Parameter estimation for image deblurring
Yongfei Gao, Zelong Wang, Jubo Zhu · 2014
Blurred images usually come from all kinds of imaging equipments, which may provide important prior information about the possible MTF models with unknown parameters. Based on this prior, we aim to estimate their corresponding parameters for image deblurring. From the fractal model of the original distinct image and the image degradation model, we firstly analyze the statistical character of the blurred image; and then we estimate the noise level by the high frequency energy of the blurred image. For the given MTF degradation model, we estimate the fractal parameters and the MTF parameters by Maximum Likelihood Estimation (MLE), which is achieved numerically by alternating optimization scheme.