PROJECT TITLE :
A Perceptually Weighted Rank Correlation Indicator for Objective ImageQuality Assessment - 2018
In the field of objective image quality assessment (IQA), Spearman's ? and Kendall's t, that straightforwardly assign uniform weights to all quality levels and assume that each combine of pictures is sortable, are the 2 most popular rank correlation indicators. These indicators will successfully live the average accuracy of an IQA metric for ranking multiple processed pictures. But, 2 important perceptual properties are ignored. Initial, the sorting accuracy (SA) of high-quality pictures is usually a lot of vital than that of poorquality images in several real-world applications, where only prime-ranked pictures are pushed to the users. Second, because of the subjective uncertainty in making judgments, two perceptually similar images are usually barely sortable, and their ranks do not contribute to the evaluation of an IQA metric. To more accurately compare different IQA algorithms, during this Project, we explore a perceptually weighted rank correlation indicator, which rewards the potential of correctly ranking high-quality pictures and suppresses the attention toward insensitive rank mistakes. Specifically, we tend to concentrate on activating a “valid” pairwise comparison of images whose quality difference exceeds a given sensory threshold (ST). Meanwhile, each image pair is assigned a unique weight that's determined by both the standard level and rank deviation. By modifying the perception threshold, we tend to can illustrate the sorting accuracy with a refined SA-ST curve instead of one rank correlation coefficient. The proposed indicator offers new insight into interpreting visual perception behavior. Furthermore, the applicability of our indicator is validated for recommending strong IQA metrics for each degraded and enhanced image information.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here