Multi-Reference Shape Priors for Active Contours

Alban Foulonneau (1) , Pierre Charbonnier (2) , Fabrice Heitz (3)

1 MIPS - Modélisation, Intelligence, Processus et Système
2 ERA 27 - Equipe de Recherche Associée n°27
3 LSIIT - Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection

In this paper, we present a new way of constraining the evolution of an active contour with respect to a set of fixed reference shapes. This approach is based on a description of shapes by the Legendre moments computed from their characteristic function. This provides a region-based representation that can handle arbitrary shape topologies. Moreover, exploiting the properties of moments, it is possible to include intrinsic affine invariance in the descriptor, which solves the issue of shape alignment without increasing the number of d.o.f. of the initial problem and allows introducing geometric shape variabilities. Our new shape prior is based on a distance, in terms of descriptors, between the evolving curve and the reference shapes.Minimizing the corresponding shape energy leads to a geometric flow that does not rely on any particular representation of the contour and can be implemented with any contour evolution algorithm. We introduce our prior into a two-class segmentation functional, showing its benefits on segmentation results in presence of severe occlusions and clutter. Examples illustrate the ability of the model to deal with large affine deformation and to take into account a set of reference shapes of different topologies.

Mots clés: Active contours; Segmentation; Region-based approach; Legendre moments; Shape constraint; Shape derivative; Multi-reference model; Geometric invariance

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Alban Foulonneau, Pierre Charbonnier, Fabrice Heitz. Multi-Reference Shape Priors for Active Contours. International Journal of Computer Vision, 2009, 81, pp.68-81. ⟨10.1007/s11263-008-0163-3⟩. ⟨hal-00873962⟩