This study intends to measure the degree of correlation/similarity between the subjective gaze points (obtained by eye tracking experiments) and the objective interest points of several well-known detectors such as Harris and SURF. For each of the latter, we look for the best setting in term of maximization of likeness with the gaze points. For this task, the Earth Mover's Distance (EMD) 1 is used to compare two data-sets with different cardinalities. We also used ANOVA to measure the influence of each parameter involved in the detectors' settings as well as the possible introduced bias. The conclusions of this study are related to the suitability of each detector to estimate the subjective gaze points.

Il est utile de pouvoir quantifier les dégradations perçues afin de juger l'intérêt de nouveaux algorithmes de compression, tatouage ou des techniques de transmission. Nous proposons d'évaluer les performances d'un lot de métriques de qualité d'images couleurs en visant la corrélation avec le jugement humain. Le but escompté est de faciliter le choix d'une métrique parmi les nombreuses disponibles, en fournissant des scores de performance standards et exhaustifs. Pour cette étude quatre bases de données d'images sont utilisées et analysées afin d'élargir au maximum le jeu d'images tests et de mesurer la flexibilité des métriques. Mots clefs Métrique de qualité, système visuel humain, qualité d'expérience, évaluation objective, tests subjectifs.

This paper proposes a global approach of JPWL (ISO/IEC 15444-11) image transmission over a realistic wireless channel able to ensure the best Quality of Service (QoS). In order to exploit the channel diversity, we consider a ClosedLoop MIMO-OFDM scheme with different precoder designs. In particular, the high flexibility of QoS precoder allows taking into account the scalability of JPWL jointly with the instantaneous MIMO channel status. This increases the visual quality of received images. The monitoring of the quality is made by a reduced-reference metric (QIP) based on object's saliency and interest point, both linked to human perception. It is performed in association with a robust JPWL decoder to determine the optimal decoding configuration in terms of PSNR. The proposed scheme provides very good results and its performance is shown through a realistic wireless channel.

Quality of Experience (QoE) is a widely used notion nowadays because the end-user has been re-integrated in the quality loop. Subjective experiments are tedious and time consuming but to date they are the main way to have the human judgment. An important effort has been put on the development of metric estimating the QoE. So, in this paper, we propose a new image quality metric based on two concepts: the interest points and the objects saliency on color images. This metric is constructed by taking advantage of the variability of the interest points impact function of the image impairment and also the hierarchical attention of a human observer. This combination helps in giving more importance to the variability of the most salient regions and reducing the influence of regions having less visual importance.The results show a high correlation between the metric scores and the human judgment and a better quality range than well-known metrics.

No abstract