Advanced Search
DSpace@MIT

Affine Matching with Bounded Sensor Error: A Study of Geometric Hashing and Alignment

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.author Grimson W. Eric L. en_US
dc.contributor.author Huttenlocher, Daniel P. en_US
dc.contributor.author Jacobs, David W. en_US
dc.date.accessioned 2004-10-04T15:31:21Z
dc.date.available 2004-10-04T15:31:21Z
dc.date.issued 1991-08-01 en_US
dc.identifier.other AIM-1250 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/6557
dc.description.abstract Affine transformations are often used in recognition systems, to approximate the effects of perspective projection. The underlying mathematics is for exact feature data, with no positional uncertainty. In practice, heuristics are added to handle uncertainty. We provide a precise analysis of affine point matching, obtaining an expression for the range of affine-invariant values consistent with bounded uncertainty. This analysis reveals that the range of affine-invariant values depends on the actual $x$-$y$-positions of the features, i.e. with uncertainty, affine representations are not invariant with respect to the Cartesian coordinate system. We analyze the effect of this on geometric hashing and alignment recognition methods. en_US
dc.format.extent 5692320 bytes
dc.format.extent 2225833 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AIM-1250 en_US
dc.title Affine Matching with Bounded Sensor Error: A Study of Geometric Hashing and Alignment en_US


Files in this item

Name Size Format Description
AIM-1250.ps 5.428Mb Postscript
AIM-1250.pdf 2.122Mb PDF

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage