Advanced Search

Rotation Invariant Object Recognition from One Training Example

Research and Teaching Output of the MIT Community

Show simple item record Yokono, Jerry Jun en_US Poggio, Tomaso en_US 2004-10-20T21:05:26Z 2004-10-20T21:05:26Z 2004-04-27 en_US
dc.identifier.other AIM-2004-010 en_US
dc.identifier.other CBCL-238 en_US
dc.description.abstract Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-- is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance of the descriptor. We also describe feature selection based on a single training image. Virtual images are generated by rotating and rescaling the image and robust features are selected. The results confirm robust performance in cluttered scenes, in the presence of partial occlusions, and when the object is embedded in different backgrounds. en_US
dc.format.extent 15 p. en_US
dc.format.extent 5162833 bytes
dc.format.extent 968095 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AIM-2004-010 en_US
dc.relation.ispartofseries CBCL-238 en_US
dc.subject AI en_US
dc.subject object recognition en_US
dc.subject local descriptor en_US
dc.subject rotation invariant en_US
dc.title Rotation Invariant Object Recognition from One Training Example en_US

Files in this item

Name Size Format Description 4.923Mb Postscript
AIM-2004-010.pdf 945.4Kb PDF

This item appears in the following Collection(s)

Show simple item record