一种自适应正则化技术的图像复原方法  

Image restoration method based on adaptive regularization technology

作　　者：苗晴[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：《电子设计工程》2014年第18期169-171,175,共4页Electronic Design Engineering

摘　　要：针对降质图像的复原问题,在正则化技术解决病态性基础上提出了一种有效的自适应图像复原算法。该方法充分考虑了图像的局部特性,引入了自适应加权矩阵,采用迭代的方法改善算法的收敛性,计算中给予复原图像一定的限制。计算机仿真结果表明,该方法可有效克服模糊退化并再现了原始图像的重要信息,复原图像在峰值信噪比和主观视觉效果方面都有明显的提高。Aiming at the restoration of degraded image, an effective adaptive approach to image restoration was proposed based on regularization technology for dealing with ill-posed problems. This method gave full consideration to local characteristic of the image,introduced adaptive weighted matrices,and adopted iterative algorithm to improve convergence. And the restored image was limited in the computation. Computer simulations showed that this proposed method could effectively overcome the blurring degradation and properly retrieve the main information of original image,and the PSNR （peak signal to noise ratio） and subjective visual effect of the restored image were improved significantly.

关 键 词：图像复原 正则化 自适应 迭代 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]