Improving a single down-sampled image using probability-filtering-based interpolation and improved poisson maximum a posteriori super-resolution

Abstract

ybrid scheme called"hyper-resolution" that integrates imageprobability-filtering-based interpolation and improved Poissonmaximum a posteriori (MAP) super-resolution torespectively enhance high spatial and spatial-frequencyresolutions of a single down-sampled image. A new approach tointerpolation is proposed for simultaneous image interpolation andsmoothing by exploiting the probability filter coupled with apyramidal decomposition and the Poisson MAP super-resolution isimproved with the techniques of edge maps and pseudo-blurring.Simulation results demonstrate that this hyper-resolution schemesubstantially improves the quality of a single gray-level, color,or noisy image, respectively.