Poisson image denoising based on fractional-order total variation
Poisson image denoising based on fractional-order total variation
复制标题
DOI：
10.3934/ipi.2019064
复制
发表时间：
2020
影响因子：
1.3
通讯作者：
M. R. Chowdhury;Jun Zhang;Jing Qin;Y. Lou
中科院分区：
文献类型：
--
作者：
M. R. Chowdhury;Jun Zhang;Jing Qin;Y. Lou
泊松噪声是一种重要的电子噪声，存在于各种光子限制成像系统中。与高斯噪声不同，泊松噪声取决于图像强度，这使得图像恢复非常具有挑战性。此外，图像的复杂几何形状需要能够保持分段平滑度的正则化。在本文中，我们提出了一种基于分数阶总变分（FOTV）的泊松去噪模型。模型解的存在性和唯一性得以建立。为了有效地解决该问题，我们提出了三种基于 Chambolle-Pock 原对偶方法、前向-后向分裂方案和乘子交替方向法 (ADMM) 的数值算法，每种算法都保证收敛。提供了各种实验结果来证明我们提出的方法相对于最先进的泊松去噪方法的有效性和效率。
Poisson noise is an important type of electronic noise that is present in a variety of photon-limited imaging systems. Different from the Gaussian noise, Poisson noise depends on the image intensity, which makes image restoration very challenging. Moreover, complex geometry of images desires a regularization that is capable of preserving piecewise smoothness. In this paper, we propose a Poisson denoising model based on the fractional-order total variation (FOTV). The existence and uniqueness of a solution to the model are established. To solve the problem efficiently, we propose three numerical algorithms based on the Chambolle-Pock primal-dual method, a forward-backward splitting scheme, and the alternating direction method of multipliers (ADMM), each with guaranteed convergence. Various experimental results are provided to demonstrate the effectiveness and efficiency of our proposed methods over the state-of-the-art in Poisson denoising.