Abstract
Most of real-world image distortions are multiply distortion rather than single distortion. To address this issue, in this paper we propose a quaternion wavelet transform (QWT) based full reference image quality assessment (FR IQA) metric for multiply distorted images, which jointly considers the local similarity of phase and magnitude of each subband via QWT. Firstly, the reference images and distorted images are decomposed by QWT, and then the similarity of amplitude and phase are calculated on each subband, thirdly the IQA metric is constructed by the weighting method considering human visual system (HVS) characteristics, and lastly the scores of each subband are averaged to get the quality score of test image. Experimental results show that the proposed method outperforms the state of art in multiply distorted IQA.
Highlights
With the large-scale use of intelligent mobile phone and computer in our modern society, evaluating the images after compression and transmission has become an increasingly important issue, and image quality assessment (IQA) has the great practical significance.IQA can be divided into three types: full-reference IQA, reduced-reference IQA, and noreference IQA
Motivated by recent progress in IQA and quaternion wavelet transform (QWT), in this paper we propose a QWT based full-reference IQA metric called QWT-IQA, which jointly takes into account the local similarity of phase and magnitude of each subband via quaternionic wavelet transform
There are several measures to evaluate the correlation between the quality scores and difference mean opinion score (DMOS), such as Spearman rank order correlation coefficient (SROCC), Pearson linear correlation coefficient (PLCC), Kendall’s rank order correlation coefficient (KROCC), and Root mean squared error (RMSE)
Summary
With the large-scale use of intelligent mobile phone and computer in our modern society, evaluating the images after compression and transmission has become an increasingly important issue, and image quality assessment (IQA) has the great practical significance. The structural similarity (SSIM) [1] index was proposed base on the human visual system (HVS) characteristics. Zhang et al [3] proposed a feature similarity (FSIM) index that uses phase congruency to weight the quality score based on SSIM index. Tang et al [11] proposed a novel dual-tree QWT based blind camera image quality assessment metric. Motivated by recent progress in IQA and QWT, in this paper we propose a QWT based full-reference IQA metric called QWT-IQA, which jointly takes into account the local similarity of phase and magnitude of each subband via quaternionic wavelet transform. In our QWT-IQA, we make use of a weighting method to compute the image quality score, inspired by human visual characteristics. A lot of experimental results demonstrate that our proposed QWT-IQA outperforms existing full-reference IQA method.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
