Region-based image retargeting quality assessment

Yichi Zhang, King Ngi Ngan

Abstract: The tremendous growth in mobile devices has resulted in huge generation and consumption of digital images. The image quality evaluation is hence an important issue for mobile media applications. In this work, we focus on the quality evaluation of images under content-aware retargeting, in which the sizes of images may differ from each other. Shape distortion and content information loss are two main factors in the evaluation of retargeting quality [1]. We have proposed a region-based framework to evaluate shape distortion and information loss caused by retargeting. The proposed algorithm is validated on the public database RetargetMe [2]. Experimental results demonstrate that this region-based quality assessment algorithm outperforms others based on pixels.