Nonlocal Active Contours - Archive ouverte HAL Access content directly
Journal Articles SIAM Journal on Imaging Sciences Year : 2012

Nonlocal Active Contours


This article introduces a novel class of active contour models for image segmentation. It makes use of non-local comparisons between pairs of patches within each region to be segmented. The corresponding variational segmentation problem is implemented using a level set formulation that can handle an arbitrary number of regions. The pairwise interaction of features only constrains the local homogeneity of image features, which is crucial to capture regions with smoothly spatially varying features. This segmentation method is generic and can be adapted to various segmentation problems by designing an appropriate metric between patches. We instantiate this framework using several classes of features and metrics. Piecewise smooth grayscale and color images are handled using $L^2$ distance between image patches. We show examples of efficient segmentation of natural color images. Locally oriented textures are segmented using the $L^2$ distance between patches of Gabor coefficients. We introduce a Wasserstein distance between local empirical distributions for locally homogenous random textures. A correlation metric between local motion signatures is able to segment piecewise smooth optical flows.
Fichier principal
Vignette du fichier
SIIMS-Nonlocal-active.pdf (1.9 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00650735 , version 1 (12-12-2011)



Jung Miyoun, Gabriel Peyré, Laurent D. Cohen. Nonlocal Active Contours. SIAM Journal on Imaging Sciences, 2012, 5 (3), pp.1022-1054. ⟨10.1137/11085863X⟩. ⟨hal-00650735⟩
933 View
782 Download



Gmail Facebook X LinkedIn More