基于破损区域分类的自适应扩散模型  

Adaptive diffusion model based on damaged region classification

作　　者：段维夏[1] 聂洪玉[1] 王猛[1] Duan Weixia;Nie Hongyu;Wang Meng(College of Information Science & Technology, Southwest Jiaotong University, Chengdu 611156 , China)

机构地区：[1]西南交通大学信息科学与技术学院,成都611756

出　　处：《计算机应用研究》2016年第9期2823-2826,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61461048);国家社会科学基金资助项目(12EF119)

摘　　要：为了提高数字图像的修复精度,加快修复速度,提出了一种自适应扩散模型。该模型利用结构张量的最大特征值将破损图像区分为平坦区域、结构信息不明显的区域以及结构信息明显的区域,使模型在不同区域进行相应的扩散;利用结构张量的两个特征值构造了速度函数,使模型在不同区域的扩散速度也不同,从而加快扩散速度并保持图像的结构信息。实验结果表明,该模型不仅可以加快修复速度,而且可以很好地抑制噪声,并且保持图像的结构特征。In order to not only improve the accuracy of digital image inpainting, but also to accelerate inpainting rate, this paper proposed an adaptive diffusion model. According to maximum eigenvalue of structure tensor the flat region, this modelcould distinguish less obvious structure region and the obvious structure region. And in different regions, the model could diffuse in the corresponding ways. Meanwhile, using two eigenvalues of structure tensor, this paper constructed smooth velocity,so that in different regions, the model had different diffusion speed, which could speed up the diffusion and maintains the structural characteristics. Experimental results show that, the model can not only accelerate repainting, but also can denoise effectively, and maintains the structural characteristics of the image.

关 键 词：自适应扩散 破损区域分类 结构张量 结构特征 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]