Show simple item record

Rotation Invariant Object Recognition from One Training Example

dc.date.accessioned2004-10-20T21:05:26Z
dc.date.accessioned2018-11-24T10:23:41Z
dc.date.available2004-10-20T21:05:26Z
dc.date.available2018-11-24T10:23:41Z
dc.date.issued2004-04-27en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/7285
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/7285
dc.description.abstractLocal 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.extent15 p.en_US
dc.format.extent5162833 bytes
dc.format.extent968095 bytes
dc.language.isoen_US
dc.subjectAIen_US
dc.subjectobject recognitionen_US
dc.subjectlocal descriptoren_US
dc.subjectrotation invarianten_US
dc.titleRotation Invariant Object Recognition from One Training Exampleen_US


Files in this item

FilesSizeFormatView
AIM-2004-010.pdf968.0Kbapplication/pdfView/Open
AIM-2004-010.ps5.162Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record