Show simple item record

Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries

dc.date.accessioned2004-10-04T14:24:21Z
dc.date.accessioned2018-11-24T10:11:19Z
dc.date.available2004-10-04T14:24:21Z
dc.date.available2018-11-24T10:11:19Z
dc.date.issued1992-02-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/5968
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/5968
dc.description.abstractIn this note we discuss how recognition can be achieved from a single 2D model view exploiting prior knowledge of an object's structure (e.g. symmetry). We prove that for any bilaterally symmetric 3D object one non- accidental 2D model view is sufficient for recognition. Symmetries of higher order allow the recovery of structure from one 2D view. Linear transformations can be learned exactly from a small set of examples in the case of "linear object classes" and used to produce new views of an object from a single view.en_US
dc.format.extent22 p.en_US
dc.format.extent1962838 bytes
dc.format.extent1538757 bytes
dc.language.isoen_US
dc.subjectobject recognitionen_US
dc.subjectclass and prototypesen_US
dc.subjectsymmetryen_US
dc.subjectlearningen_US
dc.titleRecognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetriesen_US


Files in this item

FilesSizeFormatView
AIM-1347.pdf1.538Mbapplication/pdfView/Open
AIM-1347.ps1.962Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record