Abstract
This paper presents a method for learning artistic portrait lighting template from a dataset of artistic and daily portrait photographs. The learned template can be used for (1) classification of artistic and daily portrait photographs, and (2) numerical aesthetic quality assess- ment of these photographs in lighting usage. For learning the template, we adopt Haar-like local lighting contrast features, which are then ex- tracted from pre-defined areas on frontal faces, and selected to form a log-linear model using a stepwise feature pursuit algorithm. Our learned template corresponds well to some typical studio styles of portrait pho- tography. With the template, the classification and assessment tasks are achieved under probability ratio test formulations. On our dataset com- posed of 350 artistic and 500 daily photographs, we achieve a 89.5% classification accuracy in cross-validated tests, and the assessment model assigns reasonable numerical scores based on portraits’ aesthetic quality in lighting.