From Just Noticeable Differences to Image Quality - LS2N - équipe IPI ( Image Perception Interaction ) Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

From Just Noticeable Differences to Image Quality

Résumé

Distortions can occur due to several processing steps in the imaging chain of a wide range of multimedia content. The visibility of distortions is highly correlated with the overall perceived quality of a certain multimedia content. Subjective quality evaluation of images relies mainly on mean opinion scores (MOS) to provide ground-truth for measuring image quality on a continuous scale. Alternatively, just noticeable difference (JND) defines the visibility of distortions as a binary measurement based on an anchor point. By using the pristine reference as the anchor, the first JND point can be determined. This first JND point provides an intrinsic quantification of the visible distortions within the multimedia content. Therefore, it is intuitively appealing to develop a quality assessment model by utilizing the JND information as the fundamental cornerstone. In this work, we use the first JND point information to train a Siamese Convolutional Neural Network to predict image quality scores on a continuous scale. To ensure generalization, we incorporated a white-box optical retinal pathway model to acquire achromatic responses. The proposed model, D-JNDQ, displays a competitive performance on cross dataset evaluation conducted on TID2013 dataset, proving the generalization of the model on unseen distortion types and supra-threshold distortion levels.
Fichier principal
Vignette du fichier
acm_mm_djndq (4).pdf (1.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03127756 , version 1 (01-02-2021)
hal-03127756 , version 2 (06-10-2022)

Identifiants

Citer

Ali Ak, Andreas Pastor, Patrick Le Callet. From Just Noticeable Differences to Image Quality. 2nd Workshop on Quality of Experience in Visual Multimedia Applications (QoEVMA ’22), October 14 2022, Lisboa, Portugal. ACM,, Oct 2022, Lisbon, Portugal. ⟨10.1145/3552469.3555712⟩. ⟨hal-03127756v2⟩
174 Consultations
545 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More