Image Retargeting Quality Assessment Based on Registration Confidence Measure and Noticeability-Based Pooling

Nowadays, image retargeting approaches have been widely applied to adapt images of various resolutions to heterogenous display devices. To assess the quality of the retargeted images, image retargeting quality assessment (IRQA) has emerged as a critical problem in image quality assessment. In this paper, we address the IRQA problem with a newly proposed framework based on registration confidence measurement (RCM) and noticeability-based pooling (NBP). First, we define the RCM to evaluate the accuracy of image registration, which aligns scenes between the original and retargeted images. We then integrate the proposed RCM with the computed local fidelity of each image block to alleviate the negative influence of inaccurate registration on fidelity measurements. Meanwhile, we present a visual attention fusion (VAF) framework to enhance faces and lines in the saliency map, which are observed to be highly sensitive in the human visual system (HVS). Finally, we propose the NBP strategy, which aggregates the local fidelity of each image block into the overall quality of the retargeted image. Specifically, the NBP strategy sets larger quality ranges for the regions where the visual distortions are more accessible to HVS to reflect the easy noticeability of these regions. Experimental results on the MIT RetargetMe and CUHK datasets demonstrate that the proposed IRQA metric based on RCM and NBP outperforms the state-of-the-art IRQA metrics.