How Does Image Content Affect the Added Value of Visual Attention in Objective Image Quality Assessment?

Hantao Liu (1) , Ulrich Engelke (2) , Junle Wang (3) , Patrick Le Callet (3) , Ingrid Heynderickx (2)

1 TU Delft - Delft University of Technology
2 Philips Research Laboratories [Eindhoven]
3 irccyn-ivc

Our previous research [1] has demonstrated that adding natural scene saliency (NSS) obtained from eye-tracking data may improve an objective metrics performance in predicting perceived image quality. In this letter, we further investigate the image content dependency of this improvement. Results show that the variation in saliency between observers highly depends on image content, and that this variation predicts the extent to which a certain image may profit from adding saliency in the objective image quality assessment.

Mots clés: Eye tracking; image quality assessment; objective metric; saliency map; visual attention

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

Hantao Liu, Ulrich Engelke, Junle Wang, Patrick Le Callet, Ingrid Heynderickx. How Does Image Content Affect the Added Value of Visual Attention in Objective Image Quality Assessment?. IEEE Signal Processing Letters, 2013, 20 (4), pp. 355-358. ⟨10.1109/LSP.2013.2243725⟩. ⟨hal-00788386⟩