数据保真项与稀疏约束项相融合的稀疏重建  

Sparse reconstruction method based on integrating data fidelity term and sparse constraint term

作　　者：高红霞[1,2] 谢剑河 曾润浩 吴梓灵 马鸽 

机构地区：[1]华南理工大学自动化科学与工程学院,广东广州510640 [2]华南理工大学精密电子制造装备教育部研究中心,广东广州510640 [3]广州大学机械与电气工程学院,广东广州510006

出　　处：《光学精密工程》2017年第9期2437-2447,共11页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.61403146);广州市科技计划项目(No.201707010054);中央高校基本科研业务费资助项目(No.2015ZM128)

摘　　要：本文针对低光子计数成像过程中产生的泊松高斯混合噪声,提出了一种数据保真项与稀疏约束项相融合的稀疏重建方法。首先,基于泊松高斯噪声相互独立的混合噪声模型,建立了数据保真项与稀疏约束项相融合的稀疏重建目标函数;在图像块聚类的基础上,应用改进贪婪算法实现类内稀疏分解和字典更新;最后,稀疏分解和字典更新交替迭代求解干净图像。针对强烈泊松高斯噪声污染图像的重建实验显示,本文方法与对比方法相比,重建结果的PSNR值平均提升了5.5%,MSSIM值也有明显提升。这些结果表明:本文方法对具有强烈泊松高斯混合噪声的图像有较好的图像复原和噪声去除效果。Aiming at the process of low-dose photon counting imaging with Poisson-Gaussian mixed noise,a sparse reconstruction method of integrating data fidelity term and sparse constrait term is proposed.Firstly,based on the hypothesis that Poisson and Gaussian noise are mutually independent,the sparse reconstructing objective function based on integrating data fidelity term and sparsity constraint term is established.Based on patch clustering,the improved greedy algorithm is applied to implement sparse decomposition and dictionary update.Finally,a clean image is obtained byalternating iteration.Contrast experiments on images corrupted with strong Poisson-Gaussian mixed noise show that the average PSNR of image reconstructed by the proposed method increased by 5.5% more than those of the contrast methods,moreover,their MSSIM increased significantly.The experiment results demonstrate that the proposed method has better image restoration and denoising effect for low photon counting image with strong Poisson-Gaussian mixed noise.

关 键 词：稀疏重建 字典学习 混合噪声 强噪声 低光子计数成像 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TP242.6[自动化与计算机技术—计算机科学与技术]