The Effects of Depth of Field on Subjective Evaluation of Aesthetic Appeal and Image Quality of Photographs

Abstract

Aesthetic appeal and image quality are two important features of photographs, which play the dominant role when people clean their albums. Currently, the objective image quality assessment has been documented very well whereas the objective aesthetic appeal assessment algorithms are not developed well enough. This paper first subjectively evaluated image quality and aesthetic appeal separately of 339 photographs across different levels of depth of field. With the subjective data, the paper proposed two mathematical models to predict the subjective aesthetic appeal from subjective image quality. More specifically, depth of field, as a common photographic feature, was investigated to see how it influenced aesthetic appeal and image quality. 32 participants were asked to score for the aesthetic appeal and image quality. With these subjective scores, we used two methods - linear regression and deep neural networks - to build models separately to predict aesthetic appeal from image quality. We found that both models worked well on the valid dataset and the performance of the deep neural networks model was better than the linear regression model.