This paper tackles an important aspect of the variational problem underlying ac- tive contours: optimization by gradient flows. Classically, the definition of a gra- dient depends directly on the choice of an inner product structure. This considera- tion is largely absent from the active contours literature. Most authors, explicitely or implicitely, assume that the space of admissible deformations is ruled by the canonical L2 inner product. The classical gradient flows reported in the literature are relative to this particular choice. Here, we investigate the relevance of using (i) other inner products, yielding other gradient descents, and (ii) other minimiz- ing flows not deriving from any inner product. In particular, we show how to induce different degrees of spatial consistency into the minimizing flow, in order to decrease the probability of getting trapped into irrelevant local minima. We report numerical experiments indicating that the sensitivity of the active contours method to initial conditions, which seriously limits its applicability and efficiency, is alleviated by our application-specific spatially coherent minimizing flows. We show that the choice of the inner product can be seen as a prior on the deformation fields and we present an extension of the definition of the gradient toward more general priors.
Charpiat, G., Maurel, P., Pons, J. P., Keriven, R., & Faugeras, O. (2007). Generalized gradients: Priors on minimization flows. International Journal of Computer Vision, 73(3), 325–344. https://doi.org/10.1007/s11263-006-9966-2