Accelerated Local Binary Fitting Scheme for Medical Images Segmentation

Journal Of Electrical Systems And Signals

مقاله 2، دوره 2، شماره 1، تیر 2014، صفحه 1-8   

نوع مقاله: Researsh Articles

شناسه دیجیتال (DOI): 10.22067/ess.v2i1.28646

نویسندگان

Mohammad-Bagher Khamechian¹؛ Mahdi Saadatmand-Tarzjan^{* 2}

¹Ferdowsi University of Mashhad

²Department of Electrical Engineering, Ferdowsi University of Mashhad

چکیده

Geometric and geodesic active contours are typical approaches for medical image segmentation. Specially, local binary fitting (LBF) effectively takes advantage of the local intensity average in the energy functional to overcome segmentation difficulties caused by intensity inhomogeneity and ruptured edges. Despite promising results, the convergence rate of LBF is too slow. In this paper, we proposed a new efficient implementation for LBF based on the additive operator splitting scheme. In more detail, the multi-dimensional deformation equation of LBF is decomposed into some one-dimensional equations which can be efficiently solved by Tomas' algorithm. Experimental results demonstrated that the proposed algorithm performs better than LBF in terms of both CPU time and solution quality.

کلیدواژه‌ها

Geometric Active Contours؛ Level Set؛ Local Binary Fitting؛ Additive Operator Splitting؛ Image Segmentation