Author/Authors :
Fang, Jiangxiong East China University of Technology - Nanchang, China , Liu, Hesheng East China University of Technology - Nanchang, China , Liu, Huaxiang East China University of Technology - Nanchang, China , Zhang, Liting East China University of Technology - Nanchang, China , Liu, Jun East China University of Technology - Nanchang, China
Abstract :
This paper presents a novel fuzzy region-based active contour model for image segmentation. By incorporating local patch-energy
functional along each pixel of the evolving curve into the fuzziness of the energy, we construct a patch-based energy function
without the regurgitation term. Its purpose is not only to make the active contour evolve very stably without the periodical
initialization during the evolution but also to reduce the effect of noise. In particular, in order to reject local minimal of the energy
functional, we utilize a direct method to calculate the energy alterations instead of solving the Euler-Lagrange equation of the
underlying problem. Compared with other fuzzy active contour models, experimental results on synthetic and real images show
the advantages of the proposed method in terms of computational efficiency and accuracy.
