1. DSpace at MEDIU
  2. Harvested articles مقالات مستوردة من مؤسسات وجامعات عالمية
  3. MIT Items
Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7285
Full metadata record
DC FieldValueLanguage
dc.creatorYokono, Jerry Jun-
dc.creatorPoggio, Tomaso-
dc.date2004-10-20T21:05:26Z-
dc.date2004-10-20T21:05:26Z-
dc.date2004-04-27-
dc.date.accessioned2013-10-09T02:48:58Z-
dc.date.available2013-10-09T02:48:58Z-
dc.date.issued2013-10-09-
dc.identifierAIM-2004-010-
dc.identifierCBCL-238-
dc.identifierhttp://hdl.handle.net/1721.1/7285-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/1721-
dc.descriptionLocal 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.-
dc.format15 p.-
dc.format5162833 bytes-
dc.format968095 bytes-
dc.formatapplication/postscript-
dc.formatapplication/pdf-
dc.languageen_US-
dc.relationAIM-2004-010-
dc.relationCBCL-238-
dc.subjectAI-
dc.subjectobject recognition-
dc.subjectlocal descriptor-
dc.subjectrotation invariant-
dc.titleRotation Invariant Object Recognition from One Training Example-
Appears in Collections:MIT Items

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.