图像复原中正则化参数的自适应选择方法

大多数图像复原问题都具有病态性质，需要利用正则化技术对问题加以约束。约束最小二乘法中正则化参数能够对求解后图像的精度和平滑程度加以调节并使两者之间取得平衡，与复原图像质量的好坏有着直接的关系。提出了一种自适应选择正则化参数（ASRP）方法，根据图像边缘信息自适应地确定正则化参数值，保证了复原结果为全局最优解，同时实现了复原图像边缘细节的良好保持。通过实验验证了该算法的正确性和可行性。

Adaptive selection of regularization parameter in image restoration

Most problems in image restoration are ill-posed, so regularization technique is needed to restrict the problems. Regularization parameter used in the constrained least square method can control the trade-off between fidelity to the data and smoothness of the solution, and effect on the quality of the restored image directly. A method of adaptive selection of the regularization parameter (ASRP) is proposed. It can obtain the regularization parameter adaptively according to the edge information of the image, guarantee the restored image is the best result in the total field, and keep the edge detail of the restored image well. The experiment results show that this method is correct and feasible.