The L0-regularized discrete variational level set method for image segmentation
作者：
Highlights：
• We propose a discrete variational ternary level set method with two L0-based regularizers for image segmentation.
• The proposed model can be regarded as a discrete form of the Chan-Vese model.
• We present an alternating minimization algorithm to efficiently solve the minimization problem.
• The proposed method is robust to three types of noise (speckle, Gaussian and salt & pepper) and effective for some real images.
摘要
•We propose a discrete variational ternary level set method with two L0-based regularizers for image segmentation.•The proposed model can be regarded as a discrete form of the Chan-Vese model.•We present an alternating minimization algorithm to efficiently solve the minimization problem.•The proposed method is robust to three types of noise (speckle, Gaussian and salt & pepper) and effective for some real images.
论文关键词：Image segmentation,Level set,Variational model,L 0 -based regularizer
论文评审过程：Received 23 January 2017, Revised 25 December 2017, Accepted 4 March 2018, Available online 12 March 2018, Version of Record 4 June 2018.
论文官网地址：https://doi.org/10.1016/j.imavis.2018.03.001
