A Finite Element Computational Framework for Active Contours on Graphs
This work addresses a domain-specific problem in image segmentation and computer vision, offering incremental improvements through a new computational framework.
The authors tackled the problem of solving active contour models on graphs by introducing a finite element computational framework that reduces the problem to a sparse non-linear system, and they demonstrated its effectiveness with experimental evidence for image segmentation.
In this paper we present a new framework for the solution of active contour models on graphs. With the use of the Finite Element Method we generalize active contour models on graphs and reduce the problem from a partial differential equation to the solution of a sparse non-linear system. Additionally, we extend the proposed framework to solve models where the curve evolution is locally constrained around its current location. Based on the previous extension, we propose a fast algorithm for the solution of a wide range active contour models. Last, we present a supervised extension of Geodesic Active Contours for image segmentation and provide experimental evidence for the effectiveness of our framework.