数据驱动紧框架在灰色图像去噪中的应用  

Application of data-driven tight frame in gray image denoising

作　　者：范立静 王聪[1] 

机构地区：[1]河海大学理学院,江苏南京211100

出　　处：《电子设计工程》2017年第15期180-183,188,共5页Electronic Design Engineering

基　　金：国家自然科学基金项目(11101120);中央高校基本科研业务费专项资金资助项目(2015B38014)

摘　　要：针对去除灰色图像中的泊松噪声从而进一步进行图像分析的目的,采用了基于数据驱动紧框架的含泊松噪声的图像去噪变分模型,并通过了重新赋权的分裂Bregman算法解该模型。结合Matlab仿真实验以及PSNR指标对该算法的图像去噪效果进行评估,评估结果表明该算法可行、有效。In this paper, we proposed a data-driven tight frame based variational model for image denoising with Poisson noise, in order to remove Possion noise from noisy gray image and analyze image data further. And we proposed reweighted split Bregman algorithm to solve this model. Combining with supporting numerical experiments and PSNR indicators, we assessed the model evaluation results. Results showed that the algorithm was feasible and effective.

关 键 词：数据驱动紧框架 泊松噪声 图像去噪 分裂Bregman算法 

分 类 号：TN919.8[电子电信—通信与信息系统]