A framework for improvement of importance map for image retargeting assisted by light field images

Abstract

Image retargeting methods change the size of images to an arbitrary resolution while protecting visually important regions from distortion. Since retargeting methods deform contents of an image based on these importance, importance calculation methods suitable for image retargeting is needed. In this paper, we propose a framework to improve an importance map by using depth and segmentation information obtained from light field images. Depth information is used for considering the distance of objects from a camera. Segmentation information is used for maintaining visual consistency. Experimental results show that importance improved by our framework leads to better retargeting results.