Graph Cuts in Computer Vision

Graph Cuts In Computer Vision

As applied in the field of computer vision, graph cuts can be employed to efficiently solve a wide variety of low-level computer vision problems (early vision), such as image smoothing, the stereo correspondence problem, and many other computer vision problems that can be formulated in terms of energy minimization. Such energy minimization problems can be reduced to instances of the maximum flow problem in a graph (and thus, by the max-flow min-cut theorem, define a minimal cut of the graph). Under most formulations of such problems in computer vision, the minimum energy solution corresponds to the maximum a posteriori estimate of a solution. Although many computer vision algorithms involve cutting a graph (e.g., normalized cuts), the term "graph cuts" is applied specifically to those models which employ a max-flow/min-cut optimization (other graph cutting algorithms may be considered as graph partitioning algorithms).

"Binary" problems (such as denoising a binary image) can be solved exactly using this approach; problems where pixels can be labeled with more than two different labels (such as stereo correspondence, or denoising of a grayscale image) cannot be solved exactly, but solutions produced are usually near the global optimum.

Read more about Graph Cuts In Computer Vision:  History, Notations, Existing Methods, Criticism, Algorithm, Software

Famous quotes containing the words graph, cuts, computer and/or vision:

    In this Journal, my pen is a delicate needle point, tracing out a graph of temperament so as to show its daily fluctuations: grave and gay, up and down, lamentation and revelry, self-love and self-disgust. You get here all my thoughts and opinions, always irresponsible and often contradictory or mutually exclusive, all my moods and vapours, all the varying reactions to environment of this jelly which is I.
    W.N.P. Barbellion (1889–1919)

    Spirit is the life that itself cuts into life: with its own torment it increases its own knowledge. Did you already know that?
    Friedrich Nietzsche (1844–1900)

    The computer takes up where psychoanalysis left off. It takes the ideas of a decentered self and makes it more concrete by modeling mind as a multiprocessing machine.
    Sherry Turkle (b. 1948)

    A novel is a mirror carried along a high road. At one moment it reflects to your vision the azure skies at another the mire of the puddles at your feet. And the man who carries this mirror in his pack will be accused by you of being immoral! His mirror shews [sic] the mire, and you blame the mirror! Rather blame that high road upon which the puddle lies, still more the inspector of roads who allows the water to gather and the puddle to form.
    Stendhal [Marie Henri Beyle] (1783–1842)