A FAST DIGITAL IMAGE INPAINTING ALGORITHM USING MONTE CARLO METHODS
Cheng Cun · Chinese Journal of Engineering Geophysics · 2006
Image inpainting refers to the ill-posed problem of filling in the missing data in digital images by interpolating from the vicinity.It is shown in this paper how inpainting can be performed by means of random simulation,which we call the Monte Carlo method.We will differentiate between-narrow-zonal inpainting domains and wide-block inpainting domains.For the narrow zonal inpainting domains we will use random wandering method,and for the wide-block inpainting domains we will use the random simulation of boundary integration to interpolate it.Our method is computationally less taxing than the classical diffusion method,and yields a solution that may have strong edges.