一种新的去除混合噪声的变分模型及其应用  

Novel Denosing Model and its Application for Images Corrupted by Different Types Noises

作　　者：罗志宏[1] 冯国灿[2,3] 

机构地区：[1]中山大学信息科学与技术学院,广州510275 [2]中山大学数学与计算科学学院,广州510275 [3]广东省计算科学重点实验室,广州510275

出　　处：《计算机科学》2015年第5期277-280,314,共5页Computer Science

基　　金：国家自然科学基金资助项目(61272338)资助

摘　　要：由于现有的某些去噪模型仅对某种噪声特别有效,而对其它类型噪声的效果却不够显著,因此提出一种能有效地去除多种噪声的变分模型,它融合了几种经典去噪模型的优点,并在数值求解时采用了高效且无条件稳定的AOS算法。数值实验表明,与现有的一些去噪方法相比,提出的去噪方法耗时少且效果更好。最后给出了解的存在性证明。Due to limitation of traditional variational models for denosing ability, a new variational denosing model for images corrupted by various noise was proposed. Firstly, the fitting terms are fused in the presented model by introducing the parameters,and the benefits of three models are integrated to improve the denoising ability. And the solution can be obtained by applying additive operator splitting （AOS） numerical algorithm. The experimental results demonstrate that the proposed model is effective for different types of noises. Lastly the proof on the existence of solution of the model was given.

关 键 词：图像去噪 变分模型 AOS算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]