Advanced Search
DSpace@MIT

Geometric Aspects of Visual Object Recognition

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.author Breuel, Thomas M. en_US
dc.date.accessioned 2004-11-19T17:19:47Z
dc.date.available 2004-11-19T17:19:47Z
dc.date.issued 1992-05-01 en_US
dc.identifier.other AITR-1374 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/7342
dc.description.abstract This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably. en_US
dc.format.extent 173 p. en_US
dc.format.extent 33022903 bytes
dc.format.extent 26499530 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AITR-1374 en_US
dc.subject computer vision en_US
dc.subject bouded error en_US
dc.subject point matching en_US
dc.subject 3D objectsrecognition en_US
dc.title Geometric Aspects of Visual Object Recognition en_US


Files in this item

Name Size Format Description
AITR-1374.ps 31.49Mb Postscript
AITR-1374.pdf 25.27Mb PDF

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage