Completely Convex Formulation of the Chan-Vese Image Segmentation Model

• Published in: International journal of computer vision Vol. 98; no. 1; pp. 103 - 121
• Main Authors: Brown, Ethan S., Chan, Tony F., Bresson, Xavier
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.05.2012; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Applied mathematics; Applied sciences; Approximation; Artificial Intelligence; Computer aided manufacturing; Computer Imaging; Computer Science; Computer science; control theory; systems; Data processing. List processing. Character string processing; Exact sciences and technology; Experiments; Image processing; Image Processing and Computer Vision; Image processing equipment industry; Image processing systems; Mathematical analysis; Mathematical models; Memory organisation. Data processing; Methods; Optimization; Optimization techniques; Partial differential equations; Pattern Recognition; Pattern Recognition and Graphics; Pattern recognition. Digital image processing. Computational geometry; Relaxation; Segmentation; Software; Studies; Two phase; Vision; Vision systems; Convex relaxation; Image segmentation; means; Chan-Vese model; Vector-valued functional lifting; Level set method; K-means; Computer vision; Initial condition; Computer aided manufacturing; Image processing; CAML language; Contour line; Minimization; K means algorithm; Transaction processing; Modeling; Applied mathematics; Optimal solution; Classification; Optimal approximation; Edge detection; Non convex analysis
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-011-0499-y

The active contours without edges model of Chan and Vese (IEEE Transactions on Image Processing 10(2):266–277, 2001 ) is a popular method for computing the segmentation of an image into two phases, based on the piecewise constant Mumford-Shah model. The minimization problem is non-convex even when the optimal region constants are known a priori . In (SIAM Journal of Applied Mathematics 66(5):1632–1648, 2006 ), Chan, Esedoḡlu, and Nikolova provided a method to compute global minimizers by showing that solutions could be obtained from a convex relaxation. In this paper, we propose a convex relaxation approach to solve the case in which both the segmentation and the optimal constants are unknown for two phases and multiple phases. In other words, we propose a convex relaxation of the popular K-means algorithm. Our approach is based on the vector-valued relaxation technique developed by Goldstein et  al. (UCLA CAM Report 09-77, 2009 ) and Brown et al. (UCLA CAM Report 10-43, 2010 ). The idea is to consider the optimal constants as functions subject to a constraint on their gradient. Although the proposed relaxation technique is not guaranteed to find exact global minimizers of the original problem, our experiments show that our method computes tight approximations of the optimal solutions. Particularly, we provide numerical examples in which our method finds better solutions than the method proposed by Chan et al. (SIAM Journal of Applied Mathematics 66(5):1632–1648, 2006 ), whose quality of solutions depends on the choice of the initial condition.