From Inpainting to Active Contours

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract   Background subtraction is an elementary method for detection of foreground objects and their segmentations. Obviously it requires an observation image as well as a background one. In this work we attempt to remove the last requirement by reconstructing the background from the observation image and a guess on the location of the object to be segmented via variational inpainting method. A numerical evaluation of this reconstruction provides a "disocclusion measure" and the correct foreground segmentation region is expected to maximize this measure. This formulation is in fact an optimal control problem, where controls are shapes/regions and states are the corresponding inpaintings. Optimization of the disocclusion measure leads formally to a coupled contour evolution equation, an inpainting equation (the state equation) as well as a linear PDE depending on the inpainting (the adjoint state equation). The contour evolution is implemented in the framework of level sets. Finally, the proposed method is validated on various examples. We focus among others in the segmentation of calcified plaques observed in radiographs from human lumbar aortic regions.

Keywords  Segmentation - Inpainting - Active contours - Disocclusion - Adjoint methods - Variational methods

Original languageEnglish
JournalInternational Journal of Computer Vision
Issue number1
Pages (from-to)31-43
Number of pages14
Publication statusPublished - 2008

    Research areas

  • Faculty of Science - Segmentation, Inpainting, Active contours, Disocclusion, Ajoint methods, Variational methods

ID: 6510798