Saliency-based Adaptive Scaling for Image Retargeting

In this paper, we propose a novel algorithm for image retargeting based on adaptive scaling methods. Our algorithm starts by adaptively partitioning the input image into number of strips according to the combined saliency map, which contains both gradient information and visual saliency to measure significant regions and is also used to guide the sampling process when scaling image strips. Experimental results show that our method can achieve better results than other content-aware image retargeting operators.