EDGE-PRESERVING INTERPOLATION OF DIGITAL IMAGES USING FUZZY INFERENCE

This paper presents a novel edge preserving interpolation method for d igital images. This new method reduces drastically the blurring and ja ggy artifacts at the high-contrast edges, which are generally found in the interpolated images using conventional methods. This high perform ance is achieved by two proposed operations: a fuzzy-inference based e dge preserving interpolator and a highly oblique edge compensation sch eme developed based on an edge orientation detector. The former synthe sizes the interpolated pixels to match the image local characteristics . Hence, edge sharpness can be retained. However, due to the small foo tage of the fuzzy interpolation method, it cannot avoid edge jaggednes s along the highly oblique edges that have very sharp angles against o ne of the coordinates. Therefore, a segment matching technique is deve loped to identify precisely the orientation of the highly oblique edge s. Combining these two techniques, we improve significantly the visual quality of the interpolated images, particularly at the high-contrast edges. Both the synthesized images (such as letters) and the natural scenes (captured by camera) have been tested and the results are very promising. (C) 1997 Academic Press.