A photograph reconstruction by object retargeting for better composition

Abstract

In digital photography, composition rules are essential for capturing highly aesthetic photographs. Aesthetic images create a response of visual appreciation to the viewers. Rule-of-thirds (RoT) is the most important and basic rule accepted by photographers for taking aesthetically pleasing shots. In this paper, a novel computational approach, "Retarget Object for Implementation of Rule-of-Thirds", (ROI-RT) is presented. The ROI-RT technique automatically improves the composition of the photographs according to the photo composition guidelines. For achieving the mentioned task, the key adopted steps are main object segmentation by alpha matting, texture synthesis for occluded background, features extraction for ROI-RT, and retargeting the main object on synthesized background to reproduce a photograph which respects the composition rule RoT, in photography. Experimental results performed on various sets of photographs achieve a compositional accuracy rate of 95 % by proposed approach. Aesthetic scores for the resultant reconstructed photographs are attained by average subjective rating (SR) of 30 people and also computed by online evaluation methods of OSCAR and ACQUINE. Statistical significant test is applied and obtained P---valueź=ź0.0001ź<ź0.05 shows a promising performance of our ROI-RT compositional scheme. A comparison with existing photo composition techniques shows that ROI-RT provides us a better aesthetic photographic composition.