Objective quality assessment of image retargeting based on line distortion

Yichi Zhang, King Ngi Ngan

Abstract: With the proliferation of mobile devices, research on image retargeting is becoming ever more important. However, there is little work on image retargeting quality assessment despite its importance. In this work, we focus on evaluating retargeting quality based on line distortion. Generally, image retargeting results in content loss and shape distortion. Line segments, which are fundamental image structures, are hence discarded or distorted in retargeted images. As a result, we formulate a retargeting quality index consisted of three line distortion measures: line loss, line artifact and line rotation. To test its performance, we have validated it on the public dataset RetargetMe. Experimental results demonstrate that our method outperforms many existent ones and line distortion is a good indicator of retargeting quality.