Domain decomposition methods with graph cuts algorithms for total variation minimization

Recently, graph cuts algorithms have been used to solve variational image restoration problems, especially for noise removal and segmentation. Compared to time-marching PDE methods, graph cuts based methods are more efficient and able to obtain the global minimizer. However, for high resolution and...

Full description

Saved in:
Bibliographic Details
Main Authors: Duan, Yuping, Tai, Xue Cheng
Other Authors: School of Physical and Mathematical Sciences
Format: Article
Language:English
Published: 2013
Online Access:https://hdl.handle.net/10356/98057
http://hdl.handle.net/10220/12328
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Recently, graph cuts algorithms have been used to solve variational image restoration problems, especially for noise removal and segmentation. Compared to time-marching PDE methods, graph cuts based methods are more efficient and able to obtain the global minimizer. However, for high resolution and large-scale images, the cost of both memory and computational time increases dramatically. In this paper, we combine the domain decomposition method and the graph cuts algorithm for solving the total variation minimizations with L1 and L2 fidelity term. Numerous numerical experiments on large-scale data demonstrate the proposed algorithm yield good results in terms of computational time and memory usage.