针对TV图像复原方法中产生的阶梯效应问题,结合传统的差值范数图像复原方法,提出一种四阶P-Laplace图像盲复原算法。该算法将四阶偏微分方程引入P-Laplace图像复原方法中,对图像的边缘和内部平滑区域做了分别处理以缓解TV复原方法中带来的阶梯效应,同时引入参数λ调节复原过程中的保真项,并对偏微分方程做单调灰度变化,进一步改善了图像复原效果,缓解了阶梯效应。实验结果证明,该算法对模糊图像有很好的复原效果,也适用于水下图像和雾天图像的图像复原。
In consideration of the staircase effect in TV image restoration,a method for P-Laplace blind image restoration was proposed,which was combined with the traditional difference norm image restoration method.The algorithm introduced the fourth-order partial differential equations into the P-Laplace image restoration.The image edge and smooth area within were processed separately,in order to alleviate the staircase effect from the TV recovery method.The parameterλwas introduced to regulate the fidelity term in the recovery process and monotone gray change was made in the partial differential equation.The image restoration result was further improved and the staircase effect was alleviated.The experimental results demonstrate that the algorithm has good results in blind image restoration.The algorithm also applies to the image restoration of underwater picture and fog image.