On the Sensitivity of the Hough Transform for Object Recognition
dc.date.accessioned | 2004-10-04T14:36:40Z | |
dc.date.accessioned | 2018-11-24T10:11:38Z | |
dc.date.available | 2004-10-04T14:36:40Z | |
dc.date.available | 2018-11-24T10:11:38Z | |
dc.date.issued | 1988-05-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6039 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/6039 | |
dc.description.abstract | A common method for finding an object's pose is the generalized Hough transform, which accumulates evidence for possible coordinate transformations in a parameter space and takes large clusters of similar transformations as evidence of a correct solution. We analyze this approach by deriving theoretical bounds on the set of transformations consistent with each data-model feature pairing, and by deriving bounds on the likelihood of false peaks in the parameter space, as a function of noise, occlusion, and tessellation effects. We argue that blithely applying such methods to complex recognition tasks is a risky proposition, as the probability of false positives can be very high. | en_US |
dc.format.extent | 40 p. | en_US |
dc.format.extent | 5359682 bytes | |
dc.format.extent | 2031093 bytes | |
dc.language.iso | en_US | |
dc.subject | Hough transform | en_US |
dc.subject | object recognition | en_US |
dc.title | On the Sensitivity of the Hough Transform for Object Recognition | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1044.pdf | 2.031Mb | application/pdf | View/ |
AIM-1044.ps | 5.359Mb | application/postscript | View/ |