基于空域正则化的模糊图像复原方法  

Restoration method of blurred image based on regularization in spatial domain

作　　者：苗晴[1] 杨灵娥[1] 

机构地区：[1]佛山科学技术学院信息科学与数学系,广东佛山528000

出　　处：《佛山科学技术学院学报（自然科学版）》2008年第2期5-7,18,共4页Journal of Foshan University(Natural Science Edition)

摘　　要：以解决病态问题的正则化技术为基础,针对模糊图像的复原问题提出了一种新的空间域复原方法。在空间迭代运算中引入自适应的正则化参数,使其自动修正到最优,通过锐化图像进行后续处理,由此增强了原图像中重要的信息及边缘纹理部分。计算机仿真结果表明,与传统的迭代正则化方法相比,该方法的复原图像在改进信噪比数值(ISNR)和主观视觉效果上都有明显提高。On the basis of the regularization technique for dealing with unhealthy problems, a new spatial domain approach to blurred image restoration is proposed in this paper. In the space iterative computations, the regularized parameter can regulate automatically to the appropriate value due to its adaptive character. Finally, the main information of original image and the edges and textures are properly retrieved by image sharpening processing. Computer simulations show that, compared with traditional iterative regularization method, this proposed .approach is better in the ISNR （improved signal to noise ratio） and subjective visual effect of the restored image.

关 键 词：图像复原 正则化 空域 图像锐化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]