Age-specific perceptual image quality assessment

Yinan Wang, Andrei Chubarau, Hyunjin Yoo, Tara Akhavan, James J. Clark

Abstract: With the development of image-based applications, assessing the quality of images has become increasingly important. Although our perception of image quality changes as we age, most existing image quality assessment (IQA) metrics make simplifying assumptions about the age of observers, thus limiting their use for age-specific applications. In this work, we propose a personalized IQA metric to assess the perceived image quality of observers from different age groups. Firstly, we apply an age simulation algorithm to compute how an observer with a particular age would perceive a given image. This age simulation algorithm adapts the input image according to an age-specific contrast sensitivity function (CSF), which predicts the reduction of contrast visibility associated with the aging eye. Then, we combine the age simulation algorithm with existing IQA metrics to calculate the age-specific perceptual image quality score. To validate the effectiveness of our combined model, we conducted psychophysical experiments in a controlled laboratory environment with young (18-29 y.o.), middle-aged (30-54 y.o.), and older (55+ y.o.) adults, measuring their image quality preferences for 84 test images through pairwise comparisons. The statistical analysis shows that the predictions by our age-specific IQA metric are well correlated with the collected subjective IQA results from our psychophysical experiment.