A visual attention approach to image interpolation

In this study, a new image interpolation approach using the visual attention model is proposed. First, the high-quality saliency map of an image to be interpolated is generated in an effective manner. Then based on the saliency map, the bilinear interpolation method and a proposed interpolation method are employed for non-saliency blocks and saliency blocks, respectively, to obtain the final interpolation results. Based on the experimental results obtained in this study, the interpolation results of the proposed method are better than the corresponding results of the three comparison methods.