期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
期号：NCFCSPS
页码：60
出版社：S&S Publications
摘要：Reduced-reference image quality assessment (RRIQA) provides a practical solution forautomatic image quality evaluations in various applications where only partial information about the originalreference image is accessible. In this paper, multifractal analysis is personalized to reduced-reference imagequality assessment (RR-IQA). A novel RR-QA approach is proposed, which measures the difference of spatialarrangement between the reference image and the distorted image in terms of spatial regularity measured byfractal dimension. An image is first expressed in wavelet domain using duel tree complex wavelet transform.Then, fractal dimensions are computed on each wavelet subband and concatenated as a feature vector. Finally,the extracted features are pooled as the quality score of the distorted image using ℓ1 distance. Compared withexisting approaches, the proposed method measures image quality from the perspective of the spatialdistribution of image patterns. The proposed method was evaluated on seven public benchmark data sets.Experimental results have demonstrated the excellent performance of the proposed method in comparison withstate-of-the-art approaches.
