |
en_US |
| dc.subject |
invariants |
en_US |
| dc.subject |
sensing erro |
en_US |
| dc.subject |
snon-accidental properties |
en_US |
| dc.title |
Recognizing 3-D Objects Using 2-D Images |
en_US |
