This paper is devoted to piecewise-constant segmentation of imagesusing a curve evolution approach in a variational formulation. Theproblem to be solved is also called the minimal partition problem,as formulated by Mumford and Shah [20]. The proposed new models areextensions of the techniques previously introduced in [9], [10],[27]. We represent here the set of boundaries of the segmentationimplicitly, by a multilayer of level-lines of a continuous function.In the standard approach of front propagation, only one level lineis used to represent the boundary. The multilayer idea is inspiredfrom previous work on island dynamics for epitaxial growth [14],[4]. Using a multilayer level set approach, the computational costis smaller and in some applications, a nested structure of the levellines can be useful.
CITATION STYLE
Rangarajan, A., Figueiredo, M., & Zerubia, J. (Eds.). (2003). Energy Minimization Methods in Computer Vision and Pattern Recognition (Vol. 2683). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/b11710
Mendeley helps you to discover research relevant for your work.