Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries
dc.date.accessioned | 2004-10-04T14:24:21Z | |
dc.date.accessioned | 2018-11-24T10:11:19Z | |
dc.date.available | 2004-10-04T14:24:21Z | |
dc.date.available | 2018-11-24T10:11:19Z | |
dc.date.issued | 1992-02-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/5968 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/5968 | |
dc.description.abstract | In 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.extent | 22 p. | en_US |
dc.format.extent | 1962838 bytes | |
dc.format.extent | 1538757 bytes | |
dc.language.iso | en_US | |
dc.subject | object recognition | en_US |
dc.subject | class and prototypes | en_US |
dc.subject | symmetry | en_US |
dc.subject | learning | en_US |
dc.title | Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1347.pdf | 1.538Mb | application/pdf | View/ |
AIM-1347.ps | 1.962Mb | application/postscript | View/ |