SUBPIXEL EDGE LOCALIZATION AND THE INTERPOLATION OF STILL IMAGES

In this paper, we present a nonlinear interpolation scheme for still i mage resolution enhancement. The algorithm is based on a source model emphasizing the visual integrity of detected edges and incorporates a novel edge fitting operator that has been developed for this applicati on. A small neighborhood about each pixel in the low-resolution image is first mapped to a best-fit continuous space step edge, The bilevel approximation serves as a local template on which the higher resolutio n sampling grid can then be superimposed (where disputed values in reg ions of local window overlap are averaged to smooth errors), The resul t is an image of increased resolution with noticeably sharper edges an d, in all tried cases, lower mean-squared reconstruction error than th at produced by linear techniques.