Graph cuts in computer vision: Difference between revisions

Revision as of 08:05, 8 April 2007

Revision as of 08:16, 8 April 2007

Line 1:

The theory of graph cuts, [[Cut (graph theory)]], was first applied in [[Computer vision]] in the now "classic" 1989 paper by Greig, Porteous and Seheult of Durham University, UK,. Please see asthe referencedreference below.

In the statistical context of smoothing noisy, or corrupted, images, Greig, Porteous and Seheult showed how the maximum a posteriori estimate of a binary image can be obtained ''exactly'' by maximising the flow through an associated image network. Prior to this result ''approximate'', although more general, techniques such as simulated annealing, as proposed by the Geman brothers, or iterated conditional modes, as suggested by Julian Beasg, were used to solve these types of problems.

== References ==

*DJ.ME. Greig,Besag B.T. Porteous, A.H. Seheult(1986), ''ExactOn maximumthe astatistical posteriorianalysis estimationof fordirty binarypictures (with imagesdiscussion)'', Journal of the Royal Statistical Society Series B, 27148, 259 - 279 (1989)302.

*Geman. D and Geman. S (1984), ''Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images'', IEEE Trans. Pattn Anal. Mach. Intell., 6, 721 - 741.

*D.M. Greig, B.T. Porteous, A.H. Seheult (1989), ''Exact maximum a posteriori estimation for binary images'', Journal of the Royal Statistical Society Series B, 51, 271 - 279.

[[Category: Computer vision]]