Image interpolation using visual attention model and particle swarm optimization

Abstract

In this study, a new edge-directed image interpolation approach using visual attention model and particle swarm optimization (PSO) is proposed. First, a high-quality saliency map of an image to be interpolated is generated by the proposed visual attention model in an effective manner. Then, based on the saliency map, bilinear interpolation and the proposed PSO interpolation are employed for non-saliency blocks (non-ROIs) and saliency blocks (ROIs), respectively, to obtain the final interpolation results. The proposed approach is applicable for image interpolation with arbitrary magnification factors (MFs). Based on the experimental results obtained in this study, the interpolation results of the proposed approach are better than those of three comparison methods.