【作者】 柳建军； 肖庭延； 王喆；

【Author】 Liu Jian-jun, Xiao Ting-yan,Wang Zhe(Shanghai University School of Science, Shang Hai 200436; Hebei University of Technology School of Science, TianJin 300130;Hebei University of Technology School of electrical engineering, TianJin 300130

【机构】 上海大学理学院； 河北工业大学理学院； 河北工业大学电气学院；

【摘要】 针对噪声水平未知的情况,改进文献提出的双参数(a、N)图像恢复正则化框架,实现正则参数口基于L-曲线准则迭代确定、共轭梯度最小二乘法(CGLS)迭代次数N由问题精度要求自适应产生及基于粗糙初值的正则参数迭代初值的快速改进。数值试验得到较好的恢复效果,改进信噪比(ISNR)普遍提高0.3db以上。同时,本算法程序全部应用Matlab语言在微机上实现,特别希望对在微机上实现实时高效图像恢复工作有一定的促进作用。更多还原

【Abstract】 In this paper, an improved combining regularization framework of two parameters type, proposed by R.Youmaran and A.Adler, is presented and discussed for stable image restoration without knowing noise level of the input data. Some details of the improvements include the adoption of well-known L-curve criterion with a speed-up technique for a rough initial value of regularization parameter and the iteration number of CGLS method is determined adaptively by precision of problems. The numerical experiments results have shown good restoration effect, and values of ISNR are improved upon 0.3 db generally. All the numerical experiments were achieved on personal computer in Matlab language and we wish to give a hand on these works.更多还原