| dc.contributor.author |
Poggio, Tomaso |
en_US |
| dc.contributor.author |
Brunelli, Roberto |
en_US |
| dc.date.accessioned |
2004-10-04T14:24:16Z |
|
| dc.date.available |
2004-10-04T14:24:16Z |
|
| dc.date.issued |
1992-02-01 |
en_US |
| dc.identifier.other |
AIM-1354 |
en_US |
| dc.identifier.uri |
http://hdl.handle.net/1721.1/5964 |
|
| dc.description.abstract |
sWe show that we can optimally represent the set of 2D images producedsby the point features of a rigid 3D model as two lines in twoshigh-dimensional spaces. We then decribe a working recognition systemsin which we represent these spaces discretely in a hash table. We cansaccess this table at run time to find all the groups of model featuressthat could match a group of image features, accounting for the effectssof sensing error. We also use this representation of a model's imagessto demonstrate significant new limitations of two other approaches tosrecognition: invariants, and non-accidental properties. |
en_US |
| dc.description.provenance |
Made available in DSpace on 2004-10-04T14:24:16Z (GMT). No. of bitstreams: 2
AIM-1354.ps: 1356111 bytes, checksum: 3457b3105992aeafebff31d995b1a4d8 (MD5)
AIM-1354.pdf: 1055073 bytes, checksum: d1d5defb5e0c300724cc68cc0f4d5238 (MD5)
Previous issue date: 1992-02-01 |
en |
| dc.format.extent |
15 p. |
en_US |
| dc.format.extent |
1356111 bytes |
|
| dc.format.extent |
1055073 bytes |
|
| dc.format.mimetype |
application/postscript |
|
| dc.format.mimetype |
application/pdf |
|
| dc.language.iso |
en_US |
|
| dc.relation.ispartofseries |
AIM-1354 |
en_US |
| dc.subject |
graphics |
en_US |
| dc.subject |
hyperbf networks |
en_US |
| dc.subject |
in-betweening |
en_US |
| dc.subject |
momory-basedsgraphics |
en_US |
| dc.subject |
teleconferencing |
en_US |
| dc.title |
A Novel Approach to Graphics |
en_US |
