Title :
Non-local segmentation and inpaiting
Author :
Jung, Miyoun ; Peyré, Gabriel ; Cohen, Laurent D.
Author_Institution :
Ceremade, Univ. Paris-Dauphine, Paris, France
Abstract :
This article introduces a new variational image segmentation method that makes use of non-local comparisons between pairs of patches in the image and is robust to missing data (e.g. damaged pixels or large missing regions). The resulting segmentation is at the heart of a novel inpainting algorithm that also uses a non-local regularization. This segmentation and inpainting approach only requires a local homogeneity of the features inside and outside the region to be segmented. In contrast to existing region-based segmentation methods, it allows us to segment regions with smoothly varying intensity as well as multiple objects with different intensities. This comparison principle is also less sensitive to initialization than edge-based approaches.
Keywords :
edge detection; image segmentation; edge-based approach; image patch; local homogeneity; nonlocal inpaiting algorithm; nonlocal regularization; nonlocal segmentation; region-based segmentation method; variational image segmentation method; Active contours; Conferences; Image edge detection; Image segmentation; Level set; Robustness; active contour; inpainting; level set function; non-local energy; segmentation;
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location :
Brussels
Print_ISBN :
978-1-4577-1304-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2011.6116432