Qian Weixin, Qi Shuangxi, Wang Wanli, Cheng Jinming, Liu Dongbing
Institute of Fluid Physics, CAEP, P.O. Box 919-109, Mianyang 621900, China.
Rev Sci Instrum. 2011 Sep;82(9):093504. doi: 10.1063/1.3638463.
Neutron penumbral imaging is a significant diagnostic technique in laser-driven inertial confinement fusion experiment. It is very important to develop a new reconstruction method to improve the resolution of neutron penumbral imaging. A new nonlinear reconstruction method based on total variation (TV) regularization is proposed in this paper. A TV-norm is used as regularized term to construct a smoothing functional for penumbral image reconstruction in the new method, in this way, the problem of penumbral image reconstruction is transformed to the problem of a functional minimization. In addition, a fixed point iteration scheme is introduced to solve the problem of functional minimization. The numerical experimental results show that, compared to linear reconstruction method based on Wiener filter, the TV regularized nonlinear reconstruction method is beneficial to improve the quality of reconstructed image with better performance of noise smoothing and edge preserving. Meanwhile, it can also obtain the spatial resolution with 5 μm which is higher than the Wiener method.
中子半值层成像在激光驱动惯性约束聚变实验中是一项重要的诊断技术。开发一种新的重建方法以提高中子半值层成像的分辨率非常重要。本文提出了一种基于总变差（TV）正则化的非线性重建新方法。在新方法中，使用总变差范数作为正则化项来构建用于半值层图像重建的平滑泛函，通过这种方式，将半值层图像重建问题转化为一个泛函最小化问题。此外，引入了一种不动点迭代方案来解决泛函最小化问题。数值实验结果表明，与基于维纳滤波器的线性重建方法相比，总变差正则化非线性重建方法有利于提高重建图像的质量，具有更好的噪声平滑和边缘保持性能。同时，它还能获得高于维纳方法的5μm空间分辨率。
