Optimizing Photo Composition

TLDR

Aesthetic images evoke an emotional response that goes beyond mere visual appreciation. The study develops a computational approach to evaluate composition aesthetics and proposes an optimization method to generate maximally aesthetic images. The method uses composition guidelines, a crop‑and‑retarget operator to reposition salient regions, and an optimization algorithm to produce improved images, which is validated experimentally. Experiments demonstrate that the method effectively enhances image composition aesthetics.

Abstract

Abstract Aesthetic images evoke an emotional response that transcends mere visual appreciation. In this work we develop a novel computational means for evaluating the composition aesthetics of a given image based on measuring several well‐grounded composition guidelines. A compound operator of crop‐and‐retarget is employed to change the relative position of salient regions in the image and thus to modify the composition aesthetics of the image. We propose an optimization method for automatically producing a maximally‐aesthetic version of the input image. We validate the performance of the method and show its effectiveness in a variety of experiments.