Three-Dimensional Convex and Selective Variational Image Segmentation Model
Jumaat, A. K. and Chen, K.
Corresponding Email: abdulkadir@tmsk.uitm.edu.my
Received date: 30 April 2020
Accepted date: 28 August 2020
Abstract:
Selective image segmentation is the task of extracting one object of interest among many others in an image based on minimal user input. Several three-dimensional (3-D) selective models were proposed and they would find local minimizer because of their non-convex formulation, hence they are sensitive to initialization. This paper presents a new formulation for the 3-D convex selective segmentation model. In order to solve the developed 3-D model, a projection algorithm is proposed. Numerical tests show that the proposed model is effective in segmenting 3-D complex image structures and allowing a global minimizer to be found independently of initialization.
Keywords: Convex segmentation, image processing, level set, selective image segmentation, three dimensional, total variational model