Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network
dc.date.accessioned | 2004-10-04T15:12:55Z | |
dc.date.accessioned | 2018-11-24T10:14:15Z | |
dc.date.available | 2004-10-04T15:12:55Z | |
dc.date.available | 2018-11-24T10:14:15Z | |
dc.date.issued | 1988-07-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6493 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/6493 | |
dc.description.abstract | Certain salient structures in images attract our immediate attention without requiring a systematic scan. We present a method for computing saliency by a simple iterative scheme, using a uniform network of locally connected processing elements. The network uses an optimization approach to produce a "saliency map," a representation of the image emphasizing salient locations. The main properties of the network are: (i) the computations are simple and local, (ii) globally salient structures emerge with a small number of iterations, and (iii) as a by-product of the computations, contours are smoothed and gaps are filled in. | en_US |
dc.format.extent | 2792059 bytes | |
dc.format.extent | 1101302 bytes | |
dc.language.iso | en_US | |
dc.title | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1061.pdf | 1.101Mb | application/pdf | View/ |
AIM-1061.ps | 2.792Mb | application/postscript | View/ |