Résumé
As applied in the field of computer vision, graph cut optimization can be employed to efficiently solve a wide variety of low-level computer vision problems (early vision), such as , the stereo correspondence problem, , object co-segmentation, and many other computer vision problems that can be formulated in terms of energy minimization. Many of these energy minimization problems can be approximated by solving a 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 ) 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. The theory of graph cuts used as an optimization method was first applied in computer vision in the seminal paper by Greig, Porteous and Seheult of Durham University. Allan Seheult and Bruce Porteous were members of Durham's lauded statistics group of the time, led by Julian Besag and Peter Green, with the optimisation expert Margaret Greig notable as the first ever female member of staff of the Durham Mathematical Sciences Department. In the Bayesian statistical context of smoothing noisy (or corrupted) images, they showed how the maximum a posteriori estimate of a can be obtained exactly by maximizing the flow through an associated image network, involving the introduction of a source and sink. The problem was therefore shown to be efficiently solvable.
À propos de ce résultat
Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.
Publications associées (2)
Cours associés (3)
EE-550: Image and video processing
This course covers fundamental notions in image and video processing, as well as covers most popular tools used, such as edge detection, motion estimation, segmentation, and compression. It is compose
CS-233(a): Introduction to machine learning (BA3)
Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analy
MICRO-511: Image processing I
Introduction to the basic techniques of image processing. Introduction to the development of image-processing software and to prototyping in JAVA. Application to real-world examples in industrial visi
Séances de cours associées (16)
Forme à partir de Stereo-2
Explore les concepts de vision stéréoscopique tels que les occlusions, l'impact de la taille de la fenêtre, la stéréo multivue, la reconstruction dynamique de la forme et la segmentation basée sur des graphiques.
Opérations morphologiques
Couvre les opérations morphologiques de base à avancées pour les flux de travail d'analyse d'images.
Segmentation : Techniques et applications
Explore les techniques de segmentation, y compris les modèles CNN et U-Net, pour la reconnaissance et l'analyse d'images, en mettant l'accent sur les méthodes automatisées qui permettent de gagner du temps.
Afficher plus