Reduced reference image quality assessment using regularity of phase congruency

Delei Liu , Yong Xu , Yuhui Quan , Patrick Le Callet

In this paper, a reduced-reference image quality assessment metric is proposed, which measures the difference of the regularity of the phase congruency (PC) between the reference image and the distorted image. The proposed model adopts a three-stage approach. The PC of the image is first extracted, then the fractal dimensions are computed on PC as the image features that characterize the image structures from the view of the spatial distribution. Finally the image features are pooled as the quality score using ℓ1 distance. The proposed approach is evaluated on seven public benchmark databases. Experimental results have demonstrated the excellent performance of the proposed approach.

Mots clés: Reduced-reference image quality assessment; Fractal dimension; Phase congruency

Domaines: Traitement du signal et de l'image [eess.SP]

Delei Liu, Yong Xu, Yuhui Quan, Patrick Le Callet. Reduced reference image quality assessment using regularity of phase congruency. Signal Processing: Image Communication, 2014, Signal Processing: Image Communication, 8 (29), pp.844-855. ⟨10.1016/j.image.2014.06.007⟩. ⟨hal-01074889⟩