引入连续性强度和置信度因子的快速图像修复

Fast image inpainting algorithm introducing continuous strength and confidence factor

传统的基于偏微分方程的迭代式图像修复算法的运算量较大,修复所耗时间较长,使得这些修复技术很难实际应用。而基于水平集的快速行进法可以快速有效地修复数字图像中的破损区域,但对图像的边缘信息保持不佳。针对这一问题,提出一种改进方案。在权函数设计时引入连续性强度来保持边缘信息,并采用等照度线方向来评估两像素点的位置关系。在对单点进行修复时,引入置信度因子对插值点进行加权。实验结果表明,该算法在保证运行效率的同时,很好地提高了修复效果。

The traditional iterative image inpainting algorithm which is based on partial differential equations can hardly be used in practice, for its complicated computation and unsatisfied time consumption. The fast marching method （FMM） which is based level set can inpaint the damaged area fast and effective, but it can not prevent the edge well. To solve this problem, an improved algorithm is presented. Continuity strength is introduced when weight function is designed and the factor which contains isophote is adopted to estimate the position between each pixels. When inpainting a single pixel, confidence factor is introduced to weight the interpolating point. Experiments show that the proposed algorithms can ensure the computation efficiency, and at the same time, it well improves the inpainting quality.