全变差图像恢复的自适应步长梯度投影算法

Gradient Projection Algorithm for Total Variation Image Restoration by Adaptive Steplength Selection Rules

针对图像去噪问题,本文基于全变差对偶公式提出一个新的梯度投影算法.算法采用改进的非单调线搜索和自适应BB(Barzilai-Borwein)步长,有效地改善了Chambolle梯度投影算法收敛慢的缺点.数值结果表明新算法优于一些已有的梯度投影算法.

We propose a new gradient projection algorithm for image denoising based on the dual of total variation. The new method exploits nonmonotone line-search and adaptive steplength selection based on strategies for alternation of the well-known Barzilai-Borwein rules. The proposed method is much faster than the Chambolle＇s gradient projection algorithm. Numerical results illustrate the efficiency of this method.