Browsing by Subject "mixed method"

Sort by: Order: Results:

Now showing items 1-1 of 1
  • Virtanen, Toni; Nuutinen, Mikko; Häkkinen, Jukka (2020)
    Image quality markedly affects the evaluation of images, and its control is crucial in studies using natural visual scenes as stimuli. Various image elements, such as sharpness or naturalness, can impact how observers view images and, more directly, how they evaluate their quality. To gain a better understanding of the types of interactions between these various elements, we conducted a study with a large set of images with multiple overlapping distortions, covering a wide range of quality variation. Observers assigned a quality rating of the images on a 0–10 scale and gave a verbal description explaining the elements on which their rating was based. A regression model predicting image quality ratings using 68 attributes uncovered the link between verbal descriptions and quality ratings and the importance of the image quality rating for each of the 68 image attributes. Brightness, naturalness, and good colors seem to be related to the highest image quality preference. However, the most important elements for predicting good image quality were related to image fidelity such as graininess and sharpness. This indicates that a certain level of image fidelity must be achieved before more subjective associations with, for instance, naturalness can emerge. Of the attributes, 72% had a negative impact on the preference judgment. This negative bias may be due to the fact that there are more ways that observers can perceive an image to fail than to excel when they are asked to evaluate image quality.