基于一致增强异性扩散模型的钞票图像恢复方法

摘要

Method of image restoration based on partial differential equations is presented. Several image in-painting models based on partial differential equations ( PDE) are analyzed. According to features of dirty banknote ' s image, and select the coherence-enhancing diffusion model for repairing the bill image. The experimental results show that using this model results both in the smooth areas and the detail areas of the bill image can be got good inpainted.%提出一种基于偏微分方程的钞票图像恢复方法.通过分析常用的几种基于偏微分方程( PDE)的图像恢复模型,结合赃污钞票图像特点,最后选择一致增强异性扩散模型,并提出了一种该模型的数值解法对脏污钞票图像进行修复.实验结果表明,用这种模型可以对钞票图像的平滑区域和边缘细节均有比较好的修复能力.