Some fast projection methods based on Chan-Vese model for image segmentation

Research output: Contribution to journalArticle

Authors

Colleges, School and Institutes

External organisations

  • Qingdao University

Abstract

The Chan-Vese model is very popular for image segmentation. Technically, it combines the reduced Mumford-Shah model and level set method (LSM). This segmentation problem is solved interchangeably by computing a gradient descent flow and expensively and tediously re-initializing a level set function (LSF). Though many approaches have been proposed to overcome the re-initialization problem, the low efficiency for this segmentation problem is still not solved effectively. In this paper, we first investigate the relationship between the L 1-based total variation (TV) regularizer term of Chan-Vese model and the constraint on LSF and then propose a new technique to solve the re-initialization problem. In detail, four fast projection methods are proposed, i.e., split Bregman projection method (SBPM), augmented Lagrangian projection method (ALPM), dual split Bregman projection method (DSBPM), and dual augmented Lagrangian projection method (DALPM). These four methods without re-initialization are faster than the existing approaches. Finally, extensive numerical experiments on synthetic and real images are presented to validate the effectiveness and efficiency of these four proposed methods.

Details

Original languageEnglish
Article number2496060
JournalEurasip Journal on Image and Video Processing
Volume2014
Publication statusPublished - 27 Jan 2014

Keywords

  • Chan-Vese model, Projection method, Re-initialization, Variational level set method