Adaptive image scaling based on local edge directions

An image scaling process is necessary when the resolution of a stream image is different from the screen resolution of a digital display device. Image scaling addresses the problem of generating an image of new resolution from a source image. Conventional image interpolation methods suffer blurring problems in edge regions, so it is hard to produce sharp and clear visual effects. In this paper, we propose an adaptive image interpolation algorithm which keeps the edges sharp and provides good image quality. In the region around a pixel to be interpolated this algorithm checks whether there is an edge or not. An interpolation method is then selected according to the existence and the direction of an edge in that region. Experimental results demonstrate that good image quality can be achieved.