PROJECT TITLE :

Fractal Analysis for Reduced Reference Image Quality Assessment - 2015

ABSTRACT:

In this paper, multifractal analysis is adapted to reduced-reference image quality assessment (RR-IQA). A novel RR-QA approach is proposed, which measures the distinction of spatial arrangement between the reference image and therefore the distorted image in terms of spatial regularity measured by fractal dimension. An image is 1st expressed in Log-Gabor domain. Then, fractal dimensions are computed on each Log-Gabor subband and concatenated as a feature vector. Finally, the extracted features are pooled as the standard score of the distorted image using l1 distance. Compared with existing approaches, the proposed method measures image quality from the angle of the spatial distribution of image patterns. The proposed technique was evaluated on seven public benchmark data sets. Experimental results have demonstrated the superb performance of the proposed methodology compared with state-of-the-art approaches.