Context-based adaptive image resolution upconversion

Abstract

We propose a practical context-based adaptive image resolution upconversion algorithm. The basic idea is to use a low- resolution (LR) image patch as a context in which the missing high- resolution (HR) pixels are estimated. The context is quantized into classes and for each class an adaptive linear filter is designed using a training set. The training set incorporates the prior knowledge of the point spread function, edges, textures, smooth shades, etc. into the upconversion filter design. For low complexity, two 1-D context- based adaptive interpolators are used to generate the estimates of the missing pixels in two perpendicular directions. The two direc- tional estimates are fused by linear minimum mean-squares weight- ing to obtain a more robust estimate. Upon the recovery of the miss- ing HR pixels, an efficient spatial deconvolution is proposed to deblur the observed LR image. Also, an iterative upconversion step is performed to further improve the upconverted image. Experimen- tal results show that the proposed context-based adaptive resolution upconverter performs better than the existing methods in both peak SNR and visual quality. © 2010 SPIE and IS&T.